Earn 2.2k Stars: Best Practices for Building Pro Agent Skills
tom_doerr · x · 2026-08-01
This is a GitHub repository with over 2.2k stars that systematically outlines best practices for writing professional-grade skills for AI agents.
Key highlights include:
- Directory Structure: Each skill should contain a SKILL.md (core instructions, ideally <500 lines), scripts/ (executable code), references/ (supplementary context), and assets/ (static files).
- LLM Validation: Recommends using LLMs to validate the effectiveness of skills and prevent regressions.
- Lean Context: Emphasizes the importance of maintaining a lean context window when developing skills to optimize agent execution.
More from coding & agent
- Open-Source Semantica Adds Context Graphs and Audit Trails to AI Agents — tom_doerr · 2026-08-01
- Can an Autonomous AI Engineer Maintain a Real Open-Source Project Long-Term? — AmbitiousBattle4892 · 2026-08-01
- Claude Demonstrates Cross-Tab Awareness by Catching User in Wrong Tab — ZeroStateReflex · 2026-08-01
- Uploading PDFs to AI Burns 3x More Tokens — Here's the Fix — lxfater · 2026-08-01
- Teknium Tests DeepSeek V4 Flash: Full Agent Task Costs Just $0.07 — Teknium · 2026-08-01
- Omarchy Quattro Update: Auto-Detects Claude and Codex Subscriptions to Track Usage — jxnlco · 2026-08-01