coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Skills correspondant au nom, à la description ou à l’auteur GitHub.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "plugin.json", "plugin directory structure", or mentions starting a new Claude Code plugin. Also invoke when user asks abo...
Analyze any GitHub repo to learn from implementations. Auto-clones repos locally using your own Claude setup. Use when exploring how other projects solve problems, finding prior art, or understanding unfamiliar...
This skill provides guidance on using Google's Gemini CLI for long-context code exploration. Use when the user explicitly invokes "/gemini", asks to "use gemini", "run gemini", or when Claude determines that Ge...
This skill should be used when the user asks to "set up Claude Code", "recommend automations", "what hooks should I use", "recommend plugins", or mentions Claude Code optimization. Also invoke when user says "i...
Help users configure and verify LSP (Language Server Protocol) setup for Python and JavaScript/TypeScript in Claude Code. This skill should be used when users ask about LSP configuration, need to check if LSP s...
Claude Codeのカスタマイズを支援。「Claude Codeをカスタマイズしたい」「こういう挙動にしたい」「自動で〇〇したい」などのリクエストに対応し、適切な設定ファイルを作成・配置する。
Claude-specific loctree skill with PostToolUse hook augmentation for rg/grep results and explicit loct commands.
Get plan reviews from Codex and Gemini before implementation. Both AIs review the plan against the actual codebase and suggest improvements. Claude then incorporates their feedback.
Orchestrate OpenSpec change implementation with Claude Code, including reading OpenSpec workflow guidance, implementing change tasks, and running a review/repair loop. Use when a Change is already defined and y...
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "...
Track collaboration state between Claude sessions using git branches. Enables seamless context switching by persisting progress in feature branches. Use for multi-session work, handoffs, and publishing complete...
Maestro spec-driven development for Claude Code. Use this skill when running /maestro* commands (setup, newTrack, implement, orchestrate, status, revert, leindex, tui) so workflows stay aligned with LeIndex and...
Run automated playtesting to find bugs. Deploys Claude as a player to interact with SENTINEL through the bridge API.
Automated code review loop with progressive reasoning levels. Runs n parallel Codex reviews (configurable via -n), Claude addresses findings, climbs from low→xhigh reasoning until fixed point (all n clean). Hum...
Research dispatcher for enhanced /build command Phase 1. Parses user concept input and delegates to claude-code-guide for capability inventory. Saves results to .agent/builds/{build_id}/ for resume support. Ret...
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.