A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
22 packages found
Hooks that force Claude Code to use LSP instead of Grep for code navigation. Saves ~80% tokens
一个面向 Claude、Codex 等 AI coding agents 的 harness-first 模板，让 AI 在读完 README 后就能理解项目并接手开发。
Claude Code template for building n8n workflows — onboarding agent, expert build agent, 7 n8n skills, n8n-mcp pre-config
Prevent Claude Code from breaking your non-UTF-8 files. Preserve your file as it is (also line ending format).
Claude Code Stop hook that nudges granular commits after every turn. Guarded for rebases, merges, detached HEAD. Pure ba
Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and know
Metacog isn't memory for LLMs, it gives them a nervous system. Metacognition developed on your unique user experiences.
让你的 Claude Code 会说话 — 自动语音朗读中文内容，8种微软官方音色可选，实时切换，免费无需API Key，跨平台支持
Template for using Claude Code as a planning and implementation engine across target projects. Structured context, goal-
🔊 Cross-platform Claude Code plugin that plays distinct sounds when Claude finishes a task vs. when it needs your input
Claude Code hook sounds – Warcraft, StarCraft, Mortal Kombat
Structured code review — style, bugs, security, performance checks
Semantic code search — makes your entire codebase context-aware for Claude agents
Pre-commit hooks for validating Claude Code config files with auto-fix
An LLM council that reviews your coding agent's every move for quality assurance
Official SonarQube MCP server for code quality metrics, issues, and quality gate status
Code intelligence MCP — 42-language AST parsing, FalkorDB knowledge graphs
Experimental skills extending Claude Code with novel techniques like semantic deduplication
Community-editable skills for Claude Code's superpowers framework — TDD, debugging, and more
Legacy code modernization — strangler fig, incremental migration, risk assessment
Devil's advocate code review — find edge cases, race conditions, failure modes
Codebase debt scanner — prioritization, trend tracking, refactor planning