{"skill":{"slug":"autooptimise","displayName":"Autooptimise","summary":"Autonomously optimise any OpenClaw skill using a benchmark-driven experiment loop. Scores skill outputs 0-10 across 4 dimensions, identifies the lowest-scori...","tags":{"Agents":"0.1.0","Benchmark Driven skill":"0.1.0","Optimise skills":"0.1.0","latest":"0.1.0"},"stats":{"comments":0,"downloads":102,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774446685092,"updatedAt":1774451811343},"latestVersion":{"version":"0.1.0","createdAt":1774446685092,"changelog":"- Initial release of autooptimise: Autonomous benchmark-driven skill improvement for OpenClaw. Measure quality objectively, propose targeted changes, validate with live testing.\n- Implements a modify → test → score → keep/discard experiment loop inspired by autoresearch.\n- Scores skills 0–10 across four dimensions: Accuracy, Conciseness, Tool usage, and Formatting.\n- Identifies weakest performance areas, proposes targeted SKILL.md changes, and re-tests up to 3 iterations per run.\n- Always presents proposed changes for human approval; never auto-applies modifications.\n- Includes clear safety rules and logging; does not alter benchmarks or scoring rubrics during runs.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"wealthvisionai-source","userId":"s178md4fnchf6hy55w35nska3983kc9j","displayName":"WealthVisionAI-Source","image":"https://avatars.githubusercontent.com/u/241807302?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious","suspicious.vt_suspicious"],"summary":"Detected: suspicious.llm_suspicious, suspicious.vt_suspicious","engineVersion":"v2.2.0","updatedAt":1774451811343}}