Loading...
Loading...
Found 8,783 Skills
Implement an existing PRD (`Type: feat`/`fix`/`chore`), update tests/checks, and mark completed PRD checklist items. Triggers: implement prd, build feature from prd, execute prd checklist.
Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring multiple components (3) Research component implementations and examples (4) Get component installation commands Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"
Guidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen, BindCraft, or RFdiffusion, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use the individual tool skills (boltzgen, bindcraft, rfdiffusion, etc.).
Use this at session start to discover what CodeCompass can do. Read .ai/capabilities.json for module map (5 domains, 21+ modules) instead of manual Grep/Glob. Apply when: (1) planning tasks, (2) user asks 'What can CodeCompass do?', (3) before implementing features
Apply OpenSpec OPSX in a strict one-task-at-a-time loop. Use when the user asks to execute work as single-task changes, wants spec-first implementation per task, or says to use OpenSpec method for each task from a task list. Supports both native /opsx command environments and manual fallback by creating OpenSpec artifact files directly.
Switch into structured planning mode before outlining multi-step solutions, and exit when done.
Automate NPM tasks via Rube MCP (Composio). Always search tools first for current schemas.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL. Originally from OpenAI's curated skills catalog.
Use when you need to work on multiple branches simultaneously, run parallel Claude Code sessions, handle emergency hotfixes during feature work, review PRs without switching branches, or test across branches without losing current work. Use when asked to "work on two branches at once", "parallel development", "switch without losing work", "create a worktree", or "hotfix while working on a feature".
Persistent local memory for AI agents. Silently capture and retrieve context that survives beyond a single conversation: business requirements, API specs, integration quirks, technical decisions, user preferences, and domain knowledge. Use this skill proactively whenever you encounter information worth preserving or when context from past sessions would help the current task. Also triggered manually by "braindump this" (to store) or "use your brain" (to retrieve).
Plan an open source PR contribution. Takes pr-research output and produces scope, acceptance criteria, and risk assessment. Triggers: "pr plan", "contribution plan", "plan PR", "plan contribution".
Use this skill when the user wants to organize, classify, or maintain a PARA-method second brain. Triggers include asking where to file something, distinguishing projects from areas, processing an inbox, setting up a new project, completing or archiving a project, running a monthly review, validating system structure, or finding stale/orphaned content.