lintsinghua — 4 Open-Source AI Agent Skills

lintsinghua is the author of 4 open-source AI agent skills and MCP servers spanning llm-plugin, mcp-server, claude-skill, agent-tool, with a combined 11,422+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 54/100) and security-graded where a README exists (2 of 4) — 2 verified safe.

Top skills by lintsinghua

• DeepAudit — DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。​让安全不再昂贵，让审计不再复杂。 (7.1k★ · quality 51/100)
• claude-code-book — 《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站： (4.3k★ · quality 53/100 · security: safe)
• paint-mv-skills — Agent skills that turn a song and its lyrics into a hand-painted watercolour music video (p5.brush + headless Chrome + ffmpeg), following PD (30★ · quality 64/100 · security: safe)
• Crawl4Agent-skill — Advanced web crawler skill for AI agents — anti-bot bypass, Chinese platform support, login handling, and template library. (1★ · quality 49/100)

View lintsinghua on GitHub · Explore audited agent skills