Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: guardrails

英語版ディレクトリ

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.

2.5K
Stars
85/100
信頼
カテゴリ: agent-frameworks監査

ccteam turns the coding agents you already run (Claude Code, Codex, Grok, Kimi…) into one team — any session can spawn, dispatch, and collect work from any vendor on any machine, while you steer it all from Telegram, Lark, or a browser tab. 把你在用的编程 agent 编成一支团队,跨厂商跨机器派活,Telegram/飞书/网页统一指挥。

160
Stars
75/100
信頼
カテゴリ: utility監査

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

1.2K
Stars
85/100
信頼
カテゴリ: devops監査

Pre-install security scanner and guarded installer for Agent Skills. Quarantine, scan, enforce policy, and verify skills before they reach Codex, Claude Code, Cursor, Gemini CLI, or OpenClaw.

129
Stars
74/100
信頼
カテゴリ: utility監査

A meta-skill that creates, evaluates, and improves other AI agent skills with multiple modes and evidence-based validation.

133
Stars
77/100
信頼
カテゴリ: utility監査

Open-source AI agent skills and 80+ strategy templates for autonomous trading on Hyperliquid, packaged as a reusable skill repository.

107
Stars
74/100
信頼
カテゴリ: finance-quant監査

AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability, guardrails, streaming, costs and usage tracking.

946
Stars
72/100
信頼
カテゴリ: devops監査

Claude Code skills plugin for Git, GitHub, and skill authoring workflows

70
Stars
64/100
信頼
カテゴリ: utility監査

A governance framework that enforces a five-step workflow for AI coding agents with evidence checks.

94
Stars
68/100
信頼
カテゴリ: coding-agents監査

A collection of 24 installable agent skills for coding agents covering UI audits, typography, docs, PR review, and releases, with clear installation via npx.

75
Stars
67/100
信頼
カテゴリ: coding-agents監査

Static analysis tool that catches 1000+ bug patterns across all popular programming languages, with auto-wiring into AI coding agent quality guardrails

255
Stars
64/100
信頼
カテゴリ: coding-agents監査

An Agent Skill to use Problem-Based Software Requirements Specification (SRS) method in your software project.

30
Stars
69/100
信頼
カテゴリ: utility監査