Safer agent skills

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Score basis：Source needs review · High risk signals · Claude

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization.

Score basis：Clear source · Risk needs review · Claude

Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time.

Score basis：Clear source · Risk needs review · Universal

Forge is a self-hosted middleware that unifies access to multiple AI model providers (like OpenAI, Anthropic) via a single API.

Score basis：Clear source · Risk needs review · Universal

Multi-subscription extension for pi -- use multiple OAuth accounts per provider (Anthropic, Codex, Copilot, Gemini, Antigravity)

Score basis：Clear source · Risk needs review · Universal

AetherLink is a cross-platform AI assistant application that supports multiple mainstream AI models (OpenAI, Google Gemini, Anthropic Claude, Grok, etc.).

Score basis：Clear source · Risk needs review · Universal

Answer questions about the AI SDK and help build AI-powered features.

Score basis：Clear source · Low risk signals · Claude

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.

Score basis：Clear source · Low risk signals · Claude

Unified search skill with Intelligent Auto-Routing.

Score basis：Source needs review · Low risk signals · Claude

Neon Postgres skill from neondatabase/agent-skills.

Score basis：Clear source · Low risk signals · Claude

Anthropic Dev Container Features, including Claude Code CLI

Score basis：Clear source · Risk needs review · Universal

Anthropic (Claude) API + Ruby!

Score basis：Clear source · Risk needs review · Universal

Agentic pentest tooling.

Score basis：Clear source · Risk needs review · Universal

An unofficial C#/.NET SDK for accessing the Anthropic Claude API.

Score basis：Clear source · Risk needs review · Universal

🤖 A Matrix bot for using different capabilities (text-generation, text-to-speech, speech-to-text, image-generation, etc.) of AI / Large Language Models (OpenAI, Anthropic, etc.)

Score basis：Clear source · Risk needs review · Universal

这是一个部署在 Cloudflare Workers 上的 TypeScript 项目，它充当一个代理服务器，能够将 Claude API 格式的请求无缝转换为 OpenAI API 格式。这使得任何与 Claude API 兼容的客户端（例如官方的 @anthropic-ai/claude-code CLI）都能够与任何支持 OpenAI API 格式的服务进行通信，如 Google Gemini, Groq, Ollama 等。

Score basis：Clear source · Risk needs review · Universal

Community Plugins for Genkit (OpenAI, Groq, Anthropic, Cohere, etc)

Score basis：Clear source · Risk needs review · Universal

Engine-agnostic LLM gateway in Rust.

Score basis：Clear source · Risk needs review · Universal

Claude Code 泄露源码深度分析 — 基于 2026-03-31 泄露的 Anthropic Claude Code CLI 完整 TypeScript 源码（~1,884 文件，512K+ 行）的逐模块架构解读

Score basis：Clear source · Risk needs review · Universal

Turn VS Code into your compliant AI playground!

Score basis：Clear source · Risk needs review · Universal

《深入理解 Claude Code 源码》— 系统剖析 Anthropic Claude Code CLI 的架构设计、工程实践与编程哲学 | 25 chapters, 101 Mermaid diagrams, 467 code blocks

Score basis：Clear source · Risk needs review · Universal

Source code of @anthropic-ai/claude-code v2.1.88, extracted from the npm package's source map (cli.js.map).

Score basis：Clear source · Risk needs review · Universal

从 @anthropic-ai/claude-code npm 包的 cli.js.map 中还原出的完整 TypeScript 源码，可一键本地编译运行。

Score basis：Clear source · Risk needs review · Universal

A simple proxy for AI services including OpenAI, Anthropic, Gemini, Groq, Perplexity

Score basis：Clear source · Risk needs review · Universal