80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
git-commit
by pproenca
Use when making git commits directly (not via /commit:new). Ensures safe shell quoting with heredoc format. Triggers on...
python-performance
by pproenca
Use when Python code runs slowly, needs profiling, requires async/await patterns, or needs concurrent execution - covers...
git-worktrees
by pproenca
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - cr...
verification
by pproenca
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verifi...
systematic
by pproenca
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root...
testing-skills
by pproenca
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization -...
parallel-agents
by pproenca
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multi...
executing-plans
by pproenca
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - load...
code-review
by pproenca
Use when requesting or receiving code reviews - covers dispatching review subagent, handling feedback with technical rig...
condition-wait
by pproenca
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeou...
subagent-dev
by pproenca
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for ea...
python-testing
by pproenca
Use when writing pytest tests, creating fixtures, mocking dependencies, or testing async code - provides patterns that v...
writing-plans
by pproenca
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - create...
root-cause
by pproenca
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces...
google-shell-style
by pproenca
Use when the user asks to "refactor shell script", "fix bash style", "apply Google style guide to shell", "review shell...
amazon-writing
by pproenca
Use when writing narrative memos, 6-pagers, 1-pagers, press releases, or PRFAQs in Amazon style. Applies Amazon's no-Pow...
agent-memory
by btafoya
Persistent memory system for AI agents with semantic, episodic, and procedural memory types. Use when users want to (1)...
Create an interactive HTML viewer to visualize and verify parsed metadata against source documents.
api-agent-development
by GolferGeek
Create API agents that wrap external HTTP services (n8n, LangGraph, CrewAI, OpenAI endpoints). Configure request/respons...
quality-gates
by GolferGeek
Ensure code quality before commits. Run lint, format, test, build. Use npm scripts: npm run lint, npm run format, npm te...
n8n-development
by GolferGeek
Create and manage N8N workflows in Orchestrator AI. Use Helper LLM pattern for all LLM calls, configure webhook status t...
orchestrator-git-standard...
by GolferGeek
Orchestrator AI-specific Git conventions and standards. Branch naming, commit workflow, repository organization. CRITICA...
conventional-commits
by GolferGeek
Conventional Commits specification format. Use when creating commit messages. Format: <type>(<scope>): <description>. Ty...
github-workflow
by GolferGeek
GitHub workflow patterns for Orchestrator AI. Branch naming, PR process, code review, CI/CD. CRITICAL: Use conventional...