[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBAN0EZRYVC6J1BSZ5H04J":3,"skill-same:01M6DBAN0EZRYVC6J1BSZ5H04J":212},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":14,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6DBAN0EZRYVC6J1BSZ5H04J","devtu",null,"ToolUniverse (mims-harvard\u002FToolUniverse) development toolkit - one skill, eight sub-command modes. Use when working on ToolUniverse tools: create a new scientific\u002FAPI tool, fix a failing tool, optimize tool JSON descriptions, optimize research skills, auto-discover life-science APIs and generate integration PRs, run the debug-test loop, or push and fix CI. Each mode's playbook is under modes\u002F.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"science","discover","optimize","auto","use","fix","command","tool","loop","research","api","ci","push","create","toolkit","development","debug","fix ci","test","2026-11-10 10:12:30",false,"---\nname: devtu\ndescription: \"ToolUniverse (mims-harvard\u002FToolUniverse) development toolkit - one skill, eight sub-command modes. Use when working on ToolUniverse tools: create a new scientific\u002FAPI tool, fix a failing tool, optimize tool JSON descriptions, optimize research skills, auto-discover life-science APIs and generate integration PRs, run the debug-test loop, or push and fix CI. Each mode's playbook is under modes\u002F.\"\n---\n\n# DevTU — ToolUniverse Development Toolkit\n\nOne consolidated skill for the entire ToolUniverse (`mims-harvard\u002FToolUniverse`) development\nlifecycle. Read the **mode** from the user's intent and open that mode's playbook under\n`modes\u002F\u003Cmode>\u002FREADME.md` (progressive disclosure — the full former per-skill content, references,\nand templates are preserved there unchanged).\n\n## Sub-command modes\n\n| Mode | Use when | Playbook |\n|------|----------|----------|\n| **self-evolve** | \"run the self-improvement loop\", \"do a debug\u002Ftest round\", evolve ToolUniverse end-to-end (orchestrates the other modes) | [modes\u002Fself-evolve\u002FREADME.md](modes\u002Fself-evolve\u002FREADME.md) |\n| **auto-discover-apis** | expand coverage — gap analysis, web-search for life-science APIs, batch discover + create + validate + PR | [modes\u002Fauto-discover-apis\u002FREADME.md](modes\u002Fauto-discover-apis\u002FREADME.md) |\n| **create-tool** | add a new tool: Python tool class + JSON config + registration + real test examples | [modes\u002Fcreate-tool\u002FREADME.md](modes\u002Fcreate-tool\u002FREADME.md) |\n| **fix-tool** | a tool fails tests \u002F returns errors \u002F has schema-validation issues — diagnose root cause, fix, validate | [modes\u002Ffix-tool\u002FREADME.md](modes\u002Ffix-tool\u002FREADME.md) |\n| **code-optimization** | writing\u002Frefactoring tool Python: reusable code patterns, per-API bug fixes, schema\u002Fpre-commit checklist | [modes\u002Fcode-optimization\u002FREADME.md](modes\u002Fcode-optimization\u002FREADME.md) |\n| **optimize-descriptions** | make tool JSON descriptions clear (prerequisites, abbreviations, required-vs-optional params, usage) | [modes\u002Foptimize-descriptions\u002FREADME.md](modes\u002Foptimize-descriptions\u002FREADME.md) |\n| **optimize-skills** | improve research-skill quality: tool verification, evidence grading (T1-T4), completeness, synthesis | [modes\u002Foptimize-skills\u002FREADME.md](modes\u002Foptimize-skills\u002FREADME.md) |\n| **github** | push code safely, activate pre-commit hooks, clean staged files, fix CI | [modes\u002Fgithub\u002FREADME.md](modes\u002Fgithub\u002FREADME.md) |\n\n## The cycle (self-evolve orchestration)\n\n```\nDiscover → Create → Test → Fix → Optimize → Ship → Repeat\n```\n\n- **Discover** → `auto-discover-apis` — gap analysis + API search + scoring\n- **Create** → `create-tool` — tool class + JSON config + test examples\n- **Test** → `self-evolve` — launch researcher-persona agents to find issues (verify EVERY report via CLI first — 50%+ are false positives)\n- **Fix** → `fix-tool` (code-level patterns in `code-optimization`)\n- **Optimize** → `optimize-descriptions` + `optimize-skills`\n- **Ship** → `github`\n\n## Shared rules (all modes) — CRITICAL\n\n- **Verify before fixing:** `python3 -m tooluniverse.cli run \u003CToolName> '\u003Cjson_args>'` — many agent-reported bugs are MCP-interface false positives.\n- **Tool contract:** `return_schema` MUST have `oneOf` (success + error); `test_examples` MUST use real IDs (no TEST\u002FDUMMY\u002FPLACEHOLDER); tool name at most 55 chars; NEVER raise in `run()` (return an error dict); set a 30s timeout on all HTTP.\n- **Registration (most-missed):** class `@register_tool` + entry in `default_config.py` + wrapper generation on `tu.load_tools()`.\n- **Code hygiene:** always run `Skill(skill=\"simplify\")` after writing or modifying code; `ruff check` before commit.\n- **Git:** never push to `main`; never keep multiple open fix PRs; always `git fetch origin && git rebase origin\u002Fmain` before push; commit messages use \"Feature\"\u002F\"Fix\" (never \"Bug\"); no AI attribution; repo is `mims-harvard\u002FToolUniverse` (confirm with `git remote -v`).\n\n> Consolidation note: this skill supersedes the former eight `devtu-*` micro-skills\n> (`devtu-auto-discover-apis`, `devtu-code-optimization`, `devtu-create-tool`, `devtu-fix-tool`,\n> `devtu-github`, `devtu-optimize-descriptions`, `devtu-optimize-skills`, `devtu-self-evolve`).\n> Their complete bodies, reference files, and templates are preserved verbatim under\n> `modes\u002F\u003Cmode>\u002F`. Any older `Skill(skill=\"devtu-\u003Cmode>\")` invocation is now this skill in that mode.\n","# DevTU — ToolUniverse Development Toolkit\n\nOne consolidated skill for the entire ToolUniverse (`mims-harvard\u002FToolUniverse`) development\nlifecycle. Read the **mode** from the user's intent and open that mode's playbook under\n`modes\u002F\u003Cmode>\u002FREADME.md` (progressive disclosure — the full former per-skill content, references,\nand templates are preserved there unchanged).\n\n## Sub-command modes\n\n| Mode | Use when | Playbook |\n|------|----------|----------|\n| **self-evolve** | \"run the self-improvement loop\", \"do a debug\u002Ftest round\", evolve ToolUniverse end-to-end (orchestrates the other modes) | [modes\u002Fself-evolve\u002FREADME.md](modes\u002Fself-evolve\u002FREADME.md) |\n| **auto-discover-apis** | expand coverage — gap analysis, web-search for life-science APIs, batch discover + create + validate + PR | [modes\u002Fauto-discover-apis\u002FREADME.md](modes\u002Fauto-discover-apis\u002FREADME.md) |\n| **create-tool** | add a new tool: Python tool class + JSON config + registration + real test examples | [modes\u002Fcreate-tool\u002FREADME.md](modes\u002Fcreate-tool\u002FREADME.md) |\n| **fix-tool** | a tool fails tests \u002F returns errors \u002F has schema-validation issues — diagnose root cause, fix, validate | [modes\u002Ffix-tool\u002FREADME.md](modes\u002Ffix-tool\u002FREADME.md) |\n| **code-optimization** | writing\u002Frefactoring tool Python: reusable code patterns, per-API bug fixes, schema\u002Fpre-commit checklist | [modes\u002Fcode-optimization\u002FREADME.md](modes\u002Fcode-optimization\u002FREADME.md) |\n| **optimize-descriptions** | make tool JSON descriptions clear (prerequisites, abbreviations, required-vs-optional params, usage) | [modes\u002Foptimize-descriptions\u002FREADME.md](modes\u002Foptimize-descriptions\u002FREADME.md) |\n| **optimize-skills** | improve research-skill quality: tool verification, evidence grading (T1-T4), completeness, synthesis | [modes\u002Foptimize-skills\u002FREADME.md](modes\u002Foptimize-skills\u002FREADME.md) |\n| **github** | push code safely, activate pre-commit hooks, clean staged files, fix CI | [modes\u002Fgithub\u002FREADME.md](modes\u002Fgithub\u002FREADME.md) |\n\n## The cycle (self-evolve orchestration)\n\n```\nDiscover → Create → Test → Fix → Optimize → Ship → Repeat\n```\n\n- **Discover** → `auto-discover-apis` — gap analysis + API search + scoring\n- **Create** → `create-tool` — tool class + JSON config + test examples\n- **Test** → `self-evolve` — launch researcher-persona agents to find issues (verify EVERY report via CLI first — 50%+ are false positives)\n- **Fix** → `fix-tool` (code-level patterns in `code-optimization`)\n- **Optimize** → `optimize-descriptions` + `optimize-skills`\n- **Ship** → `github`\n\n## Shared rules (all modes) — CRITICAL\n\n- **Verify before fixing:** `python3 -m tooluniverse.cli run \u003CToolName> '\u003Cjson_args>'` — many agent-reported bugs are MCP-interface false positives.\n- **Tool contract:** `return_schema` MUST have `oneOf` (success + error); `test_examples` MUST use real IDs (no TEST\u002FDUMMY\u002FPLACEHOLDER); tool name at most 55 chars; NEVER raise in `run()` (return an error dict); set a 30s timeout on all HTTP.\n- **Registration (most-missed):** class `@register_tool` + entry in `default_config.py` + wrapper generation on `tu.load_tools()`.\n- **Code hygiene:** always run `Skill(skill=\"simplify\")` after writing or modifying code; `ruff check` before commit.\n- **Git:** never push to `main`; never keep multiple open fix PRs; always `git fetch origin && git rebase origin\u002Fmain` before push; commit messages use \"Feature\"\u002F\"Fix\" (never \"Bug\"); no AI attribution; repo is `mims-harvard\u002FToolUniverse` (confirm with `git remote -v`).\n\n> Consolidation note: this skill supersedes the former eight `devtu-*` micro-skills\n> (`devtu-auto-discover-apis`, `devtu-code-optimization`, `devtu-create-tool`, `devtu-fix-tool`,\n> `devtu-github`, `devtu-optimize-descriptions`, `devtu-optimize-skills`, `devtu-self-evolve`).\n> Their complete bodies, reference files, and templates are preserved verbatim under\n> `modes\u002F\u003Cmode>\u002F`. Any older `Skill(skill=\"devtu-\u003Cmode>\")` invocation is now this skill in that mode.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fdevtu","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill devtu",{"tool":60,"command":61},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill devtu",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill devtu","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002FSKILL.md",true,[68,74,78,82,86,90,94,98,102,106,110,114,118,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,196,200,204,208],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"modes\u002Fauto-discover-apis\u002FREADME.md","REFERENCE","参考文档",4499,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fauto-discover-apis\u002FREADME.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"modes\u002Fauto-discover-apis\u002Freferences\u002Ftool-templates.md",4543,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fauto-discover-apis\u002Freferences\u002Ftool-templates.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"modes\u002Fauto-discover-apis\u002Freferences\u002Fvalidation-guide.md",2447,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fauto-discover-apis\u002Freferences\u002Fvalidation-guide.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"modes\u002Fcode-optimization\u002FREADME.md",2753,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcode-optimization\u002FREADME.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"modes\u002Fcode-optimization\u002Freferences\u002Fapi-fixes.md",3898,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcode-optimization\u002Freferences\u002Fapi-fixes.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"modes\u002Fcode-optimization\u002Freferences\u002Fcode-patterns.md",2864,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcode-optimization\u002Freferences\u002Fcode-patterns.md",{"path":95,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":96,"sourceHtmlUrl":97},"modes\u002Fcreate-tool\u002FREADME.md",7718,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002FREADME.md",{"path":99,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":100,"sourceHtmlUrl":101},"modes\u002Fcreate-tool\u002Freferences\u002Fadvanced-patterns.md",30778,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Freferences\u002Fadvanced-patterns.md",{"path":103,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":104,"sourceHtmlUrl":105},"modes\u002Fcreate-tool\u002Freferences\u002Fimplementation-guide.md",11355,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Freferences\u002Fimplementation-guide.md",{"path":107,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":108,"sourceHtmlUrl":109},"modes\u002Fcreate-tool\u002Freferences\u002Fquick-reference.md",11310,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Freferences\u002Fquick-reference.md",{"path":111,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":112,"sourceHtmlUrl":113},"modes\u002Fcreate-tool\u002Freferences\u002Ftesting-guide.md",2900,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Freferences\u002Ftesting-guide.md",{"path":115,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":116,"sourceHtmlUrl":117},"modes\u002Fcreate-tool\u002Freferences\u002Ftool-improvement-checklist.md",21241,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Freferences\u002Ftool-improvement-checklist.md",{"path":119,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":122,"sourceHtmlUrl":123},"modes\u002Fcreate-tool\u002Ftemplates\u002Fapi_tool_template.py","SCRIPT","脚本",4974,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Ftemplates\u002Fapi_tool_template.py",{"path":125,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":126,"sourceHtmlUrl":127},"modes\u002Fcreate-tool\u002Ftemplates\u002Fapi_tools_config.json",5712,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Ftemplates\u002Fapi_tools_config.json",{"path":129,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":130,"sourceHtmlUrl":131},"modes\u002Fcreate-tool\u002Ftemplates\u002Fsimple_tool_template.py",2587,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Ftemplates\u002Fsimple_tool_template.py",{"path":133,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":134,"sourceHtmlUrl":135},"modes\u002Fcreate-tool\u002Ftemplates\u002Fsimple_tools_config.json",1741,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Ftemplates\u002Fsimple_tools_config.json",{"path":137,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":138,"sourceHtmlUrl":139},"modes\u002Fcreate-tool\u002Ftemplates\u002Ftest_template.py",7257,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fcreate-tool\u002Ftemplates\u002Ftest_template.py",{"path":141,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":142,"sourceHtmlUrl":143},"modes\u002Ffix-tool\u002FEXAMPLES.md",11728,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Ffix-tool\u002FEXAMPLES.md",{"path":145,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":146,"sourceHtmlUrl":147},"modes\u002Ffix-tool\u002FQUICK-REFERENCE.md",7486,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Ffix-tool\u002FQUICK-REFERENCE.md",{"path":149,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":150,"sourceHtmlUrl":151},"modes\u002Ffix-tool\u002FREADME.md",14138,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Ffix-tool\u002FREADME.md",{"path":153,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":154,"sourceHtmlUrl":155},"modes\u002Ffix-tool\u002Funit-tests-reference.md",6956,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Ffix-tool\u002Funit-tests-reference.md",{"path":157,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":158,"sourceHtmlUrl":159},"modes\u002Fgithub\u002Finstructions.md",14842,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fgithub\u002Finstructions.md",{"path":161,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":162,"sourceHtmlUrl":163},"modes\u002Fgithub\u002FREADME.md",7002,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fgithub\u002FREADME.md",{"path":165,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":166,"sourceHtmlUrl":167},"modes\u002Fgithub\u002Fskill.json",1097,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fgithub\u002Fskill.json",{"path":169,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":170,"sourceHtmlUrl":171},"modes\u002Foptimize-descriptions\u002FCHECKLIST.md",5273,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-descriptions\u002FCHECKLIST.md",{"path":173,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":174,"sourceHtmlUrl":175},"modes\u002Foptimize-descriptions\u002FEXAMPLES.md",13759,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-descriptions\u002FEXAMPLES.md",{"path":177,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":178,"sourceHtmlUrl":179},"modes\u002Foptimize-descriptions\u002FREADME.md",10995,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-descriptions\u002FREADME.md",{"path":181,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":182,"sourceHtmlUrl":183},"modes\u002Foptimize-skills\u002FREADME.md",10858,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-skills\u002FREADME.md",{"path":185,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":186,"sourceHtmlUrl":187},"modes\u002Foptimize-skills\u002Freferences\u002Fcase-studies.md",1745,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-skills\u002Freferences\u002Fcase-studies.md",{"path":189,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":190,"sourceHtmlUrl":191},"modes\u002Foptimize-skills\u002Freferences\u002Fchecklists.md",2371,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-skills\u002Freferences\u002Fchecklists.md",{"path":193,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":194,"sourceHtmlUrl":195},"modes\u002Foptimize-skills\u002Freferences\u002Foptimization-patterns.md",6403,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-skills\u002Freferences\u002Foptimization-patterns.md",{"path":197,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":198,"sourceHtmlUrl":199},"modes\u002Foptimize-skills\u002Freferences\u002Ftesting-standards.md",2636,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Foptimize-skills\u002Freferences\u002Ftesting-standards.md",{"path":201,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":202,"sourceHtmlUrl":203},"modes\u002Fself-evolve\u002FREADME.md",8359,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fself-evolve\u002FREADME.md",{"path":205,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":206,"sourceHtmlUrl":207},"modes\u002Fself-evolve\u002Freferences\u002Fbug-patterns.md",20897,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fself-evolve\u002Freferences\u002Fbug-patterns.md",{"path":209,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":210,"sourceHtmlUrl":211},"modes\u002Fself-evolve\u002Freferences\u002Fpersona-template.md",3220,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdevtu\u002Fmodes\u002Fself-evolve\u002Freferences\u002Fpersona-template.md",[213,234,264,291,305,320],{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":43},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[220,221,222,223,224,225,226,227,228,28,229,230,231,232,233],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":245,"publishedAt":43},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[240],{"categoryNo":241,"categoryName":242,"taxonomyType":243,"taxonomyTypeDesc":244},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[246,247,248,249,250,251,31,252,253,254,255,256,257,258,28,259,260,261,262,263],"openmm md","how","decision","pick","linux","analyze","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":268,"categories":269,"keywords":276,"publishedAt":43},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[270,273],{"categoryNo":271,"categoryName":272,"taxonomyType":243,"taxonomyTypeDesc":244},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":274,"categoryName":275,"taxonomyType":243,"taxonomyTypeDesc":244},"01JBSEEDCAT000000000000008","测试与质量",[277,278,279,280,281,282,283,284,285,286,247,287,288,289,290],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":292,"name":293,"nameZh":6,"description":294,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":295,"categories":296,"keywords":297,"publishedAt":43},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[293,298,299,300,301,302,303,304],"setup","report","project","installation","project setup","issues","state",{"skillNo":306,"name":307,"nameZh":6,"description":308,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":309,"categories":310,"keywords":312,"publishedAt":43},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[311],{"categoryNo":241,"categoryName":242,"taxonomyType":243,"taxonomyTypeDesc":244},[307,313,225,314,315,316,28,317,318,319,39],"start issue","issue","ready","work on issue","user","work","work on",{"skillNo":321,"name":298,"nameZh":6,"description":322,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":323,"categories":324,"keywords":325,"publishedAt":43},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[298,300,261,326,302,327],"files","interactive"]