[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76ZPANDQADHNQESQSK295BJ":3,"skill-same:01M76ZPANDQADHNQESQSK295BJ":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M76ZPANDQADHNQESQSK295BJ","autooptimise",null,"Autonomously optimise any OpenClaw skill using a benchmark-driven experiment loop. Scores skill outputs 0-10 across 4 dimensions, identifies the lowest-scoring pattern, proposes a targeted SKILL.md change, re-tests, and keeps or discards based on measured improvement. Use when asked to: optimise my [skill] skill, run autooptimise on [skill], benchmark my [skill] skill, improve my skill overnight.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fautooptimise\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: autooptimise\ndescription: \"Autonomously optimise any OpenClaw skill using a benchmark-driven experiment loop. Scores skill outputs 0-10 across 4 dimensions, identifies the lowest-scoring pattern, proposes a targeted SKILL.md change, re-tests, and keeps or discards based on measured improvement. Use when asked to: optimise my [skill] skill, run autooptimise on [skill], benchmark my [skill] skill, improve my skill overnight.\"\nhomepage: https:\u002F\u002Fgithub.com\u002FWealthVisionAI-Source\u002Fautooptimise\nmetadata: { \"openclaw\": { \"emoji\": \"🔬\" } }\n---\n\n# autooptimise\n\nAutonomous benchmark-driven skill optimisation for OpenClaw. Inspired by Andrej Karpathy's [autoresearch](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fautoresearch) — the same modify → test → score → keep\u002Fdiscard loop, applied to agent skill quality instead of GPU training.\n\n## Trigger Phrases\n\n- `\"optimise my weather skill\"`\n- `\"run autooptimise on [skill-name]\"`\n- `\"benchmark my [skill-name] skill\"`\n- `\"improve my skill overnight\"`\n\n## Key Files\n\n| File | Purpose |\n|------|---------|\n| `benchmark\u002Ftasks.json` | Test task suite (prompts + expected qualities) |\n| `benchmark\u002Fscorer.md` | LLM judge scoring rubric |\n| `runner\u002Frun_experiment.md` | Autonomous loop instructions (load this next) |\n| `runner\u002Fexperiment_log.md` | Auto-created run log (gitignored) |\n\n## How to Run\n\n1. Read `runner\u002Frun_experiment.md` — it contains the full loop instructions\n2. Confirm the target skill with the user if not specified\n3. Execute the loop (max 3 iterations)\n4. Present proposed changes for human approval — **never auto-apply**\n\n## Scoring\n\nUse the best available LLM judge model (prefer a strong reasoning model). Score each task 0–10 on:\n- **Accuracy** — correct answer \u002F correct tool called\n- **Conciseness** — no padding, no unnecessary text\n- **Tool usage** — right tool, right parameters\n- **Formatting** — output matches expected format\n\nFull rubric: `benchmark\u002Fscorer.md`\n\n## Safety Rules\n\n- **Never auto-apply changes.** Always present a diff and wait for explicit human approval.\n- **Never modify** `benchmark\u002Ftasks.json` or `benchmark\u002Fscorer.md` during a run.\n- **Never exceed 3 iterations** per run in v0.1.\n- Log every action to `runner\u002Fexperiment_log.md`.\n","# autooptimise\n\nAutonomous benchmark-driven skill optimisation for OpenClaw. Inspired by Andrej Karpathy's [autoresearch](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fautoresearch) — the same modify → test → score → keep\u002Fdiscard loop, applied to agent skill quality instead of GPU training.\n\n## Trigger Phrases\n\n- `\"optimise my weather skill\"`\n- `\"run autooptimise on [skill-name]\"`\n- `\"benchmark my [skill-name] skill\"`\n- `\"improve my skill overnight\"`\n\n## Key Files\n\n| File | Purpose |\n|------|---------|\n| `benchmark\u002Ftasks.json` | Test task suite (prompts + expected qualities) |\n| `benchmark\u002Fscorer.md` | LLM judge scoring rubric |\n| `runner\u002Frun_experiment.md` | Autonomous loop instructions (load this next) |\n| `runner\u002Fexperiment_log.md` | Auto-created run log (gitignored) |\n\n## How to Run\n\n1. Read `runner\u002Frun_experiment.md` — it contains the full loop instructions\n2. Confirm the target skill with the user if not specified\n3. Execute the loop (max 3 iterations)\n4. Present proposed changes for human approval — **never auto-apply**\n\n## Scoring\n\nUse the best available LLM judge model (prefer a strong reasoning model). Score each task 0–10 on:\n- **Accuracy** — correct answer \u002F correct tool called\n- **Conciseness** — no padding, no unnecessary text\n- **Tool usage** — right tool, right parameters\n- **Formatting** — output matches expected format\n\nFull rubric: `benchmark\u002Fscorer.md`\n\n## Safety Rules\n\n- **Never auto-apply changes.** Always present a diff and wait for explicit human approval.\n- **Never modify** `benchmark\u002Ftasks.json` or `benchmark\u002Fscorer.md` during a run.\n- **Never exceed 3 iterations** per run in v0.1.\n- Log every action to `runner\u002Fexperiment_log.md`.\n",{"name":5,"homepage":24,"metadata":25,"description":7},"https:\u002F\u002Fgithub.com\u002FWealthVisionAI-Source\u002Fautooptimise",{"openclaw":26},{"emoji":27},"🔬","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Fautooptimise",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill autooptimise",{"tool":43,"command":44},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill autooptimise",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill autooptimise","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fautooptimise\u002FSKILL.md",true,[],[52,60,67,74,81,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":59},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":59},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":59},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":59},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":59},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":59},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]