Open-Source Directory — Claude / Anthropic

Claude
Tools

A curated index of extensions, plugins, MCP servers, hooks, and integrations for Claude — discovered from GitHub and refreshed daily.

Repository Growth — Last 30 Days

8281entries
★ starsA–Z name

vibemon-hooks

★ 7
@Streamize-llc

Bash + Python that VibeMon runs on user machines. Public, reproducible-build, audit-friendly hook installer for Claude Code / Gemini CLI / Cursor / Codex.

updated Sep 2026

orbit-prompt

★ 7
@IanVDev

A Claude Code skill that turns every AI request into a clear, constrained and verifiable prompt before execution.

updated Aug 2026

STCA-skills

★ 7
@SuperteamCanada

Curated Agentic skills for Canadian founders

updated Oct 2026

groundtruth

★ 7
@vnmoorthy

A completion-claim gate for Claude Code. Refuses to let the agent say done without evidence.

updated Oct 2026

presence

★ 7
@sara-star-quant

Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.

updated Sep 2026

autohook-coding-agent-superpowers

★ 7
@lbartoszcze

💻 Optimal configuration of a claude code addict. Automatic hook creation to make sure that if something frustrating happens, it never happens again. Self-evolving coding agent harness. Make your Coding Better, Faster, Stronger.

updated Jun 2026

werkstatt

★ 7
@Bollwerkio

Skills, hooks, and workflow discipline for Claude Code, Codex, Cursor & OpenCode. Turn an AI coding assistant into a rigorous engineer.

updated Jul 2026

delegate-local

★ 7
@IsmaelMartinez

Claude Code skill that delegates summarisation, log triage, and bulk-text tasks to local models. Saves API tokens, keeps content on-device, hardware-aware model auditing.

updated Oct 2026

production-audit

★ 7
@commitshow

Claude Code skill that audits a shipped repo for the production-readiness gaps ~70% of AI-coded projects miss · companion to in-session security skills, scans the deployed product not the editor buffer

updated Oct 2026

dev-team-agents

★ 7
@Dev-Toolbelt

Multi-agent development harness for Claude Code, Codex CLI, and opencode — stack-agnostic, project-aware agents, commands, skills, and hooks for planning, building, reviewing, and documenting software.

updated Oct 2026

mcp-fileencoding

★ 7
@jidzhang

一个MCP服务器,解决AI编码助手在Windows中文环境下读写GBK/GB18030文件时乱码的问题。读取时自动检测编码并转为UTF-8返回给AI,写入时自动转回原始编码,文件编码保持不变。还保证编辑写回时缩进风格与换行符(CRLF/LF)与原文件一致。支持UTF-8(含BOM)、GBK、GB2312、GB18030等编码。提供read、write、edit、查询编码记录等6个工具,通过PreToolUse Hook或系统提示词引导AI按需使用。适用于Claude Code、Cursor等支持MCP的客户端。Python 3.10+,pyright strict零错误,175个测试全部通过。

updated Sep 2026

claude-code-deepseek-3p-parity-skill

★ 7
@kingcharleslzy-ai

修复 Claude Code Desktop 接入 DeepSeek/第三方模型后能力缺失、联网失败、频繁权限弹窗的 Claude Skill

updated Sep 2026

claude-pets

★ 7
@xianshang33

🐾 Claude Pets brings Codex-style desktop companions to Claude Code, with local hooks, animated pets, and permission controls.

updated Sep 2026

job-hunt-skill

★ 7
@CalebLiu

End-to-end Claude Code skill for job applications. 8 phases, 2 sub-skills, originally built for UK AI startup hunt, generalised. Bilingual EN/中文.

updated Oct 2026

claude-code-plugins

★ 7
@zhebil

Claude Code plugin marketplace with developer productivity hooks

updated Oct 2026

skillguard

★ 7
@yangyixxxx

Local-first security scanner for AI Skill bundles. 72 rules, < 2s, zero LLM cost. Apache-2.0. SaaS at skillguard.vip

updated Jul 2026

macos-26-design

★ 7
@juanlara-aidev

macOS 26 (Liquid Glass) como skill drop-in para Claude Code, Cursor y Gemini CLI.

updated Sep 2026

claude-skills

★ 7
@startx-founders

Community-curated catalog of Claude Code skills built by StartX founders. Curated, not Anthropic-audited.

updated Jun 2026

html-effectiveness

★ 7
@Azhi-ss

Agent Skill that teaches Cursor & Claude Code to output single-file HTML for spatial, parallel, comparable, or interactive content. 9 categories, 20 patterns, 12 ready-to-use templates. Inspired by Thariq Shihipar's 'unreasonable effectiveness of HTML'.

updated Oct 2026

playing-to-win

★ 7
@paultaki

Playing to Win strategy framework as a Claude Code skill. Pressure-test business ideas through Roger Martin and A.G. Lafley's choice cascade.

updated Sep 2026

core-agent

★ 7
@go-steer

Reusable Go base agent on the Google ADK — multi-provider (Gemini, Vertex, Claude on Anthropic + Vertex), MCP-native, with AGENTS.md, skills, and permissions wired up.

updated Oct 2026

instrument-claude

★ 7
@AstraBert

Hooks-based, OTel-compatible observability for Claude Code

updated Oct 2026

vessel-traffic-mcp

★ 7
@tools-mcp

Read-only MCP server for vessel AIS, ship tracking, schedules, and BYOK maritime providers

updated Oct 2026

ai-video-skill

★ 7
@0xadvait

The AI video skill for Claude Code that learns — end-to-end generation across 6 models (Seedance 2.0, Kling, Wan, Veo, OmniHuman) with a self-improving quality-control loop

updated Oct 2026
← PREV01...238239240241242...346NEXT →