Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
Load context for a new agent session by analyzing codebase structure and README. Use when starting a new session or needing to understand an unfamiliar codebase.
CodeFocus for Quarto Revealjs. Use when creating presentations with progressive code highlighting.
Generate TypeScript types from JSON files using quicktype CLI. Use when user wants to create types/interfaces from JSON data, API responses, or config files.
Reference for the AndroidSdk.Tool CLI (`android` command) - a .NET global tool for Android SDK automation. Use when: (1) Managing Android SDK packages (list, install, uninstall, download), (2) Working with AVDs...
Interact with and test the CC Director WPF app using the cc-click CLI tool. Use this to click buttons, read text, take screenshots, list elements, right-click session tabs, and navigate the UI.
CLI tool for persistent browser automation with multi-session support, featuring Chromium/Real/Remote browser modes, cookie management, JavaScript execution, and long-running automation workflows.
Browser automation for AI agents. Navigate pages, fill forms, click elements, take screenshots, and manage tabs — all through simple CLI commands. 2.6k+ GitHub stars.
Launch unpacked Codex Desktop builds with debug ports and optional SSH host autostart using launch_codex_unpacked.sh. Use when asked to run Codex from extracted app.asar, enable inspect/remote-debugging, select...
CLI-first browser automation using Playwright CLI for navigation, form filling, snapshots, screenshots, data extraction, and UI-flow debugging from the terminal.
Classify task complexity (1-10) to route to optimal model. Use when starting any non-trivial task to determine resources and approach. Triggers include: 'classify', 'complexity', 'what model', 'how complex'.
Manually trigger context save when auto-compact fails in VSCode/Cursor extensions. Use when context is high and you need to preserve state before starting fresh.
Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.
OpenAI Codex CLI orchestration for AI-assisted development using gpt-5.2-codex model. Capabilities: code generation, refactoring, automated editing, parallel task execution, session management, code review, arc...
Patterns for using Context7 MCP for library documentation (v2.25)
Optimal patterns for MiniMax MCP tools (web_search + understand_image)
YAML-based skills system for lightweight skill management (H70-inspired, +36.7pts improvement)
Smart Forking - Find and fork from relevant historical sessions using parallel memory search across claude-mem, memvid, handoffs, and ledgers
Access OpenAI developer documentation via Context7 MCP. Provides up-to-date docs for Codex CLI, OpenAI API, Python/Node SDKs, Agents SDK, and MCP configuration. Use when: (1) configuring Codex CLI or MCP server...
Visualize task dependencies and progress (Gastown-style)
Full orchestration workflow with Smart Memory-Driven context (v2.47), RLM-inspired routing (v2.46), and quality gates: clarify, smart memory search, classify 3D, plan, delegate, execute with parallel memory, va...
进行全面的代码审查，涵盖安全、性能与可维护性分析。适用于用户要求审查代码、排查缺陷或审计代码库的场景。
Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a d...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.