Repo-To-Skill: distilling 1,000 GitHub repos into 5,000+ verified agent skills
rohanpaul_ai · x · 2026-09-06
The arXiv paper "Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills" (Jianlyu Chen et al.) presents DisCo, a skill-powered research agent. It targets the missing "operational knowledge" layer — the gap between knowing a method and making it work — which lives in human-oriented repos and papers too large to load at task time.
Distillation runs in two forms: task-agnostic (condensing widely used repos into reusable skills) and task-oriented. The former yields the AREX-Skill Library: 5,000+ verified skills from 1,000 widely used ML repositories, organized into 20 areas and 178 capability families. With the GPT-5.5 backbone and execution budget fixed, MLE-bench improves 134.3% and PaperBench 34.4%.
More from coding & agent
- Indie dev's agent tracks 519 directories, 311 submitted for SEO backlinks — fekdaoui · 2026-10-23
- ScienceClaw Hackathon at MIT Media Lab to build decentralized AI agent collectives for science — ProfBuehlerMIT · 2026-10-23
- What should a native agent harness handle beyond tool calling? — Glittering812 · 2026-10-23
- Running ~100 DeepSeek v4.1 flash agents in parallel for under $20/month — zack_overflow · 2026-10-23
- MCP's stateless 2026-07-28 spec drops session-id — how are stateful tools adapting? — Stock-Pumpkin-8859 · 2026-10-23
- Dev adds local MCP server to Mac screenshot app so Claude designs from your references — Embarrassed-Ebb-740 · 2026-10-23