🔓The meta-skill that builds and improves all your skills, including itself. Watches your work sessions, captures corrections and judgement calls, and turns th…
// skillsrebelytics/★ 3,170◷ CC-BY-4.0[ claude ]
Hidden Gems
// healthy, active, under-viewed — the undiscovered long tail
// observatory (2347)
🔓
🔓16 cross-platform Agent Skills for enterprise ontology engineering, supporting Codex, Claude Code, and WorkBuddy.
// skillsSuperChason/⟨Python⟩★ 15◷ MIT[ claude ]
🔓Claude Design in Claude Code, Codex, Cursor, and 20+ agents. Designs come from your real components, tokens, and states; approved revisions sync back.
// skillsmaxritter/⟨Python⟩★ 28◷ NOASSERTION[ claude ]
🔓Beautiful, AI-native markdown IDE and LLM wiki
// uncategorizedinkeep/⟨TypeScript⟩★ 4,344◷ GPL-3.0[ claude ]
🔓Interactive patcher for the Claude Code native binary. Live inline thinking, detailed tool calls, subagent model overrides, custom branding — and your ChatGP…
// devtoolsanfreire/⟨Python⟩★ 19◷ MIT[ claude ]
🔓Claude Code Skill for browser automation with Playwright. Model-invoked - Claude autonomously writes and executes custom automation for testing and validation.
// skillslackeyjb/⟨JavaScript⟩★ 3,168◷ MIT[ claude ]
🔓Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and…
// ragrohitg00/⟨JavaScript⟩★ 2,899[ claude ]
🔓你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
// automationtanweai/⟨TypeScript⟩★ 19,713[ claude ]
🔓A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestratio…
// automationyzhao062/⟨Python⟩★ 10,015◷ BSD-2-Clause[ claude ]
🔓Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orc…
// securitygadievron/⟨Python⟩★ 3,817◷ NOASSERTION[ claude ]
🔓Connect AI models like Claude & GPT with robots using MCP and ROS.
// uncategorizedrobotmcp/⟨Python⟩★ 1,480◷ Apache-2.0[ claude ]
🔓Watch your Claude Code agents work as a pixel-art office. Replay any second of a session exactly, see what every agent cost. Read-only, 100% local, never cal…
// devtoolsKostakurta8/⟨TypeScript⟩★ 21◷ MIT[ claude ]
🔓The official Rust SDK for the Model Context Protocol
// uncategorizedmodelcontextprotocol/⟨Rust⟩★ 3,976◷ NOASSERTION[ claude ]
🔓88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemi…
// skillssandbaseai/⟨Python⟩★ 202◷ Apache-2.0[ claude ]
🔓One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.
// ragrahilp/⟨TypeScript⟩★ 786◷ MIT[ claude ]
🔓A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware eng…
// devtoolsbjgreenberg/⟨Shell⟩★ 151◷ Apache-2.0[ claude ]
🔓WeChat group & official-account AI knowledge digest — agent-friendly (Codex/Claude Code), Windows/macOS/Linux
// integrationsJackyCufe/⟨Python⟩★ 75◷ Apache-2.0[ claude ]
🔓Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
// uncategorizedsimstudioai/⟨TypeScript⟩★ 29,765◷ Apache-2.0[ claude ]
🔓Agent skills for Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent and other agentskills.io-compatible agents. See https://developert…
// skillswondelai/⟨Shell⟩★ 2,263◷ MIT[ claude ]
🔓See how many times over each AI plan has paid for itself — Claude Code, Codex and the rest, priced against the published API rates, at the edge of your Mac's…
// devtoolsReffWu/⟨Swift⟩★ 23◷ MIT[ claude ]
🔓Open-source plugin marketplace for AI coding assistants — write skills once, ship to Claude Code, Cursor, OpenAI Codex, OpenCode, Gemini CLI, and AGENTS.md h…
// devtoolsbravew/⟨TypeScript⟩★ 10◷ MIT[ claude ]
🔓macOS 菜单栏工具，聚合显示多个 AI 编程/Agent工具（Claude Code / Codex / Cursor / Qoder / 悟空/ Workbuddy 等）的 token 用量，全本地直读零配置
// devtoolsChanningYuan/⟨Swift⟩★ 28◷ MIT[ claude ]
🔓Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works wit…
// ragVonderVuflya/⟨Python⟩★ 21◷ AGPL-3.0[ claude ]
🔓Open-source Agent Skill that scores AI-sounding writing 0–100, edits it with your assistant, and checks source details locally.
// skillsmanavmishra/⟨Python⟩★ 123◷ MIT[ claude ]
🔓蒸餾 Fable 5 後，產出索引式 CLAUDE.md + 按需 rules + skills，為較弱模型的 session 設計的可執行規範。
// othercurtischoutw/⟨Python⟩★ 5◷ MIT[ claude ]
🔓Exa MCP for web search and web crawling!
// mcp-serversexa-labs/⟨TypeScript⟩★ 5,084◷ MIT[ claude ]
🔓Keep Claude Fable 5 (or Opus) as your daily driver without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: model-t…
// automationRylaa/⟨Python⟩★ 78◷ MIT[ claude ]
🔓Claude Skill for making human sounding docs
// devtoolsstephenoffer/⟨Python⟩★ 38◷ MIT[ claude ]
🔓A Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored p…
// pluginsWunderlandmedia/⟨Python⟩★ 92◷ MIT[ claude ]
🔓Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig
// integrationsnullclaw/⟨Zig⟩★ 8,106◷ MIT[ claude ]