Skills matching the name, description or GitHub author.
Autonomous AI coding loop with PRD-based task tracking. Use when user says "leo-wiggum", "/leo-wiggum", "start leo loop", "autonomous coding", "run leo", or wants to implement a feature using iterative AI sessi...
Patterns for building Claude Code plugins including commands, agents, hooks, MCP servers, and plugin marketplaces. Use when creating extensions for Claude Code or distributing plugins to teams.
dotfileの編集・修正を依頼されたとき、ホームディレクトリのファイルではなくchezmoiで管理されているファイルを優先的に確認・編集する。対象：~/.bashrc、~/.zshrc、~/.vimrc、~/.rsync-exclude、~/.config/**、~/.ssh/**、...
Autonomously analyzes a repository, detects architectural and coding patterns, and generates/updates a docs/ folder with a root CLAUDE.md as table of contents. Use when asked to generate documentation, create C...
Review and improve repository documentation including both human-readable docs (`docs/`), `README.md`, and AI agent memory context files (`CLAUDE.md`, `CODEX.md`, `AGENTS.md`, `.cursorrules`, etc.) for clarity,...
Codex CLIを使ってコードレビュー・分析を自動実行するスキル。Claude Codeの相棒として複雑な問題解決やセカンドオピニオンの取得に活用できます。
Context-driven development methodology for organized, spec-first coding. Use when: - Project has a `conductor/` directory - User mentions specs, plans, tracks, or context-driven development - Files like `conduc...
Sync modified and new files to chezmoi repository and push to GitHub. Use when Claude Code has modified or created files in a chezmoi-managed directory and needs to re-add them to chezmoi, commit changes, and p...
Write files outside workspace sandbox (e.g., ~/.claude/skills). Use when creating/editing personal agent skills or other files that must exist outside the current workspace.
Create Copilot-optimized task specifications for handoff between Claude and GitHub Copilot. Use when planning implementation tasks that Copilot will complete. Optimizes comment format, provides rich context, in...
Iterate on specs for better code generation. Use when Claude output needs refinement.
Review code written by Claude Code or humans across multiple languages. Use when asked to review, audit, critique, or analyze code quality. Supports R, Python, JavaScript, SQL, C++, Rust, Go, Ansible, Kustomize...
This skill should be used when the user asks to "review code with codex", "run codex review", "check code quality", "codex レビュー", mentions "レビューゲート", or before git commit/PR/merge/release. Performs i...
Multi-agent spec review with parallel Claude/OpenCode reviewers. Use after spec-create or standalone via /spec.review.
Project organization methodology for AI-assisted development with Claude Code or similar tools. Use when users want to set up a navigation system for large-scale AI code generation projects (10k+ lines), need t...
Comprehensive file organization workflow for SORT/ directory. Validates filenames, renames to CLAUDE.md standards, relocates to correct directories, runs OPSEC agents, and generates detailed reports. Main orche...
Moves files to correct repository directories based on type, category, and naming conventions. Organizes images into assets/, documents into docs/ or prd/, and maintains proper directory structure according to...
Renames files to comply with repository CLAUDE.md naming conventions. Handles images, documents, and markdown files with proper pattern enforcement. Converts uppercase to lowercase, replaces spaces with hyphens...
Tracks version consistency across version.json, README, CLAUDE.md, CHANGELOG, and SETUP_CONTEXT. Auto-activates when users ask about version updates, version sync, or what files need updating for a release. Val...
Guides users through per-project Claude Code setup. Auto-activates when users ask about project setup, CLAUDE.md creation, or project-specific configuration. Reduces per-project setup time from 20min to 5min.
Creates a high-level implementation plan file for issues from any tracker (Linear, GitHub, Jira) that another Claude Code instance can use as a guide. Use when the user asks to create an implementation plan fil...
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or auto...
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding...
Grep/wc replacement for .runs artifacts. Use for: count, extract, Machine Summary, receipt reading, marker counts. Null-safe counting (REQ/NFR/QID/RSK markers), YAML block parsing, BDD scenario counting. Determ...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.