https://www.solosoft.dev/tags/open-source-compliance/Recent content in Open Source Compliance on SoloSoftHugoen-usSat, 26 Sep 2026 00:00:00 +0000https://www.solosoft.dev/post/agent-skills-validator-audit/Sat, 26 Sep 2026 00:00:00 +0000https://www.solosoft.dev/post/agent-skills-validator-audit/<p>GitHub Trending on 26 September 2026 is topped by an application: <code>paperclipai/paperclip</code>, 84,938 stars and 2,109 of them gained in a single day, 7,806 tracked files, 120 MB of TypeScript. But the largest single concentration of stars in the agent tooling ecosystem is not an application at all. It is three folders full of Markdown.</p> <p><code>obra/superpowers</code> (291,663 stars), <code>mattpocock/skills</code> (269,725) and <code>anthropics/skills</code> (178,317) hold <strong>739,705 stars between them</strong> for <strong>13.0 MB of tracked content — of which just 3.4 MB is Markdown</strong>. Together they define 73 skills: 348 Markdown files, 65,966 lines, 497,932 words.</p> <p>Those 73 skill definitions are supposed to conform to one format, the Agent Skills specification published at <code>agentskills.io</code>, which ships a reference validator. So I cloned all three repositories, installed the validator from PyPI, and ran it against every skill directory. The result is not what the star counts would lead you to expect:</p>