aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Analyze Every Compound Engineering plugin and compare to our plugin for improvement suggestions
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
Enforces iterative web research for coding and DevOps questions to prevent assumptions about libraries, frameworks, APIs, versions, and configurations. Use this skill when the user asks about programming languages, frameworks, libraries, DevOps tools, cloud platforms, databases, container orchestration, CI/CD, infrastructure as code, or any technical topic where current documentation, version-specific behavior, or recent changes matter. This skill ensures Claude searches and fetches authoritative sources before answering, even for topics Claude may have knowledge about, to verify current state and avoid outdated information.
Allra 백엔드 테스트 작성 표준. Use when writing test code, choosing test helpers, generating test data with Fixture Monkey, or verifying test coverage.
Generate changelog entries from commits for any project type
This skill should be used when writing code in any opinionated framework's distinctive style. It applies when writing framework-based applications, creating models/controllers/views, or any framework code. Triggers on code generation, refactoring requests, code review, or when the user mentions framework conventions. Embodies the philosophy of embracing framework conventions, fighting complexity, and choosing simplicity over cleverness.
Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
This skill provides patterns for safe, systematic refactoring including extract, rename, move, and simplification operations with proper testing and rollback strategies.
Commits staged and unstaged changes to git with a concise conventional commit message. Use when changes are ready to be committed, after completing a task, or when the user asks to commit.
This skill provides patterns and best practices for generating and organizing tests. It covers unit testing, integration testing, test data factories, and coverage strategies across multiple languages and frameworks.
AIDA pipeline orchestration with Task tool multi-agent delegation. Manages 5-phase workflow with Leader/Player subagents.
Use when using, writing, reviewing, or refactoring Python code.
A Star Wars trash compactor-themed quiz skill that activates after significant code implementations (50+ lines, new features, APIs) to quiz developers on their understanding. Automatically triggers during coding sessions when installed.
Use when optimizing codebase performance, reducing bundle sizes, improving build times, or eliminating code bloat. Launches parallel optimization hunters with mandatory before/after verification.
This skill should be used when the user invokes /gtr:* commands to manage git worktrees using git-worktree-runner (gtr). Enables parallel branch development through worktree creation, editor/AI integration, and lifecycle management.
Material-UI theme customization
Differential testing with Theodore Calvin's framework (tc). Use when writing tc tests, reasoning about test scenarios, creating input/expected JSON pairs, or debugging test failures.
Interactive markdown review with web UI. Use when: - User says "review this", "check this plan", "/review" - User wants to give feedback on a plan or document - User says "let me review", "피드백", "검토해줘" - User specifies a file path to review (e.g., "review /path/to/file.md")
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, extract data, or test web applications. Uses ref-based element selection from accessibility snapshots. Alternative to Playwright MCP for Bash-based workflows.
Merge GitHub pull requests with strict CI validation. Never bypasses failed checks. Use when merging PRs or when user says /pr-merge.