aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Use for code review and quality feedback from Codex. Triggers on "codex review code", "codex code review", "have codex review this", "get codex feedback on code".
Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling
Load methodology context for creating or fixing Claude Code instruction artifacts (discovery: implementation-clarity). Evaluate at implementation-clarity when artifact type is known (command, skill, hook, protocol, external tool config) and implementation approach needs methodology guidance.
Guide for implementing code following the noop function-first, layered architecture. Use when writing handlers, services, database operations, or middleware. Automatically invoked when working on noop-based projects.
Use for Python development requiring async programming, type system expertise, testing patterns, or performance optimization.
Secure credential manager for AI tools. Secrets are injected transparently into shell commands via a PreToolUse hook — the agent never sees secret values or the master key. Trigger phrases include "add a secret", "inject credentials", "set up vault", "rv init", "rv add", or any secret/credential management request.
Designer-turned-developer who crafts stunning UI/UX even without design mockups
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
Conduct comprehensive pull request reviews with security, architecture, and quality checks. Use when user wants to review a PR.
Intelligent workflow orchestrator that commits, pushes, and creates/updates PRs automatically. Use when user wants to save their work or create a PR.
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
Critical path resolution patterns for Electron apps - avoid process.cwd() and __dirname pitfalls
This skill provides foundational knowledge about Asleep sleep tracking platform, covering core concepts, authentication, data structures, error handling, and platform-agnostic best practices. Use this skill when developers ask about Asleep fundamentals, API concepts, error codes, sleep data structures, or need to understand how the platform works before implementing platform-specific integration. This skill serves as prerequisite knowledge for sleeptrack-ios, sleeptrack-android, and sleeptrack-be skills.
Initialize the file-based memory system for the current project. Creates the directory structure and starter files. Use when starting organized work on a new project.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
This skill teaches proper Gemini CLI usage patterns. Use stdin piping instead of shell variable gymnastics. Covers code review, plan review, and general prompts.
Filter by machine type (work, personal, all)
执行 task-breakdown 创建的子任务。 从任务清单文件中读取并执行 waiting 或 failed 状态的子任务,执行完成后更新状态。 当用户需要执行项目路径 .claude/tasks/ 中的任务清单时使用该 skill。
TDD Refactor Phase expert. Activate when: - Tests are passing, need to improve code quality - User mentions "refactor", "clean up", "improve code" - Applying DRY, SOLID, or design patterns - Code review findings need addressing Auto-triggers on: refactoring, code improvement, cleanup, tech debt
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.