[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7900YAWM1DCT2EQYB2SD0V2":3,"skill-same:01M7900YAWM1DCT2EQYB2SD0V2":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7900YAWM1DCT2EQYB2SD0V2","operations-and-audit",null,"Route general medical utilities, privacy-sensitive operations, document and laboratory work, quality audits, safe catalog queries, and installation\u002Fexport questions with explicit safety boundaries.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: operations-and-audit\ndescription: \"Route general medical utilities, privacy-sensitive operations,\n  document and laboratory work, quality audits, safe catalog queries, and\n  installation\u002Fexport questions with explicit safety boundaries.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Operations and Audit\n\nUse this route for the operational layer around the medical-research skill\ncatalog: safe selection of general utilities, PHI\u002Fprivacy handling, local\ndocument\u002Ffigure\u002Flab operations, audit interpretation, deterministic\ncalculations, and installation or export planning. Keep this file as a router;\nthe detailed rules live in the bundled references.\n\n## Triage Before Doing Work\n\n1. **Protect data first.** Treat patient, specimen, accession, EHR, lab-report,\n   DICOM, or chart-shaped content as potentially PHI. Do not echo it, read\n   unknown clinical files into context, or execute a query that may return\n   rows. Apply the minimum-necessary and de-identification rules in\n   [audit-and-safety.md](references\u002Faudit-and-safety.md).\n2. **Identify the operation.** Separate a deterministic local utility from a\n   document\u002Ffigure\u002Flab workflow, a quality audit, a catalog lookup, or an\n   installation\u002Fexport request. Confirm inputs, output location, dependencies,\n   overwrite policy, and whether external services are involved.\n3. **Select the smallest catalog skill.** Query the generated catalog index by\n   canonical skill id, collection, category, capability, or input format when\n   a lookup helper is available. Do not invent a skill, capability, package,\n   result, or compliance status. Use the routing table below for specialist\n   work.\n4. **Validate before execution.** Prefer deterministic, local, reversible\n   operations. Use stable output fields, explicit units\u002Fformulas, bounded input\n   ranges, and a validation summary. Stop on missing required inputs or an\n   unsupported dependency rather than silently guessing.\n5. **Apply clinical boundaries.** A calculator, converter, de-identification\n   helper, document tool, or protocol utility is research support—not a\n   diagnosis, prescription, treatment recommendation, legal certification, or\n   release approval. Include an appropriate disclaimer and require qualified\n   human review where the result could affect care, dosing, privacy, or release.\n\n## Route Map\n\n| User need | Route here | Hand off when |\n|---|---|---|\n| General calculator, unit conversion, date\u002Fgestational-age helper, buffer\u002Fdilution or other bounded utility | Use the relevant catalog skill after validating units, ranges, formula, and output contract | A study design decision is needed: [protocol-design](..\u002Fprotocol-design\u002FSKILL.md); statistical\u002Fmodel execution: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| PHI prompt, clinical file\u002Fdatabase access, text de-identification, DICOM metadata, privacy review | Apply the privacy gate and route to the relevant privacy skill; require manual QA | Evidence retrieval: [evidence-insight](..\u002Fevidence-insight\u002FSKILL.md); analysis of de-identified data: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| PDF, Word, spreadsheet, slide, image\u002Ffigure, poster, OCR, figure assembly, lab inventory or preparation operation | Select the narrow local document\u002Ffigure\u002Flab skill and confirm dependencies and file targets | Manuscript prose, claims, citations, or submission adaptation: [academic-writing](..\u002Facademic-writing\u002FSKILL.md); analysis: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| Structural or research-quality audit of a skill | Apply the two veto gates and audit workflow in [audit-and-safety.md](references\u002Faudit-and-safety.md) | Specialist category scoring or scientific-content review may require the owning sibling route and human reviewer |\n| Catalog discovery or task-to-skill selection | Use the root catalog index and its bundled safe query\u002Fcheck helpers, if present; return canonical id, collection, category, fit, requirements, and limits | Detailed execution belongs to the selected catalog skill, not this router |\n| OpenClaw installation, compatible-agent export, or destination collision | Read [installation-and-export.md](references\u002Finstallation-and-export.md); treat installation as an explicit, reference-only operation | Never install implicitly; ask for authorization and target details before side effects |\n\nUse the sibling handoff only after stating what was learned, what remains\nunverified, and which inputs the next route needs. Do not duplicate a sibling's\nspecialist workflow in this route.\n\n## Compact Operating Contract\n\n- **Inputs:** a task description, selected skill or operation, local files only\n  when their privacy status is known, required parameters, and an explicit\n  output target for writes.\n- **Outputs:** a bounded plan or local result with objective, inputs and\n  assumptions, selected path, validation status, risks\u002Flimits, and next checks.\n- **Safe failure:** name the exact missing field, unsupported pair, unavailable\n  dependency, collision, or privacy uncertainty; provide the minimum safe\n  recovery step. Label partial work as `PARTIAL`.\n- **No hidden side effects:** do not download data, call APIs, install packages,\n  overwrite files, expose PHI, or restart gateways without explicit authority\n  and a reviewed target.\n\nFor full rules, consult:\n\n- [audit-and-safety.md](references\u002Faudit-and-safety.md) for veto gates, PHI,\n  deterministic utilities, and clinical disclaimers.\n- [installation-and-export.md](references\u002Finstallation-and-export.md) for the\n  OpenClaw reference contract and safe export planning.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for bounded recovery of\n  install, dependency, input, CLI\u002FAPI, document, figure, and lab failures.\n","# Operations and Audit\n\nUse this route for the operational layer around the medical-research skill\ncatalog: safe selection of general utilities, PHI\u002Fprivacy handling, local\ndocument\u002Ffigure\u002Flab operations, audit interpretation, deterministic\ncalculations, and installation or export planning. Keep this file as a router;\nthe detailed rules live in the bundled references.\n\n## Triage Before Doing Work\n\n1. **Protect data first.** Treat patient, specimen, accession, EHR, lab-report,\n   DICOM, or chart-shaped content as potentially PHI. Do not echo it, read\n   unknown clinical files into context, or execute a query that may return\n   rows. Apply the minimum-necessary and de-identification rules in\n   [audit-and-safety.md](references\u002Faudit-and-safety.md).\n2. **Identify the operation.** Separate a deterministic local utility from a\n   document\u002Ffigure\u002Flab workflow, a quality audit, a catalog lookup, or an\n   installation\u002Fexport request. Confirm inputs, output location, dependencies,\n   overwrite policy, and whether external services are involved.\n3. **Select the smallest catalog skill.** Query the generated catalog index by\n   canonical skill id, collection, category, capability, or input format when\n   a lookup helper is available. Do not invent a skill, capability, package,\n   result, or compliance status. Use the routing table below for specialist\n   work.\n4. **Validate before execution.** Prefer deterministic, local, reversible\n   operations. Use stable output fields, explicit units\u002Fformulas, bounded input\n   ranges, and a validation summary. Stop on missing required inputs or an\n   unsupported dependency rather than silently guessing.\n5. **Apply clinical boundaries.** A calculator, converter, de-identification\n   helper, document tool, or protocol utility is research support—not a\n   diagnosis, prescription, treatment recommendation, legal certification, or\n   release approval. Include an appropriate disclaimer and require qualified\n   human review where the result could affect care, dosing, privacy, or release.\n\n## Route Map\n\n| User need | Route here | Hand off when |\n|---|---|---|\n| General calculator, unit conversion, date\u002Fgestational-age helper, buffer\u002Fdilution or other bounded utility | Use the relevant catalog skill after validating units, ranges, formula, and output contract | A study design decision is needed: [protocol-design](..\u002Fprotocol-design\u002FSKILL.md); statistical\u002Fmodel execution: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| PHI prompt, clinical file\u002Fdatabase access, text de-identification, DICOM metadata, privacy review | Apply the privacy gate and route to the relevant privacy skill; require manual QA | Evidence retrieval: [evidence-insight](..\u002Fevidence-insight\u002FSKILL.md); analysis of de-identified data: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| PDF, Word, spreadsheet, slide, image\u002Ffigure, poster, OCR, figure assembly, lab inventory or preparation operation | Select the narrow local document\u002Ffigure\u002Flab skill and confirm dependencies and file targets | Manuscript prose, claims, citations, or submission adaptation: [academic-writing](..\u002Facademic-writing\u002FSKILL.md); analysis: [data-analysis](..\u002Fdata-analysis\u002FSKILL.md) |\n| Structural or research-quality audit of a skill | Apply the two veto gates and audit workflow in [audit-and-safety.md](references\u002Faudit-and-safety.md) | Specialist category scoring or scientific-content review may require the owning sibling route and human reviewer |\n| Catalog discovery or task-to-skill selection | Use the root catalog index and its bundled safe query\u002Fcheck helpers, if present; return canonical id, collection, category, fit, requirements, and limits | Detailed execution belongs to the selected catalog skill, not this router |\n| OpenClaw installation, compatible-agent export, or destination collision | Read [installation-and-export.md](references\u002Finstallation-and-export.md); treat installation as an explicit, reference-only operation | Never install implicitly; ask for authorization and target details before side effects |\n\nUse the sibling handoff only after stating what was learned, what remains\nunverified, and which inputs the next route needs. Do not duplicate a sibling's\nspecialist workflow in this route.\n\n## Compact Operating Contract\n\n- **Inputs:** a task description, selected skill or operation, local files only\n  when their privacy status is known, required parameters, and an explicit\n  output target for writes.\n- **Outputs:** a bounded plan or local result with objective, inputs and\n  assumptions, selected path, validation status, risks\u002Flimits, and next checks.\n- **Safe failure:** name the exact missing field, unsupported pair, unavailable\n  dependency, collision, or privacy uncertainty; provide the minimum safe\n  recovery step. Label partial work as `PARTIAL`.\n- **No hidden side effects:** do not download data, call APIs, install packages,\n  overwrite files, expose PHI, or restart gateways without explicit authority\n  and a reviewed target.\n\nFor full rules, consult:\n\n- [audit-and-safety.md](references\u002Faudit-and-safety.md) for veto gates, PHI,\n  deterministic utilities, and clinical disclaimers.\n- [installation-and-export.md](references\u002Finstallation-and-export.md) for the\n  OpenClaw reference contract and safe export planning.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for bounded recovery of\n  install, dependency, input, CLI\u002FAPI, document, figure, and lab failures.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill operations-and-audit",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill operations-and-audit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill operations-and-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Faudit-and-safety.md","REFERENCE","参考文档",9871,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit\u002Freferences\u002Faudit-and-safety.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Finstallation-and-export.md",4974,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit\u002Freferences\u002Finstallation-and-export.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6791,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Foperations-and-audit\u002Freferences\u002Ftroubleshooting.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]