Skills matching the name, description or GitHub author.
Automatically discovers coding standards from project files (CLAUDE.md, tsconfig.json, ESLint, etc.) and generates validation scenarios for the benchmarks framework. Use when user wants to generate test scenari...
Validate .claude/ configuration quality and compliance with 2026 best practices. Use when auditing project setup, checking skills/mcp/hooks compliance, or validating local-first configuration. Do not use for st...
Install, manage, and remove Claude skills from GitHub repositories. Use when you need to add new skills from git or manage installed skills.
Proactively capture and archive project discoveries during work. Maintains CLAUDE.md by capturing working commands, architectural decisions, gotchas, and insights as they emerge during development. Use during a...
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks (skills/commands/a...
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks with PreToolUse/Po...
Orchestrate parallel Claude Code agents across git worktrees for large implementations
Analyze claude-trace JSONL files for session health, patterns, and actionable insights. Use when debugging session issues, understanding token usage, or identifying failure patterns.
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks,...
Anthropic Claude plugin "clangd-lsp" の内容を参照して作業するときに使うスキル。claude-plugins-official の plugins/clangd-lsp を参照する必要がある場合に使用する。
Extracts reusable patterns from Claude Code sessions and captures knowledge as atomic memory units. Use when session ends (Stop hook), when recording technical decisions, implementation insights, or lessons lea...
.claude/skills/以下に新しいスキルを作成するためのガイドとテンプレートを提供します。スキルの目的、アクティベーション条件、チェックリスト、詳細なリファレンス、例、テンプレートの作成を支援します。
Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation for complex tasks, refactors, or API changes.
Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or API integration.
Review Claude Code skills for quality and correctness
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
Analyze the current repository and create or refresh .claude/PROJECT.md to match the project. Use when PROJECT.md is missing, stale, or the user asks to generate/update project-specific rules, structure, comman...
Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (plan validation + implementation review)
Universal guide for all unmangleJS pass development tasks. Covers creating, modifying, debugging, refactoring, reviewing, and documenting passes. Integrates with existing project documentation - see CLAUDE.md f...
Model Context Protocol server for Sigil MPC signing. Use for deploying Sigil as a universal agent-compatible signing server that works with Claude Desktop, VS Code, and any MCP-compliant client.
Codex CLI（read-only）を用いて、レビュー→Claude Code修正→再レビュー（ok: true まで）を反復し収束させるレビューゲート。仕様書/SPEC/PRD/要件定義/設計、実装計画（PLANS.md等）の作成・更新直後、major step（>=5 files...
Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code
Bootstrap and install BMAD-METHOD skills for Claude Code, Cursor, Antigravity, and other tools.
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and Opencode backends with file references (@syntax) and structured output.
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.