註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

EverMind
@evermind
Long-term agent memory | self-improving | agent harness
加入 November 2025
21 正在關注    4.3K 粉絲
Yet another paper. This time, we asked a practical question: Do public SKILL.md files actually make agents better? The open skill ecosystem has a quality problem. The hard part isn’t finding more skills. It’s knowing which ones are unique, useful, safe, permissively licensed, and relevant to the task. We crawled ~821K public skills and curated them into 96,401. Then we tested the full retrieval pipeline across 3 benchmarks, 2 harnesses, and 2 open backbones. It improved all three benchmarks, with the largest pooled gain at +7.5pp on SkillsBench. More skills are not automatically better. Curation, retrieval, and the harness determine whether skills become capability.
顯示更多