Skills matching the name, description or GitHub author.
This skill should be used when the user asks to "analyze this project", "what type of project is this", "detect project structure", "understand this codebase", or when Claude needs to determine project type for...
Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so Claude can see client-side errors. Essential for...
Fork terminal to new window with Claude Code, Codex CLI, Gemini CLI, or raw commands.
Implements MCP (Model Context Protocol) server for ZoneWise zoning queries. Exposes tools for district lookup, permitted uses, setbacks, density calculations, and site analysis. Built with FastMCP (Python) or M...
Guides structure decisions for Next.js App Router projects with TypeScript. Invoked by prompt-classifier on PLANNING/IMPLEMENT sequences via "plan-structure". Focuses on minimal, colocated organization per CLAU...
Execute implementation plans in batches with Claude CodePro
This skill should be used when the user asks about "memory", "remember this", "what do you know about me", "recall", "forget this", "search memories", "save preference", or when Claude needs guidance on using m...
Create comprehensive feature specifications for Claude Code projects using iterative refinement with ISO/IEC/IEEE 29148:2018 criteria. Use when user requests creating a technical specification (ТЗ) for a new fe...
Code review for all uncommitted changes (staging status is irrelevant). Checks CLAUDE.md compliance, identifies bugs, security issues, style problems, and simplification opportunities.
Review recent code changes, check against standards, and suggest CLAUDE.md updates. Use this after completing a feature or before committing.
Analyze Claude Code releases and recommend plugin improvements
Run multiple Claude Code sessions simultaneously using git worktrees. Use when discussing parallel work, worktrees, concurrent development, or multiple sessions.
Retrieval-augmented Lean4 proof generation. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25 + semantic + graph), generates via Claude, compiles in Docker, retries on failure.
Gemini CLIを呼び出して、Claude Codeの機能を補完する。以下の場合に使用: (1) マルチモーダル分析 - 画像/音声/動画/PDFファイルの処理 (2) 大規模コンテキスト分析 - プロジェクト全体のコード分析（100万トークン活用） (3...
Comprehensive guide for AI agents on proper Claude-style tool calling with correct syntax, patterns, and examples
Update a skill from the canonical ClaudeSkills repository. Use to sync local skills with latest versions.
Update a skill from the canonical ClaudeSkills repository. Use to sync local skills with latest versions.
Autonomous development loop with fresh context per iteration. Uses an external bash loop that spawns fresh Claude sessions, storing state in files to prevent context drift. Based on the original Ralph Wiggum te...
This skill should be used when users want to restore, reload, or copy their Claude Code configuration files (commands, skills, agents) from a backup directory back to ~/.claude/. Triggered by phrases like "rest...
Expert in Model Context Protocol (MCP) server development. Use when building MCP servers, creating tools for Claude, implementing resources, debugging MCP connections, or integrating databases with Claude Code.
Set up a cross-platform Ralph Wiggum loop for continuous autonomous Claude execution. Use when the user wants to run Claude in a loop, implement the Ralph technique, or needs continuous autonomous operation. Th...
启动或推进多 Agent 并行开发流程。用于协调多个 Claude Code 实例并行开发项目。
Call claude to perform a task.
Expert guidance for building autonomous AI agents using Anthropic's Claude Agent SDK (Python). Covers: agent loop patterns (GTVR: gather context, take action, verify, repeat), ClaudeSDKClient and query() APIs,...
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.