cobusgreyling — 6 Open-Source AI Agent Skills

cobusgreyling is the author of 6 open-source AI agent skills and MCP servers spanning mcp-server, uncategorized, codex-skill, agent-tool, with a combined 11,596+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 60/100) and security-graded where a README exists (4 of 6) — 4 verified safe.

Top skills by cobusgreyling

• loop-engineering — Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (insp (11.4k★ · quality 72/100 · security: safe)
• Jev — Unofficial TypeSafe Jev showcase — System One decisions, not chat. (131★ · quality 64/100 · security: safe)
• llm-wiki — A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern (45★ · quality 70/100 · security: safe)
• agent-skills — Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.) (7★ · quality 56/100 · security: safe)
• is-the-missing-piece-in-ai-agent-tools — Markdown version of the blog post: Is The Missing Piece in AI Agent Tools? (1★ · quality 45/100)
• committee-protocol — Pi_k,m,r — propose/critique/compare orchestration that lets a weak reasoning model match frontier performance on verifier-backed tasks. (0★ · quality 56/100)

View cobusgreyling on GitHub · Explore audited agent skills