Project setup commands

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For US legal or regulatory questions use gov; for papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use the gog CLI (gogcli) for Gmail, Calendar, Drive, Docs, Sheets, Slides, and Contacts. Use when searching Google Workspace, drafting or replying to email, managing calendar events or files, editing Google documents, spreadsheet ranges or presentations, or looking up contacts from a terminal. Do not use for local Office files or sessions without a terminal.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or extract files, or perform any PDF manipulation from the command line.

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Help users craft compelling brand narratives. Use when someone is defining brand strategy, writing company positioning, creating pitch narratives, developing messaging frameworks, or trying to make their company story more memorable.

Transforms technical work into persuasive business-language documents for non-technical stakeholders, including internal announcements, approval proposals, incident explainers, technical-debt cases, product explainers, and investor or partner memos. Use when the user asks to present technical work to the company, explain software to business teams, write a business case, make an approval document, or convert a technical artifact into stakeholder communication in the requested language. Do not use for READMEs, specs, ADRs, external marketing pages, or customer-facing sales copy.

When the user wants to write, rewrite, or improve marketing copy for any page, including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "hero section copy," "this copy is weak," "this sounds like AI," "AI slop," "make it sound human," or "help me describe my product." Drafts never use AI tells like "it's not X, it's Y" reveals, "no X, no Y, no Z" lists, or sentences that trail into extra comma clauses. For email copy, see emails. For popup copy, see popups. For editing existing copy, see copy-editing. For the offer underneath the copy (bonuses, guarantees, value framing), see offers. Claims must be supportable, and a declined claim names the evidence that would unlock it. Diagnoses the input first (blank brief, real voice, or point edit) and changes only what it calls for.

When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market positioning,' or 'competitive positioning.' This skill covers market positioning, ICP definition, messaging architecture, and PMF validation for AI-native products. Do NOT use for technical implementation, code review, or software architecture.

Comprehensive startup idea validation and market analysis tool. Use when users need to evaluate a startup idea, assess market fit, analyze competition, validate problem-solution fit, or determine market positioning. Triggers include requests to "validate my startup idea", "analyze market opportunity", "check if there's demand for", "research competition for", "evaluate business idea", or "see if my idea is viable". Provides data-driven analysis using web search, market frameworks, competitive research, and positioning recommendations.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Work with project documentation and the central knowledge repository (marcioaltoe/secondbrain). Use when editing docs/, CONTEXT.md, specs, ADRs, or task files in any repo with a .secondbrain-project file; when deciding where a documentation change should be committed; when touching secondbrain's mirror, notes, shared or wiki areas; and when research, planning or implementation work could consult or feed the second brain (wiki + qmd search).

Adopt, update, or verify a repository's Context-Driven Baseline through the public Roundfix Baseline Command. Use when preparing a repository for the write-prd/write-tasks/implement pipeline, changing its Baseline Profile, preserving existing instructions, restoring its Repository Skill Set, or confirming that Baseline-owned content is current.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design through one question at a time, then routes the outcome to write-idea, write-prd, write-techspec (refactors/bug fixes), or a direct task.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.

Write a PRD as a durable local artifact at docs/specs/<slug>/_prd.md — research first, clarify with one multiple-choice question at a time, record decisions as ADRs, then write directly without draft-approval rounds.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks.

Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.

Decompose a spec's PRD/TechSpec into a dependency-ordered task graph — vertical-slice task files plus a machine-parseable _tasks.md DAG manifest under docs/specs/<slug>/, including the authored QA gate decision, decided autonomously from the Spec and escalated only when authority, architecture, or blast radius is at stake.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Prepare a spec with Roundfix's Delivery Plan, delegate implementation to Roundfix, monitor the Run or delivery queue, and ask the maintainer only its Pending Question.

Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.

Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.

Author or review software tests and LLM/agent evals; choose test placement and mocks, diagnose flaky CI, or repair brittle suites. Excludes unrelated code review, debugging, CI design, and production observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Use when reviewing whether code has enough operational evidence: structured logs, correlation IDs, metrics, traces, run summaries, error normalization, and safe redaction. Trigger for production readiness reviews, sync/job reviews, incident-prone code, or before delivery of backend workflows. Do not use for visual UI-only review.

Execute the self-contained final QA gate as a Spec's authored terminal `qa` Task — derive a resumable QA matrix from the PRD and task evidence, execute real user flows through every declared surface, probe high-risk user behavior, capture auditable evidence, classify findings by user impact, and write the spec-local dated QA report. Do not use as a substitute for implementation tests or a broad standalone QA knowledge base.

Use Roundfix to plan releases with the read-only Release Plan Command, clean CodeRabbit pull request feedback, diagnose runtime readiness with the Doctor Command, execute a Spec's Task Graph with the Implement Command, monitor Runs through the Supervisor Run Event Stream, reclaim Run storage with the GC Command, archive completed Specs, run its `--follow-up`, `--status` and `--unattended` Skill Modes, and, inside daemon-assigned Batch runs, follow the bounded Review Issue or Task resolution contract.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of the implement-spec loop after a QA pass, or whenever the user asks to archive a spec.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.

Provision and operate DigitalOcean infrastructure with Terraform and doctl — Droplets, VPCs, cloud firewalls, managed PostgreSQL/Valkey, Spaces, Container Registry, load balancers, reserved IPs, and DNS. Use when the user mentions DigitalOcean, doctl, droplets, DOCR, Spaces, DO managed databases, or Terraform state stored on Spaces.

Docker containerization expert: Dockerfile optimization, multi-stage builds, security hardening, Docker Compose orchestration, and production deployment. Use for Dockerfile creation/review, image size issues, container security, networking, and orchestration.

Operate production infrastructure like an experienced engineer — reconcile reality before planning, review the plan before applying, keep one writer on the state, size the blast radius, and back every claim with evidence. Use for Terraform/OpenTofu changes, cloud provisioning, deploys, rollbacks, incident response, runbooks, or when the user says "apply this", "deploy to prod", "infra change", or "devops".

Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.

Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Work with project documentation and the central knowledge repository (marcioaltoe/secondbrain). Use when editing docs/, CONTEXT.md, specs, ADRs, or task files in any repo with a .secondbrain-project file; when deciding where a documentation change should be committed; when touching secondbrain's mirror, notes, shared or wiki areas; and when research, planning or implementation work could consult or feed the second brain (wiki + qmd search).

Adopt, update, or verify a repository's Context-Driven Baseline through the public Roundfix Baseline Command. Use when preparing a repository for the write-prd/write-tasks/implement pipeline, changing its Baseline Profile, preserving existing instructions, restoring its Repository Skill Set, or confirming that Baseline-owned content is current.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design through one question at a time, then routes the outcome to write-idea, write-prd, write-techspec (refactors/bug fixes), or a direct task.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.

Write a PRD as a durable local artifact at docs/specs/<slug>/_prd.md — research first, clarify with one multiple-choice question at a time, record decisions as ADRs, then write directly without draft-approval rounds.

Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Use this skill when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets, Bubbletea views, terminal color palette, keybinding design, panel layout, split panes, terminal dashboard, box-drawing characters, sparklines, progress bars, modal dialogs, focus management, or terminal accessibility.

Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.

Decompose a spec's PRD/TechSpec into a dependency-ordered task graph — vertical-slice task files plus a machine-parseable _tasks.md DAG manifest under docs/specs/<slug>/, including the authored QA gate decision, decided autonomously from the Spec and escalated only when authority, architecture, or blast radius is at stake.

Build interactive Go TUIs with Bubbletea, Elm architecture, Lipgloss, layouts, and keyboard/mouse handling. Excludes plain-text CLIs, web/desktop GUIs, and other TUI frameworks.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Golang CLI application development. Use when building, modifying, or reviewing a Go CLI tool — especially for command structure, flag handling, configuration layering, version embedding, exit codes, I/O patterns, signal handling, shell completion, argument validation, and CLI unit testing. Also triggers when code uses cobra, viper, or urfave/cli. For cobra-specific APIs → See `samber/cc-skills-golang@golang-spf13-cobra` skill; for viper configuration layering → See `samber/cc-skills-golang@golang-spf13-viper` skill.

Golang concurrency design — goroutine lifecycle and leak prevention, channels and `select`, channel ownership and direction, `sync.Mutex`/`RWMutex`/`sync.Map`/`sync.Once`/atomics, `errgroup`, `singleflight`, worker pools, and fan-out/fan-in pipelines. Use when writing or reviewing concurrent Go code, when choosing between channels and mutexes, when protecting a shared map or counter, or when a goroutine has no clear exit. Not for defensive coding unrelated to concurrency such as nil panics, slice aliasing, or numeric overflow (→ See `samber/cc-skills-golang@golang-safety` skill), and not for debugging a specific hung, crashing, or racing program after the fact (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).

Idiomatic context.Context usage in Golang — propagation through API boundaries, cancellation, timeouts and deadlines, request-scoped values, context.WithoutCancel for background work outliving requests. Apply when designing context propagation across layers, debugging leaked or unexpired contexts, choosing between context.Background/TODO/WithoutCancel, or storing values in context. Not for code that merely accepts ctx as first parameter.

Dependency management for Golang projects — go.mod and go.sum, `go get` install and upgrade flows, Minimal Version Selection, conflict resolution with replace/exclude/retract, `govulncheck` scanning of the module tree, outdated dependency and binary size auditing, vendoring, `tool` directives, and go.work workspaces. Use when adding, removing, or upgrading Go dependencies, deciding whether to take on a package, resolving version conflicts, or auditing what a module pulls in. Covers choosing and upgrading dependency versions, not the surrounding tooling: do NOT use for fixing an exploitable vulnerability in code (→ See `samber/cc-skills-golang@golang-security` skill) or for wiring Dependabot/Renovate update bots into CI workflows (→ See `samber/cc-skills-golang@golang-continuous-integration` skill).

Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log aggregation 3rd-party tools. Apply when creating, wrapping, inspecting, or logging errors in Go code. For samber/oops specifics → See `samber/cc-skills-golang@golang-samber-oops` skill; for slog handler ecosystem → See `samber/cc-skills-golang@golang-samber-slog` skill.

Linting best practices and golangci-lint configuration for Golang projects — running linters, configuring .golangci.yml, suppressing warnings with nolint directives, interpreting lint output, and selecting linters. Use when configuring golangci-lint, asking about lint warnings or nolint suppressions, setting up code quality tooling, or choosing linters. Also use when the user mentions golangci-lint, go vet, staticcheck, or revive. Not for wiring a lint step into a GitHub Actions pipeline (→ See `samber/cc-skills-golang@golang-continuous-integration` skill).

Defensive Golang coding against accidental bugs — nil panics, typed-nil interfaces, `append` backing-array aliasing, silent int64-to-int32 truncation, float `==` comparison, `defer` inside loops, defensive copies of slices and maps, and usable zero values. Use when a Go program panics on a nil map write or nil pointer dereference, when reviewing code for nil-safety, numeric conversion overflow, or resource lifecycle, or when designing a type whose zero value must be safe. Not for designing concurrent access with goroutines, channels, or sync primitives (→ See `samber/cc-skills-golang@golang-concurrency` skill), not for exploitable vulnerabilities such as injection, weak crypto, or leaked secrets (→ See `samber/cc-skills-golang@golang-security` skill), and not for debugging an already-failing program (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).

Golang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency injection via interfaces, struct field tags, and pointer vs value receivers. Use this skill when designing Go types, defining or implementing interfaces, embedding structs or interfaces, writing type assertions or type switches, adding struct field tags for JSON/YAML/DB serialization, or choosing between pointer and value receivers. Also use when the user asks about "accept interfaces, return structs", compile-time interface checks, or composing small interfaces into larger ones.

Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI, or debugging flaky/slow tests. For testify-specific APIs see `samber/cc-skills-golang@golang-stretchr-testify`; for measurement methodology see `samber/cc-skills-golang@golang-benchmark`.

Prepare a spec with Roundfix's Delivery Plan, delegate implementation to Roundfix, monitor the Run or delivery queue, and ask the maintainer only its Pending Question.

Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.

Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.

Author or review software tests and LLM/agent evals; choose test placement and mocks, diagnose flaky CI, or repair brittle suites. Excludes unrelated code review, debugging, CI design, and production observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Execute the self-contained final QA gate as a Spec's authored terminal `qa` Task — derive a resumable QA matrix from the PRD and task evidence, execute real user flows through every declared surface, probe high-risk user behavior, capture auditable evidence, classify findings by user impact, and write the spec-local dated QA report. Do not use as a substitute for implementation tests or a broad standalone QA knowledge base.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use Roundfix to plan releases with the read-only Release Plan Command, clean CodeRabbit pull request feedback, diagnose runtime readiness with the Doctor Command, execute a Spec's Task Graph with the Implement Command, monitor Runs through the Supervisor Run Event Stream, reclaim Run storage with the GC Command, archive completed Specs, run its `--follow-up`, `--status` and `--unattended` Skill Modes, and, inside daemon-assigned Batch runs, follow the bounded Review Issue or Task resolution contract.

Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of the implement-spec loop after a QA pass, or whenever the user asks to archive a spec.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Work with project documentation and the central knowledge repository (marcioaltoe/secondbrain). Use when editing docs/, CONTEXT.md, specs, ADRs, or task files in any repo with a .secondbrain-project file; when deciding where a documentation change should be committed; when touching secondbrain's mirror, notes, shared or wiki areas; and when research, planning or implementation work could consult or feed the second brain (wiki + qmd search).

Adopt, update, or verify a repository's Context-Driven Baseline through the public Roundfix Baseline Command. Use when preparing a repository for the write-prd/write-tasks/implement pipeline, changing its Baseline Profile, preserving existing instructions, restoring its Repository Skill Set, or confirming that Baseline-owned content is current.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design through one question at a time, then routes the outcome to write-idea, write-prd, write-techspec (refactors/bug fixes), or a direct task.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.

Write a PRD as a durable local artifact at docs/specs/<slug>/_prd.md — research first, clarify with one multiple-choice question at a time, record decisions as ADRs, then write directly without draft-approval rounds.

Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.

Decompose a spec's PRD/TechSpec into a dependency-ordered task graph — vertical-slice task files plus a machine-parseable _tasks.md DAG manifest under docs/specs/<slug>/, including the authored QA gate decision, decided autonomously from the Spec and escalated only when authority, architecture, or blast radius is at stake.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Prepare a spec with Roundfix's Delivery Plan, delegate implementation to Roundfix, monitor the Run or delivery queue, and ask the maintainer only its Pending Question.

Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.

Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.

Author or review software tests and LLM/agent evals; choose test placement and mocks, diagnose flaky CI, or repair brittle suites. Excludes unrelated code review, debugging, CI design, and production observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Execute the self-contained final QA gate as a Spec's authored terminal `qa` Task — derive a resumable QA matrix from the PRD and task evidence, execute real user flows through every declared surface, probe high-risk user behavior, capture auditable evidence, classify findings by user impact, and write the spec-local dated QA report. Do not use as a substitute for implementation tests or a broad standalone QA knowledge base.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use Roundfix to plan releases with the read-only Release Plan Command, clean CodeRabbit pull request feedback, diagnose runtime readiness with the Doctor Command, execute a Spec's Task Graph with the Implement Command, monitor Runs through the Supervisor Run Event Stream, reclaim Run storage with the GC Command, archive completed Specs, run its `--follow-up`, `--status` and `--unattended` Skill Modes, and, inside daemon-assigned Batch runs, follow the bounded Review Issue or Task resolution contract.

Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of the implement-spec loop after a QA pass, or whenever the user asks to archive a spec.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Guide for using uv, the Python package and project manager. Use this when working with Python projects, scripts, packages, or tools.

Guide for using ruff, the extremely fast Python linter and formatter. Use this when linting, formatting, or fixing Python code.

Guide for using ty, the extremely fast Python type checker and language server. Use this when type checking Python code or setting up type checking in Python projects.

Best practices for writing and organizing tests with pytest including fixtures, parametrize, and plugins.

Typer best practices and conventions. Use when working with Typer CLIs. Keeps Typer code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.

FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.

Build Python CLIs, HTTP backends, and workers around shared application services. Use when creating a Python project, exposing a command as an API or job, choosing uv tooling, or implementing retries, cancellation, and durable work. Preserve existing argparse and framework contracts. For file ingestion and report generation, also load python-file-pipelines. Do not use for production frontend development.

Implement Python file ingestion, reconciliation, and deterministic report pipelines for CSV, XML, ZIP, SQLite, XLSX, and DOCX. Use for large-file parsing, exact monetary values, incomplete evidence, dry runs, cache isolation, and safe report publication. Do not use for one-off office file creation or to define accounting or tax rules.

Creates selected backend Markdown documentation from code evidence, including architecture/design docs, bounded context maps, developer onboarding, API contracts, and gap analysis for code smells, project-rule violations, DDD issues, coupling, and improvement opportunities. Use when the user asks to document a backend, map backend architecture or domains, onboard backend developers, audit backend documentation gaps, or produce objective backend docs. Do NOT use for frontend docs, generic README writing, or implementing backend changes.

Use when designing, writing, or reviewing adapters for external APIs, ERP systems, payment providers, storage providers, or third-party services. Covers boundary contracts, typed clients, retries, timeouts, pagination, error normalization, observability, and tests. Do not use for pure internal domain logic with no external service boundary.

Use when writing or reviewing tests for external API adapters, storage adapters, database integration boundaries, or service contracts. Covers fixture design, schema validation, negative contracts, fakes, recorded responses, and CI-safe verification. Do not use for simple pure unit tests with no boundary contract.

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or extract files, or perform any PDF manipulation from the command line.

Docker containerization expert: Dockerfile optimization, multi-stage builds, security hardening, Docker Compose orchestration, and production deployment. Use for Dockerfile creation/review, image size issues, container security, networking, and orchestration.

Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st., dashboard, app.py, beautify, style, CSS, color, background, theme, button, widget styling, custom component, st.components, CCv2, session state, performance, cache, fragment, slow rerun, deploy.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Work with project documentation and the central knowledge repository (marcioaltoe/secondbrain). Use when editing docs/, CONTEXT.md, specs, ADRs, or task files in any repo with a .secondbrain-project file; when deciding where a documentation change should be committed; when touching secondbrain's mirror, notes, shared or wiki areas; and when research, planning or implementation work could consult or feed the second brain (wiki + qmd search).

Adopt, update, or verify a repository's Context-Driven Baseline through the public Roundfix Baseline Command. Use when preparing a repository for the write-prd/write-tasks/implement pipeline, changing its Baseline Profile, preserving existing instructions, restoring its Repository Skill Set, or confirming that Baseline-owned content is current.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design through one question at a time, then routes the outcome to write-idea, write-prd, write-techspec (refactors/bug fixes), or a direct task.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.

Write a PRD as a durable local artifact at docs/specs/<slug>/_prd.md — research first, clarify with one multiple-choice question at a time, record decisions as ADRs, then write directly without draft-approval rounds.

Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.

Decompose a spec's PRD/TechSpec into a dependency-ordered task graph — vertical-slice task files plus a machine-parseable _tasks.md DAG manifest under docs/specs/<slug>/, including the authored QA gate decision, decided autonomously from the Spec and escalated only when authority, architecture, or blast radius is at stake.

Use when building or reviewing Rust command-line interfaces with clap: derive Parser/Args/Subcommand/ValueEnum, builder Command/Arg, typed value parsers, env/default handling, bool flags, repeated flags, subcommands, shell completions, help text, and CLI tests.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Prepare a spec with Roundfix's Delivery Plan, delegate implementation to Roundfix, monitor the Run or delivery queue, and ask the maintainer only its Pending Question.

Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.

Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.

Design and implementation guidance for maintainable Rust CLIs with strong ergonomics, machine-friendly behavior, testable structure, and release automation. Use when creating or refactoring a Rust command-line tool, choosing crates like clap/anyhow/tracing/serde_json, improving command UX, adding JSON output, tightening test/release workflows, or making an existing CLI safer for agents and automation.

Senior Rust engineer specialized in building memory-safe, high-performance systems and backend applications. Use this skill when writing core Rust logic, designing trait hierarchies, working with the borrow checker (lifetimes, ownership), implementing async/await with Tokio, optimizing performance, or applying modern Rust idioms and best practices.

Author or review software tests and LLM/agent evals; choose test placement and mocks, diagnose flaky CI, or repair brittle suites. Excludes unrelated code review, debugging, CI design, and production observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Execute the self-contained final QA gate as a Spec's authored terminal `qa` Task — derive a resumable QA matrix from the PRD and task evidence, execute real user flows through every declared surface, probe high-risk user behavior, capture auditable evidence, classify findings by user impact, and write the spec-local dated QA report. Do not use as a substitute for implementation tests or a broad standalone QA knowledge base.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use Roundfix to plan releases with the read-only Release Plan Command, clean CodeRabbit pull request feedback, diagnose runtime readiness with the Doctor Command, execute a Spec's Task Graph with the Implement Command, monitor Runs through the Supervisor Run Event Stream, reclaim Run storage with the GC Command, archive completed Specs, run its `--follow-up`, `--status` and `--unattended` Skill Modes, and, inside daemon-assigned Batch runs, follow the bounded Review Issue or Task resolution contract.

Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of the implement-spec loop after a QA pass, or whenever the user asks to archive a spec.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Cut a release for a CLI or library — verify version sync across every manifest, run the full verification gate and publish dry-runs, tag, push, and watch the release workflow to completion with evidence at each step.

Discover and understand project rules, coding standards, and architectural guidelines before starting a task. Use when you need to know the constraints, patterns, or compliance requirements for a feature, file, or technology.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Work with project documentation and the central knowledge repository (marcioaltoe/secondbrain). Use when editing docs/, CONTEXT.md, specs, ADRs, or task files in any repo with a .secondbrain-project file; when deciding where a documentation change should be committed; when touching secondbrain's mirror, notes, shared or wiki areas; and when research, planning or implementation work could consult or feed the second brain (wiki + qmd search).

Adopt, update, or verify a repository's Context-Driven Baseline through the public Roundfix Baseline Command. Use when preparing a repository for the write-prd/write-tasks/implement pipeline, changing its Baseline Profile, preserving existing instructions, restoring its Repository Skill Set, or confirming that Baseline-owned content is current.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to set up Context7 for their AI coding agent.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Write a PRD as a durable local artifact at docs/specs/<slug>/_prd.md — research first, clarify with one multiple-choice question at a time, record decisions as ADRs, then write directly without draft-approval rounds.

Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.

Audit architecture, dead code, duplication, type confusion, and code smells across a codebase. Excludes formatting, performance profiling, security audits, and feature-level reviews.

Creates selected backend Markdown documentation from code evidence, including architecture/design docs, bounded context maps, developer onboarding, API contracts, and gap analysis for code smells, project-rule violations, DDD issues, coupling, and improvement opportunities. Use when the user asks to document a backend, map backend architecture or domains, onboard backend developers, audit backend documentation gaps, or produce objective backend docs. Do NOT use for frontend docs, generic README writing, or implementing backend changes.

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go", "decouple from the database", "swap the framework without a rewrite", or "keep business rules independent". Also trigger when deciding which layer code belongs in, isolating core logic from infrastructure, defining module boundaries, or debating whether the framework should call your code or the reverse. Covers component principles, boundaries, and SOLID. For code-level quality, see clean-code. For domain modeling, see domain-driven-design.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Use when designing, planning, implementing, or reviewing data synchronization workflows, ERP imports, incremental syncs, backfills, reconciliation jobs, or scheduled ingestion. Covers source of truth, checkpoints, idempotency, deduplication, retries, repair, evidence, and operational controls. Do not use for one-off pure CRUD code.

Apply Gang of Four design patterns to solve architectural problems in TypeScript. Use when refactoring code architecture, implementing extensible systems, decoupling components, or following SOLID principles. Covers all 22 GoF patterns: Creational (Factory Method, Abstract Factory, Builder, Prototype, Singleton), Structural (Adapter, Bridge, Composite, Decorator, Facade, Flyweight, Proxy), and Behavioral (Chain of Responsibility, Command, Iterator, Mediator, Memento, Observer, State, Strategy, Template Method, Visitor).

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Creates selected frontend Markdown documentation from code evidence, including frontend architecture/design docs, feature-system maps, developer onboarding, route and data-flow docs, DESIGN.md compliance, and gap analysis for React, Vite, TanStack Router, TanStack Query, Tailwind CSS, design systems, UI quality, accessibility, testing, and maintainability issues. Use when the user asks to document a frontend app, map UI architecture or frontend systems, onboard frontend developers, audit frontend documentation gaps, document systems/<domain> feature architecture, validate frontend adherence to DESIGN.md, evaluate gaps against UI quality practices, or produce objective frontend docs. Do NOT use for backend docs, generic README writing, or implementing frontend changes.

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks.

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Use when the user asks to threat model a codebase or path, enumerate threats or abuse paths, or perform AppSec threat modeling. Do NOT use for general architecture summaries, code review, security best practices (use security-best-practices), or non-security design work.

Detects anemic domain models, validates and refactors them into rich domain models, and enforces tactical DDD patterns (Entities, Value Objects, Aggregates, Domain Services, Domain Events). Use when the user asks to validate, review, or check domain models or DDD code; detect anemia; refactor domain objects; improve encapsulation; or mentions terms like "anemic model", "rich domain", "aggregate", "value object", "domain event", "ubiquitous language", "is this good DDD", "does this follow DDD", or "check my domain". Do NOT use for module or service boundary design, architectural decomposition, strategic DDD context mapping, or code outside the domain layer (DTOs, controllers, infrastructure adapters).

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Enforce Vertical Slice Architecture (VSA) when building applications in any language (Go, .NET/C#, Java, Kotlin, TypeScript, Python, etc.) and any type (web API, mobile backend, CLI, event-driven). Organize code by feature/use-case instead of technical layers. Each feature is a self-contained vertical slice with a single entry point that receives the router/framework handle and its dependencies. Use when the user says "vertical slice architecture", "VSA", "organize by feature", "feature-based architecture", "slice architecture", or when building a new app or feature and the project already follows VSA conventions. Also use when reviewing or refactoring code to align with VSA principles.

Write the technical spec at docs/specs/<slug>/_techspec.md — explore the architecture, settle technical decisions one question at a time, record them as ADRs, and produce a build order that write-tasks can decompose. Entry point for feature work with an approved PRD, and also for refactors and bug fixes, where it mints the spec folder with a minimal _prd.md instead of requiring a product interview.

Decompose a spec's PRD/TechSpec into a dependency-ordered task graph — vertical-slice task files plus a machine-parseable _tasks.md DAG manifest under docs/specs/<slug>/, including the authored QA gate decision, decided autonomously from the Spec and escalated only when authority, architecture, or blast radius is at stake.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.

Better Auth — framework-agnostic TypeScript authentication & authorization library. Covers setup, email/password, social OAuth (40+ providers), passkeys, magic links, 2FA, organizations, sessions, plugins, admin, hooks, and security hardening. Use when implementing auth with Better Auth: configuring auth instances, adding providers, setting up database adapters (Prisma, Drizzle, PostgreSQL, MySQL, SQLite, MongoDB), integrating with frameworks (Next.js, Nuxt, SvelteKit, Astro, Hono, Express, Elysia, Fastify, Expo), managing sessions, or extending with plugins.

Bun runtime, package manager, bundler, and test runner. Use when running scripts with bun, managing packages, serving HTTP with Bun.serve, querying databases with Bun.sql/bun:sqlite/Bun.redis, shell scripting with $, using S3/file I/O, writing tests with bun:test, bundling or compiling to executable, or using any Bun-specific API (spawn, glob, semver, FFI, workers, plugins, HTMLRewriter).

Guide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs, setting up design tokens, publishing to npm/registry, or writing component documentation.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Drizzle ORM — type-safe, lightweight TypeScript ORM for SQL databases. Schema declaration, CRUD queries, joins, relations, migrations with Drizzle Kit, and database seeding. Use when defining database schemas, writing queries (select/insert/update/delete), setting up migrations, configuring drizzle.config.ts, establishing database connections, validating data with drizzle-zod/valibot, or working with PostgreSQL, MySQL, SQLite, Turso, Bun SQL, Neon, Supabase, PGlite, Expo SQLite, Cloudflare D1, PlanetScale, SingleStore, MSSQL, CockroachDB.

Use when designing, writing, or reviewing adapters for external APIs, ERP systems, payment providers, storage providers, or third-party services. Covers boundary contracts, typed clients, retries, timeouts, pagination, error normalization, observability, and tests. Do not use for pure internal domain logic with no external service boundary.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Use when building Hono web applications or when the user asks about Hono APIs, routing, middleware, JSX, validation, testing, or streaming. TRIGGER when code imports from 'hono' or 'hono/*', or user mentions Hono. Use `npx hono request` to test endpoints.

Design HTTP APIs for Bun + Hono backends using Clean Architecture, Zod contracts in a shared package, OpenAPI generation from Zod, and thin controllers. Supports two selectable conventions — standard REST (resource paths with GET/POST/PATCH/PUT/DELETE) and POST-only action-based paths — picking one per project. Use when defining new endpoints, auditing or refactoring existing routes, shaping request/response contracts and envelopes, establishing API standards, or mapping typed application errors to HTTP status codes. Do not use for GraphQL, tRPC, non-Hono runtimes, or frontend-only concerns.

Prepare a spec with Roundfix's Delivery Plan, delegate implementation to Roundfix, monitor the Run or delivery queue, and ask the maintainer only its Pending Question.

Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven wor...

Use when writing or reviewing tests for external API adapters, storage adapters, database integration boundaries, or service contracts. Covers fixture design, schema validation, negative contracts, fakes, recorded responses, and CI-safe verification. Do not use for simple pure unit tests with no boundary contract.

Craft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, or design-system consistency matter. Not for marketing pages, landing pages, campaigns, or brand-only work.

Design and implement microinteractions, motion design, transitions, and user feedback patterns. Use when adding polish to UI interactions, implementing loading states, or creating delightful user experiences.

Use this skill when writing any code that uses LogTape for logging in JavaScript or TypeScript. Covers getting loggers, the structured message syntax, configuration, library author rules, context, lazy evaluation, testing, and common mistakes to avoid. Trigger whenever the user is adding logging to a project, debugging log output, or integrating LogTape with a framework.

Build React animations with Motion (Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG. Bundle: 2.3 KB (mini) to 34 KB (full). Use when: drag-and-drop, scroll animations, modals, carousels, parallax. Troubleshoot: AnimatePresence exit, list performance, Tailwind conflicts, Next.js "use client".

Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.

Build React 19 components and hooks under React Compiler: state, Effects, memoization, props/refs, Actions, use(), compiler/lint setup, and Vitest tests. Excludes React Native, other frameworks, and backend-only Node.js.

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements. Do NOT use for component API architecture or composition patterns (use react-composition-patterns instead).

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes. Do NOT use for React/Next.js performance optimization (use react-best-practices instead).

Build type-safe validated forms using React Hook Form v7 and Zod v4. Single schema works on client and server with full TypeScript inference via z.infer. Use when building forms, multi-step wizards, or fixing uncontrolled warnings, resolver errors, useFieldArray issues, performance problems with large forms.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

Apply SOLID principles to write flexible, maintainable, and testable code. Use when designing classes, interfaces, and module boundaries. Covers Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion with practical TypeScript examples and detection heuristics.

Style components with Tailwind CSS v4 and project tokens. Excludes plain CSS, CSS-in-JS, and other utility frameworks.

TanStack Query (React Query) v5 best practices for data fetching, caching, mutations, and server state management. Use when building data-driven React applications, setting up query configurations, implementing mutations/optimistic updates, configuring caching strategies, integrating with SSR, or fixing v4→v5 migration errors.

TanStack Router best practices for type-safe routing, file-based routing, data loading, search params, and navigation in React. Use when building React SPAs with complex routing, implementing type-safe search params, setting up route loaders, integrating with TanStack Query, or configuring code splitting and preloading.

TanStack Table best practices for building headless, type-safe data tables in React with sorting, filtering, pagination, row selection, and column management. Use when building data grids, implementing client-side or server-side table features, defining column structures, managing table state, or optimizing table rendering performance.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Author or review software tests and LLM/agent evals; choose test placement and mocks, diagnose flaky CI, or repair brittle suites. Excludes unrelated code review, debugging, CI design, and production observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Implement advanced TypeScript types, reusable type utilities, and compile-time contracts with generics, conditional/mapped types, and template literals. Excludes basic syntax, JavaScript, and runtime validation.

Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.

Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

Zod 4 — TypeScript-first schema validation with static type inference. Use when writing Zod schemas, validating data, defining types with Zod, parsing input, creating form validation schemas, defining API request/response schemas, working with z.object, z.string, z.number, z.enum, z.array, z.union, z.discriminatedUnion, z.file, z.jwt, z.email, z.uuid, z.url, z.codec, z.toJSONSchema, z.fromJSONSchema, z.int, z.stringbool, z.templateLiteral, z.record, z.partialRecord, or any other Zod API. Also use when migrating from Zod 3 to Zod 4, or when the user's package.json shows zod@^4. CRITICAL: Always use Zod 4 APIs. Never use deprecated Zod 3 patterns unless user explicitly requests Zod 3 compatibility.

Implement global state management for React/TypeScript applications. Use when creating, modifying, or debugging Zustand stores, implementing state management patterns (slices, persist, devtools, immer), setting up Zustand with Next.js/SSR, writing tests for Zustand stores, or working with TypeScript typing for Zustand (curried create, StateCreator, middleware mutators).

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Write clean, readable, and maintainable code following principles from Robert C. Martin's "Clean Code" and Object Calisthenics. Use when writing, reviewing, or refactoring code to improve naming, function design, formatting, error handling, and class structure. Includes code smell detection and refactoring guidance.

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.

Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags.

Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.

Rebase branches and resolve cross-commit conflicts while preserving changes. Excludes merge-commit workflows, cherry-picking, and repository setup.

Use when reviewing whether code has enough operational evidence: structured logs, correlation IDs, metrics, traces, run summaries, error normalization, and safe redaction. Trigger for production readiness reviews, sync/job reviews, incident-prone code, or before delivery of backend workflows. Do not use for visual UI-only review.

Run and interpret the OnionCry Rust CLI for architecture-boundary checks in JavaScript and TypeScript repositories. Use when the user asks to check architecture boundaries, generate or review .onioncryrc.jsonc, run onioncry check or explain, adopt a violation baseline, inspect llm-mode reports, render boundary graphs, add repo/package scripts, or automate OnionCry in agent workflows. Do NOT use for generic Rust implementation work.

Execute the self-contained final QA gate as a Spec's authored terminal `qa` Task — derive a resumable QA matrix from the PRD and task evidence, execute real user flows through every declared surface, probe high-risk user behavior, capture auditable evidence, classify findings by user impact, and write the spec-local dated QA report. Do not use as a substitute for implementation tests or a broad standalone QA knowledge base.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of the implement-spec loop after a QA pass, or whenever the user asks to archive a spec.

Create Conventional Commits and PR titles that pass Cocogitto validation. Use when the user asks to commit, stage changes, split commits, write a commit message, open or update a PR title, or prepare squash-merge history.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.

Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.

Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.

Use this skill for cross-project agent-to-agent messaging: sending a request to another project's inbox, checking or popping this project's inbox, or retracting a message you sent. Trigger by semantic intent (delegate to another repo, check my inbox, tell the other agent) rather than exact wording.

Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.

Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.

Write or rewrite anything technical people write — READMEs, documentation pages, quickstarts, PRDs, tech specs, RFCs, ADRs, design docs, task breakdowns and task files, GitHub issues, bug reports, QA test plans, test cases, exploratory charters, verification reports, PR descriptions, code review comments, and async team updates — so it reads clearly, scans fast, stays faithful to source facts, and sounds human. Use when the user says "write a README", "improve these docs", "write a PRD", "write a tech spec", "draft an ADR", "break this into tasks", "write the task files", "open an issue", "write a test plan", "write test cases", "file a bug report", "write the QA report", "write the PR description", "draft a status update", or wants technical writing that persuades without marketing fluff. Do NOT use for marketing landing pages, sales copy, or ad copywriting.

Docker containerization expert: Dockerfile optimization, multi-stage builds, security hardening, Docker Compose orchestration, and production deployment. Use for Dockerfile creation/review, image size issues, container security, networking, and orchestration.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design through one question at a time, then routes the outcome to write-idea, write-prd, write-techspec (refactors/bug fixes), or a direct task.

Transforms technical work into persuasive business-language documents for non-technical stakeholders, including internal announcements, approval proposals, incident explainers, technical-debt cases, product explainers, and investor or partner memos. Use when the user asks to present technical work to the company, explain software to business teams, write a business case, make an approval document, or convert a technical artifact into stakeholder communication in the requested language. Do not use for READMEs, specs, ADRs, external marketing pages, or customer-facing sales copy.

Turns exploration into decision-ready analysis: scores feature ideas on six viability criteria with KPI targets, converts open questions into A/B/C options with a recommended default, and produces executive-grade deliverables (KPI frameworks, forecasts, cohort/LTV-CAC models, A/B readouts, market sizing). Use during idea/PRD discovery to score or structure a decision, and whenever the task is quantitative decision support. Don't use for software implementation, UI work, or database migration.

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

Create, extend, or debug frontend domain modules organized under systems/. Covers adapters, Query hooks, local state, and public exports; excludes generic components and backend implementation.

Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For US legal or regulatory questions use gov; for papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."

Audit code quality and architectural health or plan refactoring using Fowler code smells and techniques; write prioritized findings to docs/_refacs/. Excludes formatting, performance, and security audits.

Use Roundfix to plan releases with the read-only Release Plan Command, clean CodeRabbit pull request feedback, diagnose runtime readiness with the Doctor Command, execute a Spec's Task Graph with the Implement Command, monitor Runs through the Supervisor Run Event Stream, reclaim Run storage with the GC Command, archive completed Specs, run its `--follow-up`, `--status` and `--unattended` Skill Modes, and, inside daemon-assigned Batch runs, follow the bounded Review Issue or Task resolution contract.

Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.

Create a handoff brief for another LLM to implement. Preserve accepted decisions and write to docs/prompts/; excludes one-shot questions and end-user copy.

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.