RESOURCE2SKILL turns multimodal resources into executable agent skills
microsoft · hf · 2026-07-20
Microsoft and collaborators introduce **RESOURCE2SKILL**, a framework that distills multimodal human resources—tutorial videos, repositories, articles, and reference artifacts—into executable skills for software agents. - It organizes skills into a hierarchical **multimodal Skill Wiki**. - Each entry combines structured text, code, visual examples, metadata, and provenance so agents can reuse complementary signals from different sources. - At inference time, agents retrieve and compose skills from the wiki; if coverage is insufficient, the same operator can acquire new skills online. - Across seven practical authoring domains, the method improves average overall score by **+11.9 points** over no-skill agents and beats strong harness baselines in **26 of 28** main-aggregate model-domain cells. - Ablations show gains from multimodal format, hierarchy, source diversity, selection strategy, and online acquisition.
Related event: Microsoft and Teams Introduce RESOURCE2SKILL(2 posts)→
More from coding & agent
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21
- Sonar CEO says a guide-verify-solve loop cuts coding-agent issues by 92% — alex_verem · 2026-07-21
- OpenAI’s Codex app is good enough that one user would pay for it even with open models — drdanielbender · 2026-07-21
- A creator built an Awwwards-style landing page with ChatGPT 5.6 Sol in one conversation — paw_lean · 2026-07-21
- A creator rebuilt a personal website as a Jupyter Notebook with Codex — paw_lean · 2026-07-21
- OpenAI’s Build Week buildathon drew 40 people for 11 hours with Codex — paw_lean · 2026-07-21