[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CARNP4ERE6D2MBXTNV7K9T":3,"skill-same:01M6CARNP4ERE6D2MBXTNV7K9T":94},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6CARNP4ERE6D2MBXTNV7K9T","dogfood",null,"Exploratory QA of web apps: find bugs, evidence, reports.","adnichols\u002Fai-configs","adnichols","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F493746?v=4","01M6C33VRY9WF6XWYPT1AFA7JJ","Aaron Nichols","01M6C33VWTNKGRM92E9G643V4W",5,"MIT","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fprofiles\u002Fwriting\u002Fskills\u002Fsoftware-development\u002Fdogfood\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36],"testing","macos","linux","web","windows","qa","browser","find bugs","hermes","hermes agent","find","evidence","reports","2026-11-10 10:12:30",false,"---\nname: dogfood\ndescription: \"Exploratory QA of web apps: find bugs, evidence, reports.\"\nversion: 1.0.0\nauthor: Teknium (teknium1), Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [qa, testing, browser, web, dogfood]\n    related_skills: []\n---\n\n# Dogfood: Systematic Web Application QA Testing\n\n## Overview\n\nThis skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.\n\n## Prerequisites\n\n- Browser toolset must be available (`browser_navigate`, `browser_snapshot`, `browser_click`, `browser_type`, `browser_vision`, `browser_console`, `browser_scroll`, `browser_back`, `browser_press`)\n- A target URL and testing scope from the user\n\n## Inputs\n\nThe user provides:\n1. **Target URL** — the entry point for testing\n2. **Scope** — what areas\u002Ffeatures to focus on (or \"full site\" for comprehensive testing)\n3. **Output directory** (optional) — where to save screenshots and the report (default: `.\u002Fdogfood-output`)\n\n## Workflow\n\nFollow this 5-phase systematic workflow:\n\n### Phase 1: Plan\n\n1. Create the output directory structure:\n   ```\n   {output_dir}\u002F\n   ├── screenshots\u002F       # Evidence screenshots\n   └── report.md          # Final report (generated in Phase 5)\n   ```\n2. Identify the testing scope based on user input.\n3. Build a rough sitemap by planning which pages and features to test:\n   - Landing\u002Fhome page\n   - Navigation links (header, footer, sidebar)\n   - Key user flows (sign up, login, search, checkout, etc.)\n   - Forms and interactive elements\n   - Edge cases (empty states, error pages, 404s)\n\n### Phase 2: Explore\n\nFor each page or feature in your plan:\n\n1. **Navigate** to the page:\n   ```\n   browser_navigate(url=\"https:\u002F\u002Fexample.com\u002Fpage\")\n   ```\n\n2. **Take a snapshot** to understand the DOM structure:\n   ```\n   browser_snapshot()\n   ```\n\n3. **Check the console** for JavaScript errors:\n   ```\n   browser_console(clear=true)\n   ```\n   Do this after every navigation and after every significant interaction. Silent JS errors are high-value findings.\n\n4. **Take an annotated screenshot** to visually assess the page and identify interactive elements:\n   ```\n   browser_vision(question=\"Describe the page layout, identify any visual issues, broken elements, or accessibility concerns\", annotate=true)\n   ```\n   The `annotate=true` flag overlays numbered `[N]` labels on interactive elements. Each `[N]` maps to ref `@eN` for subsequent browser commands.\n\n5. **Test interactive elements** systematically:\n   - Click buttons and links: `browser_click(ref=\"@eN\")`\n   - Fill forms: `browser_type(ref=\"@eN\", text=\"test input\")`\n   - Test keyboard navigation: `browser_press(key=\"Tab\")`, `browser_press(key=\"Enter\")`\n   - Scroll through content: `browser_scroll(direction=\"down\")`\n   - Test form validation with invalid inputs\n   - Test empty submissions\n\n6. **After each interaction**, check for:\n   - Console errors: `browser_console()`\n   - Visual changes: `browser_vision(question=\"What changed after the interaction?\")`\n   - Expected vs actual behavior\n\n### Phase 3: Collect Evidence\n\nFor every issue found:\n\n1. **Take a screenshot** showing the issue:\n   ```\n   browser_vision(question=\"Capture and describe the issue visible on this page\", annotate=false)\n   ```\n   Save the `screenshot_path` from the response — you will reference it in the report.\n\n2. **Record the details**:\n   - URL where the issue occurs\n   - Steps to reproduce\n   - Expected behavior\n   - Actual behavior\n   - Console errors (if any)\n   - Screenshot path\n\n3. **Classify the issue** using the issue taxonomy (see `references\u002Fissue-taxonomy.md`):\n   - Severity: Critical \u002F High \u002F Medium \u002F Low\n   - Category: Functional \u002F Visual \u002F Accessibility \u002F Console \u002F UX \u002F Content\n\n### Phase 4: Categorize\n\n1. Review all collected issues.\n2. De-duplicate — merge issues that are the same bug manifesting in different places.\n3. Assign final severity and category to each issue.\n4. Sort by severity (Critical first, then High, Medium, Low).\n5. Count issues by severity and category for the executive summary.\n\n### Phase 5: Report\n\nGenerate the final report using the template at `templates\u002Fdogfood-report-template.md`.\n\nThe report must include:\n1. **Executive summary** with total issue count, breakdown by severity, and testing scope\n2. **Per-issue sections** with:\n   - Issue number and title\n   - Severity and category badges\n   - URL where observed\n   - Description of the issue\n   - Steps to reproduce\n   - Expected vs actual behavior\n   - Screenshot references (use `MEDIA:\u003Cscreenshot_path>` for inline images)\n   - Console errors if relevant\n3. **Summary table** of all issues\n4. **Testing notes** — what was tested, what was not, any blockers\n\nSave the report to `{output_dir}\u002Freport.md`.\n\n## Tools Reference\n\n| Tool | Purpose |\n|------|---------|\n| `browser_navigate` | Go to a URL |\n| `browser_snapshot` | Get DOM text snapshot (accessibility tree) |\n| `browser_click` | Click an element by ref (`@eN`) or text |\n| `browser_type` | Type into an input field |\n| `browser_scroll` | Scroll up\u002Fdown on the page |\n| `browser_back` | Go back in browser history |\n| `browser_press` | Press a keyboard key |\n| `browser_vision` | Screenshot + AI analysis; use `annotate=true` for element labels |\n| `browser_console` | Get JS console output and errors |\n\n## Tips\n\n- **Always check `browser_console()` after navigating and after significant interactions.** Silent JS errors are among the most valuable findings.\n- **Use `annotate=true` with `browser_vision`** when you need to reason about interactive element positions or when the snapshot refs are unclear.\n- **Test with both valid and invalid inputs** — form validation bugs are common.\n- **Scroll through long pages** — content below the fold may have rendering issues.\n- **Test navigation flows** — click through multi-step processes end-to-end.\n- **Check responsive behavior** by noting any layout issues visible in screenshots.\n- **Don't forget edge cases**: empty states, very long text, special characters, rapid clicking.\n- When reporting screenshots to the user, include `MEDIA:\u003Cscreenshot_path>` so they can see the evidence inline.\n","# Dogfood: Systematic Web Application QA Testing\n\n## Overview\n\nThis skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.\n\n## Prerequisites\n\n- Browser toolset must be available (`browser_navigate`, `browser_snapshot`, `browser_click`, `browser_type`, `browser_vision`, `browser_console`, `browser_scroll`, `browser_back`, `browser_press`)\n- A target URL and testing scope from the user\n\n## Inputs\n\nThe user provides:\n1. **Target URL** — the entry point for testing\n2. **Scope** — what areas\u002Ffeatures to focus on (or \"full site\" for comprehensive testing)\n3. **Output directory** (optional) — where to save screenshots and the report (default: `.\u002Fdogfood-output`)\n\n## Workflow\n\nFollow this 5-phase systematic workflow:\n\n### Phase 1: Plan\n\n1. Create the output directory structure:\n   ```\n   {output_dir}\u002F\n   ├── screenshots\u002F       # Evidence screenshots\n   └── report.md          # Final report (generated in Phase 5)\n   ```\n2. Identify the testing scope based on user input.\n3. Build a rough sitemap by planning which pages and features to test:\n   - Landing\u002Fhome page\n   - Navigation links (header, footer, sidebar)\n   - Key user flows (sign up, login, search, checkout, etc.)\n   - Forms and interactive elements\n   - Edge cases (empty states, error pages, 404s)\n\n### Phase 2: Explore\n\nFor each page or feature in your plan:\n\n1. **Navigate** to the page:\n   ```\n   browser_navigate(url=\"https:\u002F\u002Fexample.com\u002Fpage\")\n   ```\n\n2. **Take a snapshot** to understand the DOM structure:\n   ```\n   browser_snapshot()\n   ```\n\n3. **Check the console** for JavaScript errors:\n   ```\n   browser_console(clear=true)\n   ```\n   Do this after every navigation and after every significant interaction. Silent JS errors are high-value findings.\n\n4. **Take an annotated screenshot** to visually assess the page and identify interactive elements:\n   ```\n   browser_vision(question=\"Describe the page layout, identify any visual issues, broken elements, or accessibility concerns\", annotate=true)\n   ```\n   The `annotate=true` flag overlays numbered `[N]` labels on interactive elements. Each `[N]` maps to ref `@eN` for subsequent browser commands.\n\n5. **Test interactive elements** systematically:\n   - Click buttons and links: `browser_click(ref=\"@eN\")`\n   - Fill forms: `browser_type(ref=\"@eN\", text=\"test input\")`\n   - Test keyboard navigation: `browser_press(key=\"Tab\")`, `browser_press(key=\"Enter\")`\n   - Scroll through content: `browser_scroll(direction=\"down\")`\n   - Test form validation with invalid inputs\n   - Test empty submissions\n\n6. **After each interaction**, check for:\n   - Console errors: `browser_console()`\n   - Visual changes: `browser_vision(question=\"What changed after the interaction?\")`\n   - Expected vs actual behavior\n\n### Phase 3: Collect Evidence\n\nFor every issue found:\n\n1. **Take a screenshot** showing the issue:\n   ```\n   browser_vision(question=\"Capture and describe the issue visible on this page\", annotate=false)\n   ```\n   Save the `screenshot_path` from the response — you will reference it in the report.\n\n2. **Record the details**:\n   - URL where the issue occurs\n   - Steps to reproduce\n   - Expected behavior\n   - Actual behavior\n   - Console errors (if any)\n   - Screenshot path\n\n3. **Classify the issue** using the issue taxonomy (see `references\u002Fissue-taxonomy.md`):\n   - Severity: Critical \u002F High \u002F Medium \u002F Low\n   - Category: Functional \u002F Visual \u002F Accessibility \u002F Console \u002F UX \u002F Content\n\n### Phase 4: Categorize\n\n1. Review all collected issues.\n2. De-duplicate — merge issues that are the same bug manifesting in different places.\n3. Assign final severity and category to each issue.\n4. Sort by severity (Critical first, then High, Medium, Low).\n5. Count issues by severity and category for the executive summary.\n\n### Phase 5: Report\n\nGenerate the final report using the template at `templates\u002Fdogfood-report-template.md`.\n\nThe report must include:\n1. **Executive summary** with total issue count, breakdown by severity, and testing scope\n2. **Per-issue sections** with:\n   - Issue number and title\n   - Severity and category badges\n   - URL where observed\n   - Description of the issue\n   - Steps to reproduce\n   - Expected vs actual behavior\n   - Screenshot references (use `MEDIA:\u003Cscreenshot_path>` for inline images)\n   - Console errors if relevant\n3. **Summary table** of all issues\n4. **Testing notes** — what was tested, what was not, any blockers\n\nSave the report to `{output_dir}\u002Freport.md`.\n\n## Tools Reference\n\n| Tool | Purpose |\n|------|---------|\n| `browser_navigate` | Go to a URL |\n| `browser_snapshot` | Get DOM text snapshot (accessibility tree) |\n| `browser_click` | Click an element by ref (`@eN`) or text |\n| `browser_type` | Type into an input field |\n| `browser_scroll` | Scroll up\u002Fdown on the page |\n| `browser_back` | Go back in browser history |\n| `browser_press` | Press a keyboard key |\n| `browser_vision` | Screenshot + AI analysis; use `annotate=true` for element labels |\n| `browser_console` | Get JS console output and errors |\n\n## Tips\n\n- **Always check `browser_console()` after navigating and after significant interactions.** Silent JS errors are among the most valuable findings.\n- **Use `annotate=true` with `browser_vision`** when you need to reason about interactive element positions or when the snapshot refs are unclear.\n- **Test with both valid and invalid inputs** — form validation bugs are common.\n- **Scroll through long pages** — content below the fold may have rendering issues.\n- **Test navigation flows** — click through multi-step processes end-to-end.\n- **Check responsive behavior** by noting any layout issues visible in screenshots.\n- **Don't forget edge cases**: empty states, very long text, special characters, rapid clicking.\n- When reporting screenshots to the user, include `MEDIA:\u003Cscreenshot_path>` so they can see the evidence inline.\n",{"name":5,"author":42,"license":15,"version":43,"metadata":44,"platforms":48,"description":7},"Teknium (teknium1), Hermes Agent","1.0.0",{"hermes":45},{"tags":46,"related_skills":47},[29,24,30,27,5],[],[26,25,28],"main","64e2fc9afa7bb3da1138eb73399144d0e7e73e9d","_hermes\u002Fdefault\u002Fprofiles\u002Fwriting\u002Fskills\u002Fsoftware-development\u002Fdogfood",4,"https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs","https:\u002F\u002Fgithub.com\u002Fadnichols","2026-11-06 00:28:38",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add adnichols\u002Fai-configs --skill dogfood",{"tool":62,"command":63},"bunx","bunx skills add adnichols\u002Fai-configs --skill dogfood",{"tool":65,"command":66},"pnpm","pnpm dlx skills add adnichols\u002Fai-configs --skill dogfood","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fprofiles\u002Fwriting\u002Fskills\u002Fsoftware-development\u002Fdogfood\u002FSKILL.md",true,[70,76,80,86,90],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fapi_reference.md","REFERENCE","参考文档",10731,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpubchem-database\u002Freferences\u002Fapi_reference.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fissue-taxonomy.md",3682,"https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fprofiles\u002Fwriting\u002Fskills\u002Fsoftware-development\u002Fdogfood\u002Freferences\u002Fissue-taxonomy.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fbioactivity_query.py","SCRIPT","脚本",9845,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpubchem-database\u002Fscripts\u002Fbioactivity_query.py",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fcompound_search.py",8302,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpubchem-database\u002Fscripts\u002Fcompound_search.py",{"path":91,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":92,"sourceHtmlUrl":93},"templates\u002Fdogfood-report-template.md",1528,"https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fprofiles\u002Fwriting\u002Fskills\u002Fsoftware-development\u002Fdogfood\u002Ftemplates\u002Fdogfood-report-template.md",[95,112,144,166,177,193],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":37},"01M6CB7RN791P5RRRCJWWC7DAR","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[102,103,104,105,106,107,108,33,32,109,110,28,111,26,25],"recovery","page","blocked page recovery","bot","fallback","use","fetch","Citations","waf","research",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":129,"publishedAt":37},"01M6CB7NQY2VVYCQJ1QBXACQF4","writing-plans","Use when creating or updating executable software plans. Keep plans as local files unless the user explicitly asks to register them in Doct.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[118,121,124],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[130,131,132,133,134,135,136,137,138,139,140,141,107,142,33,32,143],"writing","writing plans","documentation","test","workflow","design","user","development","planning","files","implementation","html","ops","plan",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":157,"publishedAt":37},"01M6CB7JME246KZQHP73Z2STDF","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[150,153,154],{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":155,"categoryName":156,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000037","律师与法务",[133,137,158,159,160,33,32,161,143,162,163,164,25,165,26,24,28],"test driven development","red-green-refactor","superpowers","quality","refactor","code","debugging","tdd",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":173,"publishedAt":37},"01M6CB7FQ407KQTD4Z9VAWKY54","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[172],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[164,174,137,160,33,32,175,143,176,28,133,26,25],"systematic debugging","troubleshooting","investigation",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":37},"01M6CB7D57MK88HE5YPZHKH68Q","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[179,28,187,188,111,189,26,25,190,191,192,33,32,143,138],"validate","experiments","prototype","feasibility","sketch","experiment",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":203,"publishedAt":37},"01M6CB7APAQ37YE5YE1MAAFT42","simplify-code","Parallel 3-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[199,200],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":201,"categoryName":202,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000030","开发工程师",[204,205,163,206,33,32,207,143,162,208,209,210,137,28,133,26,211,25],"simplify code","simplify","subagent","parallel","code-review","delegation","cleanup","review"]