Total 46,953 skills
Showing 12 of 46953 skills
Triages new GitHub issues — classifies, reproduces bugs, attempts conservative fixes, and comments. Use when a new issue is opened and needs automated triage.
Comprehensive guide to AI SDK v6 for agent development, tool definitions, multi-step agentic workflows, and result extraction patterns
Write or update documentation for the Inkeep docs site (agents-docs package). Use when: creating new docs, modifying existing docs, introducing features that need documentation, touching MDX files in agents-docs/content/. Triggers on: docs, documentation, MDX, agents-docs, write docs, update docs, add page, new tutorial, API reference, integration guide.
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
Workleap's shared web configuration packages (@workleap/eslint-configs, typescript-configs, rsbuild-configs, rslib-configs, stylelint-configs, browserslist-config). Use when: (1) Setting up or customizing shared web tooling configs in a Workleap project (2) Configuring ESLint by project type (web app, React library, TS library, monorepo) (3) Configuring TypeScript by project type (web-application, library, monorepo-workspace) (4) Configuring Rsbuild or Rslib bundling (dev, build, Storybook) (5) Configuring Stylelint, Browserslist, or monorepo (Turborepo) vs polyrepo strategies (6) Extending or customizing shared configs, troubleshooting ESM/ESNext constraints
Smart commit creation with conventional commits. Use when user says "commit" or requests committing changes. Handles staged file detection, suggests splits for multi-concern changes, and applies proper commit format without emoji prefixes.
Self-Evolving Agent: Given a goal, it autonomously learns and iteratively improves until completion. Integrates superpowers workflow discipline.
PostHog integration for Next.js App Router applications
Socratic discovery and design exploration before planning. Activates when starting non-trivial work — asks clarifying questions, explores alternatives and tradeoffs, produces a design document for approval. Pulls context from Linear issue description, linked docs, and existing CLAUDE.md learnings. Simple bugs and fixes skip this automatically.
Analyze parliamentary sessions from Chile, Spain, Peru and EU. Research transcripts, identify topics and trends, generate analytical PDF reports. Also search Official Journals (BOE, EUR-Lex) for decrees, laws, resolutions and published regulations. Use when user asks about legislative sessions, committees, parliamentary debates, official journal, decrees, laws, resolutions or requests reports/analysis.
Claude Code hooks configuration specialist. Use when creating hooks for tool validation, logging, notifications, or custom automation in Claude Code.
Use this skill for ANY question about creating test or evaluation datasets for LangChain agents. Covers generating datasets from traces (final_response, single_step, trajectory, RAG types), uploading to LangSmith, and managing evaluation data.