Loading...
Loading...
Found 2,914 Skills
Use when scaffolding a new repository (public or private) to the Patina Project baseline, when realigning an existing repository with that baseline, or when auditing or adding commit conventions, PR templates, husky + commitlint, PNPM tooling, release-please, agent docs (AGENTS.md, CLAUDE.md), or AI agent plugin manifests for Claude Code, Codex, Cursor, Windsurf, and Copilot. Triggers on phrases like "scaffold this repo", "scaffold a Patina plugin", "realign with the baseline", "audit our repo conventions", "set up commitlint and husky", or "add Codex/Cursor/Windsurf surfaces".
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
Review local code changes organized into logical chapters with Stage CLI, a code review tool that works with any AI agent
This skill should be used when the user says "update CLAUDE.md", "refresh CLAUDE.md", "sync CLAUDE.md with the codebase", "reorganize CLAUDE.md", "optimize project instructions", or when CLAUDE.md is stale, verbose, or out of sync.
Comet Phase 3: Planning and Building. Invoke with /comet-build. Develop a plan and select an execution method (subagent or direct execution) for implementation.
Spawn a focused code review subagent. Use after every RED/GREEN cycle (pass the files changed in that cycle), after a commit, or whenever the user asks for a review. Always use this skill for reviews — it ensures the review lens is test-first and findings are fix-oriented.
Cerrar e integrar el trabajo de una historia de usuario haciendo merge de la rama feature/US-XXX hacia la rama desde la que se creó, previa verificación de que progress.md tenga todas las tareas en Done. Activar cuando el usuario pida cerrar, entregar, mergear, integrar, finalizar o hacer submit del trabajo de una historia, una US o de la rama actual.
Ghostty submodule and GhosttyKit workflow rules for cmux. Use when modifying the ghostty submodule, rebuilding GhosttyKit.xcframework, updating the parent submodule pointer, or documenting fork conflict notes.
Use when checking doc freshness and computing domain quality grades without making fixes.
Use when performing a first-pass, read-only PR review in a clean isolated context.
Use when running the automated security alert fix pipeline — opens fix PRs, creates issues for breaking changes, dismisses false positives.
Distills a completed deep-plan document (e.g. docs/PLAN.md) into durable project knowledge files: AGENTS.md (agent operating rules and verified ground truth), docs/ARCHITECTURE.md (component map, data flow, framework mechanisms with citations), and ROADMAP.md (phased roadmap with live status). Carries only VERIFIED evidence forward, re-checks stale claims, and merges into existing files instead of overwriting. Use after a deep-plan finishes, when the user mentions deep-plan-ingest or ingest the plan, or asks to generate/update AGENTS.md, ARCHITECTURE.md, or ROADMAP.md from a plan.