[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77N9M8CC9BVFQEBQPJ4PK2D":3,"skill-same:01M77N9M8CC9BVFQEBQPJ4PK2D":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77N9M8CC9BVFQEBQPJ4PK2D","model-tester",null,"Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or model works correctly, (2) debugging model fallback chains, (3) testing model selection behavior, (4) validating extraction\u002Freasoning\u002Fclassification across different models, or (5) verifying a model actually got used after routing. Supports --agent, --model, --case parameters with structured JSON output.","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\u002Fm\u002Fmodel-tester\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-tester\nversion: 1.0.0\ndescription: \"Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or model works correctly, (2) debugging model fallback chains, (3) testing model selection behavior, (4) validating extraction\u002Freasoning\u002Fclassification across different models, or (5) verifying a model actually got used after routing. Supports --agent, --model, --case parameters with structured JSON output.\"\n---\n\nUse `scripts\u002Fmodel_tester.py` to run repeatable test prompts and compare requested vs actual model usage from OpenClaw logs.\n\n## Run\n\nFrom the skill directory (or pass absolute paths):\n\n```bash\npython3 scripts\u002Fmodel_tester.py --agent menial --case extract-emails\npython3 scripts\u002Fmodel_tester.py --model openai\u002Fgpt-4.1 --case math-reasoning\npython3 scripts\u002Fmodel_tester.py --agent chat --model openai\u002Fgpt-4.1 --case all --out \u002Ftmp\u002Fmodel-test.json\n```\n\n## Inputs\n\n- `--agent \u003Cname>`: Target agent (chat, menial, coder, etc.)\n- `--model \u003Cname>`: Requested model alias\u002Fname to test\n- `--case \u003Cid|all>`: Case from `references\u002Ftest-cases.json` or `all`\n- `--timeout \u003Csec>`: Per-case timeout (default `120`)\n- `--out \u003Cfile>`: Optional JSON output file\n\nRequire at least one of `--agent` or `--model`.\n\n## What the runner does\n\n1. Load test cases from `references\u002Ftest-cases.json`.\n2. Start `openclaw logs --follow --json` in parallel.\n3. Run `openclaw agent --json` with a bounded test prompt (asks agent to use a subagent for the task).\n4. Parse response + tailed logs.\n5. Emit machine-readable JSON and a short human summary.\n\n## Output format\n\nTop-level JSON:\n\n- `tool`\n- `timestamp`\n- `agent`\n- `requested_model`\n- `results[]`\n\nEach result entry returns:\n\n- `test_case`\n- `agent`\n- `requested_model`\n- `actual_model` (parsed from logs when available)\n- `status` (`ok`\u002F`error`)\n- `result_summary`\n- `runtime_seconds`\n- `tokens` (when discoverable)\n- `errors[]`\n\n## Privacy & Safety\n\nThe tester spawns isolated subagent tasks with **predefined test prompts only** — no user data is passed to models. It tails OpenClaw logs to extract:\n- which model was actually selected (routing validation)\n- token usage statistics\n- runtime metrics\n\nLog extraction uses regex patterns to find model\u002Ftoken fields. No personally identifiable information or arbitrary log content is captured — only structured fields related to the test execution.\n\n## Notes\n\n- Model extraction and token extraction are best-effort because log fields may vary by OpenClaw\u002Fprovider version.\n- If `openclaw` config is invalid or gateway is unavailable, the script returns `status=error` with stderr details.\n- Edit `references\u002Ftest-cases.json` to add custom prompts for your benchmark set.\n- All test cases are generic; no workspace or user data is baked in.\n","Use `scripts\u002Fmodel_tester.py` to run repeatable test prompts and compare requested vs actual model usage from OpenClaw logs.\n\n## Run\n\nFrom the skill directory (or pass absolute paths):\n\n```bash\npython3 scripts\u002Fmodel_tester.py --agent menial --case extract-emails\npython3 scripts\u002Fmodel_tester.py --model openai\u002Fgpt-4.1 --case math-reasoning\npython3 scripts\u002Fmodel_tester.py --agent chat --model openai\u002Fgpt-4.1 --case all --out \u002Ftmp\u002Fmodel-test.json\n```\n\n## Inputs\n\n- `--agent \u003Cname>`: Target agent (chat, menial, coder, etc.)\n- `--model \u003Cname>`: Requested model alias\u002Fname to test\n- `--case \u003Cid|all>`: Case from `references\u002Ftest-cases.json` or `all`\n- `--timeout \u003Csec>`: Per-case timeout (default `120`)\n- `--out \u003Cfile>`: Optional JSON output file\n\nRequire at least one of `--agent` or `--model`.\n\n## What the runner does\n\n1. Load test cases from `references\u002Ftest-cases.json`.\n2. Start `openclaw logs --follow --json` in parallel.\n3. Run `openclaw agent --json` with a bounded test prompt (asks agent to use a subagent for the task).\n4. Parse response + tailed logs.\n5. Emit machine-readable JSON and a short human summary.\n\n## Output format\n\nTop-level JSON:\n\n- `tool`\n- `timestamp`\n- `agent`\n- `requested_model`\n- `results[]`\n\nEach result entry returns:\n\n- `test_case`\n- `agent`\n- `requested_model`\n- `actual_model` (parsed from logs when available)\n- `status` (`ok`\u002F`error`)\n- `result_summary`\n- `runtime_seconds`\n- `tokens` (when discoverable)\n- `errors[]`\n\n## Privacy & Safety\n\nThe tester spawns isolated subagent tasks with **predefined test prompts only** — no user data is passed to models. It tails OpenClaw logs to extract:\n- which model was actually selected (routing validation)\n- token usage statistics\n- runtime metrics\n\nLog extraction uses regex patterns to find model\u002Ftoken fields. No personally identifiable information or arbitrary log content is captured — only structured fields related to the test execution.\n\n## Notes\n\n- Model extraction and token extraction are best-effort because log fields may vary by OpenClaw\u002Fprovider version.\n- If `openclaw` config is invalid or gateway is unavailable, the script returns `status=error` with stderr details.\n- Edit `references\u002Ftest-cases.json` to add custom prompts for your benchmark set.\n- All test cases are generic; no workspace or user data is baked in.\n",{"name":5,"version":24,"description":7},"1.0.0","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fm\u002Fmodel-tester",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill model-tester",{"tool":40,"command":41},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill model-tester",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill model-tester","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmodel-tester\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"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",[],[]]