jnMetaCode — 7 Open-Source AI Agent Skills
jnMetaCode is the author of 7 open-source AI agent skills and MCP servers spanning codex-skill, mcp-server, agent-tool, claude-skill, with a combined 30,320+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 62/100) and security-graded — 6 verified safe.
Top skills by jnMetaCode
- agency-agents-zh — 🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）。搭配编排器 ag (19.5k★ · quality 62/100 · security: safe)
- superpowers-zh — 🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemi (7.7k★ · quality 60/100 · security: safe)
- agency-orchestrator — 🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/i (2.1k★ · quality 61/100 · security: safe)
- ai-coding-guide — AI 编程工具实战指南 — 66 个 Claude Code 技巧 + 9 款工具最佳实践 + 可复制配置模板 | AI Coding Tools Guide with 66 Claude Code tips (491★ · quality 60/100 · security: safe)
- ai-shortfilm-prompts — Claude Code Skill that turns any idea into a cinematic, model-ready video prompt — Sora · Kling · Veo · Seedance. 21 genre templates, 5-stag (357★ · quality 69/100 · security: safe)
- shellward — AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源 (129★ · quality 73/100 · security: safe)
- tracelet — tracelet — local-first DevTools for AI agents. Point any OpenTelemetry exporter at localhost and watch the execution tree (LLM calls, tools, (0★ · quality 51/100)
View jnMetaCode on GitHub · Explore audited agent skills