Map an unfamiliar repository before changing it. Use when a task crosses packages, public contracts, persistence, runtime wiring, or verification lanes and the owning architecture is not yet clear.

Author lean AGENTS.md/CLAUDE.md instruction files — resident system-prompt context where every line pays rent. Use when writing an agent instruction file from scratch, auditing or trimming a bloated one, or gating whether a new rule earns residence and at which scope. Don't use for on-demand skills (use writing-skills) or human-facing docs and READMEs.

Ships a finished feature, bug fix, or refactor end-to-end — explores the change's impact on docs/site/README, generates release notes (via pr-release if present, otherwise inline from git log), writes a complete PR description (including QA screenshots and summary when qa-report/qa-execution artifacts exist), commits staged changes following the repo's commitlint config, opens the PR via gh CLI, and optionally launches a CodeRabbit review watch loop. Use when a feature/bug/refactor is implementation-complete and ready to ship. Do not use for draft PRs without finished work, for amending an already-merged PR, for repo-level release publishing (use pr-release directly), or for in-progress development checkpoints.

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.

Orchestrate Claude and Codex worker TUIs from a controller agent — one worker per named herdr tab, driven over the herdr socket CLI.

Intelligently handle git rebase operations and resolve merge conflicts while preserving features and maintaining code quality. Use when rebasing feature branches, resolving conflicts across commits, and ensuring clean linear history without losing changes. Don't use for merge-commit workflows, cherry-picking individual commits, or initial repository setup.

Authoritative guide for the Fumadocs documentation framework — Core (headless), MDX (content loader), and UI (Tailwind v4 layouts and components). Use when scaffolding a Fumadocs project, editing source.config.ts, wiring loader() and meta.json conventions, picking a search adapter, composing DocsLayout/Notebook/Flux/Home layouts, customising the MDX component map, integrating OpenAPI specs, generating OG images, exporting PDF/EPUB/RSS, or configuring i18n across Next.js, React Router, TanStack Start, and Waku adapters. Surfaces canonical install snippets per adapter, decision tables for entry modes and content sources, and the most common pitfalls (Tailwind v3 silent failure, ESM-only config, .source/ generation, layout/page import mismatch, slug collisions, edge runtime ban). Don't use for generic MDX/Markdown questions outside Fumadocs, for unrelated React framework setup, or for projects that don't use fumadocs-core/fumadocs-mdx/fumadocs-ui.

Generate custom favicons from logos, text, or brand colours. Produces all required formats: favicon.svg, favicon.ico, apple-touch-icon.png, icon-192/512.png, and web manifest. Use when initialising websites, replacing CMS default favicons, converting logos to favicons, creating branded icons from initials, or troubleshooting favicon not displaying, iOS black square, or missing manifest.

Isolates Compozy runtime state for concurrent worktrees and QA runs. Use when another agent or runtime may share the machine, or when creating a parallel worktree. Do not use for single-worktree or build-only work.

Screenshot capture for deterministic PNG evidence and visual-contract bundles for Compozy Storybook stories and local UI URLs. Use for visual audits, regression diffs, and design-parity checks. Do not use for interactive E2E flows, remote authenticated sites, or Storybook test execution.

Go test-shape discipline for Compozy. Use when writing or editing *_test.go under cmd or internal after test placement is justified. Do not use for non-Go tests, fixture-only changes, or as a replacement for eng-consolidate-test-suites.

Authors append-only Goose SQL migrations for Compozy SQLite streams and keeps declarative schema sources, atlas.sum, Atlas checks, sqlc output, and migration tests synchronized. Use for SQLite table, column, index, constraint, trigger, or seed-data changes under internal/store or internal/memory. Do not use for in-memory structures, derived Markdown memory, or non-SQLite caches.

Dogfoods Compozy through an autonomous startup scenario with live providers, cross-surface observation, and strict evidence audit. Use for release or complex-integration QA. Do not use for smoke, static, mock-only, or unit-test work.

Bootstraps isolated Compozy QA labs and emits the canonical manifest for downstream QA. Use when local QA needs daemon, workspace, provider, or playbook setup. Do not use for unit tests, planning-only work, or browser-only checks.

Compozy visual-design authority for production UI, static artifacts, prototypes, and reviews. Use when creating or reviewing a Compozy surface or changing tokens, typography, spacing, depth, icons, or motion. Do not use for capture-only verification; use eng-ui-screenshot.

Data-boundary audit for Compozy route loaders, TanStack Query caches, paginated catalogs, filters, ordering, totals, live streams, workspace-scoped reads, and their backend APIs. Use when adding, changing, or debugging those paths. Don't use for presentational-only UI or backend work with no public read-model impact.

Contract co-ship for Compozy wire changes. Use when editing public DTOs, OpenAPI, JSON-RPC extension shapes, generated clients, or handler request/response semantics. Do not use for internal Go refactors or test-only changes that leave the wire contract unchanged.

Use when adding, moving, reviewing, or auditing tests in Compozy to identify the invariant, owning layer, and canonical suite before changing coverage. Do not use as a replacement for framework-specific testing skills or final verification gates.

Go production discipline for Compozy. Use when writing or editing non-test Go files under cmd or internal, including config, logging, CLI, concurrency, and process-lifecycle paths. Do not use for Go tests; pair it with the narrower schema, contract, cleanup, or network skill when those domains apply.

Partial-failure cleanup audit for Compozy Go functions. Use when a changed function acquires, registers, starts, claims, leases, or opens more than one fallible resource before returning. Do not use for pure transformations, read-only helpers, or test-only code.