Skip to main content
VERIFYING TELEMETRY
SafeOpenSource Cryptographic Engine
Autonomous Agent Ecosystem

AI Agent Skills Directory

Agent Skills equip autonomous AI coding agents (Claude Code, Hermes Agent, Cursor, Codex, OpenHands) with specialized operational workflows, security telemetry, database branching, and hardened container configurations. Skills our finder adds are scored like every tool on the site and checked for dangerous instructions (such as piping a download into a shell) before they are listed.

AI AGENT SKILLS

Browse AI Agent Skills (31)

Security & AuditNetwork & API

SafeOpenSource Verification

by SafeOpenSource.org·★ 1420
Safety Score98/100

Inspect repository supply-chain health, OpenSSF Scorecards, and unpatched CVEs before pulling open-source dependencies or Docker images.

Key Autonomous Capabilities:
✓Query 0-100 real-time Safety Scores for 200+ catalog repositories
✓Detect unpatched remote-code execution CVEs and dormant maintainer status
✓Generate production-hardened docker-compose templates with non-root UID
✓Check SPDX license compliance (AGPL vs MIT vs Apache-2.0)
Compatible:Claude CodeHermes AgentCursorCodexOpenHands
npx skills add safeopensource
Inspect SKILL.md→
Databases & StorageNetwork & API

Neon Serverless Postgres

by Neon Databricks·★ 3410
Safety Score97/100

Manage Lakebase Postgres branches, execute serverless SQL queries, create zero-copy schema forks for CI, and optimize indexing.

Key Autonomous Capabilities:
✓Instant copy-on-write database branching for preview environments
✓Zero-filesystem HTTP driver integration (@neondatabase/serverless)
✓Inspect query execution plans, missing indexes, and connection pools
✓Seamless Drizzle and Prisma ORM migrations
Compatible:Claude CodeHermes AgentCursorCodexOpenHands
npx neon skills -s neon-postgres -y
Inspect SKILL.md→
Healthy

ui-ux-pro-max-skill

by nextlevelbuilder·★ 145899
Safety Score94.3/100

An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.

Healthy

taste-skill

by Leonxlnx·★ 110931
Safety Score94.1/100

Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

Healthy

chrome-devtools-mcp

by ChromeDevTools·★ 54868
Safety Score93.1/100

Chrome DevTools for coding agents

Healthy

github-mcp-server

by github·★ 34276
Safety Score92.3/100

GitHub's official MCP Server

Healthy

n8n-mcp

by czlonkowski·★ 23220
Safety Score90.7/100

A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you

Healthy

mcp-for-beginners

by microsoft·★ 17614
Safety Score90.1/100

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.

Healthy

xiaohongshu-mcp

by xpzouying·★ 16954
Safety Score90.1/100

MCP for xiaohongshu.com

Healthy

Skill_Seekers

by yusufkaraaslan·★ 15285
Safety Score89.9/100

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

Healthy

Vibe-Skills

by foryourhealth111-pixel·★ 3801
Safety Score85.7/100

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

Healthy

ai-manju-skills

by zhanghao123vip·★ 595
Safety Score85.5/100

21 个题材的 AI 漫剧全流程 Skill:一句点子生成企划案、资产图提示词、分集剧本、分镜与视频提示词。可用于 Claude Code、WorkBuddy、DeepSeek

Healthy

ai-research-skills

by WenyuChiou·★ 602
Safety Score85.5/100

Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.

Healthy

anythingmcp

by HelpCode-ai·★ 756
Safety Score85.5/100

Company brain for AI agents as MCP gateway. Connect your infrastructure and services, APIs, databases, file servers, memory, skills and knowledge graph to Claude, ChatGPT, Gemini and Microsoft Copilot. With SSO/RBAC, audit, user roles and self learning. 600+ predefined connectors (SAP, Odoo, Telegram …).

Healthy

claude-skill-registry

by majiayu000·★ 715
Safety Score85.5/100

Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts

Healthy

flutter-ai-rules

by evanca·★ 669
Safety Score85.5/100

Flutter AI Skills and Rules for Claude, Codex, Cursor, and Other AI-Powered IDEs

Healthy

pm-skills

by product-on-purpose·★ 788
Safety Score85.5/100

68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundation + 12 utility + 15 tool (Foundation Sprint + Design Sprint). Plus 6 sub-agents, workflows, 200+ output samples, guides, and CI-enforced contracts. Apache 2.0.

Healthy

sap-skills

by secondsky·★ 491
Safety Score85.5/100

Production-ready plugins for SAP development with AI coding assistants — BTP, CAP, Fiori, ABAP, HANA, Analytics Cloud, Datasphere, and more

Healthy

SkillNet

by zjunlp·★ 1450
Safety Score85.5/100

Create, Evaluate, and Connect AI Skills

Healthy

skillpack

by CreminiAI·★ 1205
Safety Score85.5/100

Pack and deploy local AI agents for your team in minutes

Healthy

wechat-article-skills

by aiworkskills·★ 727
Safety Score85.5/100

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill,支持 OpenClaw / Claude Code / Cursor / Codex

Caution

golive-skill

by mikehasa·★ 1400
Safety Score83.8/100

Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, backend or telemetry.

Caution

agent-rules-books

by ciembor·★ 3208
Safety Score80.7/100

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Cl

Caution

ai-skills

by sanjay3290·★ 451
Safety Score80.7/100

24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, TTS, DevOps

Caution

compass-skills

by dongshuyan·★ 764
Safety Score80.7/100

司南:个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

Caution

skills

by wondelai·★ 2610
Safety Score80.7/100

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journ

Caution

agent-skills

by TheQtCompanyRnD·★ 523
Safety Score78.5/100

Official Qt AI engineering skills for Claude Code, Codex, Copilot, Gemini,and other AI coding tools

Caution

best-skills

by LinklyAI·★ 748
Safety Score78.5/100

Daily-updated Top 100 Agent Skills rankings — installs, growth, and social buzz aggregated from skills.sh, ClawHub, Tencent SkillHub, GitHub, X and 10+ communities. Open data (CSV).

Caution

Claude-Skills

by borghei·★ 1056
Safety Score78.5/100

385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.

Caution

one-skill-to-rule-them-all

by rebelytics·★ 3751
Safety Score78.5/100

The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0.

Caution

Light-skills

by Light0305·★ 872
Safety Score74.7/100

An AI workflow skill pack for research, competitions, and innovation projects.

SKILL ARCHITECTURE & SPECIFICATION

How Agent Skills Work

An agent skill is an open-standard SKILL.md specification that provides autonomous LLM runtimes with procedural memory, deterministic tool-calling workflows, and safety constraints.

01 / DISCOVERY

Automatic Loading

Agents discover installed skills through standard CLI registries (npx skills or hermes skill) and only load instructions when relevant to the user's prompt.

02 / SANDBOXING

Explicit Permissions

Every skill declares its execution boundary: Read-Only filesystem access, Network & API calls, or Full Shell execution with human-in-the-loop validation gates.

03 / SECURITY

Supply-Chain Auditing

SafeOpenSource continuously scans agent skills for prompt injection vulnerabilities, dangerous eval calls, and credential leakage before awarding verified status.

FLAGSHIP REPOSITORY SKILLSKILL.md v1.0

Install the SafeOpenSource Skill Today

Teach your coding agent to verify open-source package safety, scan for unpatched CVEs, check copyleft license risks, and output production-hardened Docker Compose setups before writing a single line of infrastructure code.

CLI
ONE-CLICK INSTALLATION FOR ALL AGENTS:npx skills add safeopensource
Works with Claude Code, Cursor, Hermes, & Codex