[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79011VD489M4SHFN17T7WAP":3,"skill-same:01M79011VD489M4SHFN17T7WAP":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},"01M79011VD489M4SHFN17T7WAP","protocol-design",null,"Routes biomedical research questions into ethically aware, feasibility-conscious study protocols covering aims, design, endpoints, bias, power, validation, and translational planning.","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\u002Fprotocol-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: protocol-design\ndescription: \"Routes biomedical research questions into ethically aware,\n  feasibility-conscious study protocols covering aims, design, endpoints, bias,\n  power, validation, and translational planning.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Protocol Design\n\nUse this route when a researcher needs to turn a biomedical idea into a\nstudy-design plan: aims and hypotheses, design family, eligibility and\nendpoints, bias\u002Fconfounding controls, sample-size logic, validation, or a\ntranslational\u002Fspecialized protocol. This is protocol planning, not patient care,\nstatistical execution, or manuscript prose.\n\n## Route and boundary\n\n1. **Frame the question.** State the population\u002Fmodel, exposure or intervention,\n   comparator, primary outcome, time horizon, intended estimand, and whether the\n   claim is descriptive, associative, predictive, mechanistic, or causal-leaning.\n   Create one coherent primary aim; subordinate secondary and exploratory aims.\n2. **Select the study design.** Choose among experimental, clinical cohort,\n   case-control, diagnostic\u002Fprognostic, RWE, translational, omics, or genetic\n   (including MR) designs based on temporal logic, available data\u002Fspecimens,\n   recruitment, and the claim—not on habit. Define time-zero, eligibility,\n   baseline window, exposure\u002Fintervention, follow-up, censoring, and endpoints.\n3. **Stress validity and feasibility.** Separate baseline from post-baseline\n   variables; identify selection, confounding, immortal-time, measurement,\n   missingness, multiplicity, transportability, and competing-risk threats.\n   Treat effect sizes, event rates, variance, follow-up, data capture, and\n   validation resources as unknown until supported. Obtain ethics, privacy,\n   safety, recruitment, specimen, site, and operational feasibility review.\n4. **Plan power and validation.** Let the primary endpoint\u002Festimand drive\n   formal, range-based, event-driven, precision, or fixed-N feasibility\n   planning. Specify internal versus independent, temporal\u002Fsite\u002Fexternal,\n   technical\u002Forthogonal, functional, and translational validation tiers; never\n   call resampling external validation or infer causal proof from support alone.\n5. **Produce a bounded handoff.** Return assumptions, decisions, alternatives,\n   feasibility blockers, minimum credible protocol, analysis\u002Fvalidation needs,\n   and what remains unverified. Route live evidence retrieval and citation\n   verification to **evidence-insight**, executable modeling\u002Fdata checks to\n   **data-analysis**, and protocol\u002Fmanuscript\u002Fgrant prose to\n   **academic-writing**. Ethics\u002Fprivacy or operational concerns may also need\n   **operations-and-audit**.\n\n## Read the bundled references\n\n- [workflows.md](references\u002Fworkflows.md) for the end-to-end route, design\n  families, outputs, and specialist handoffs.\n- [design-checklists.md](references\u002Fdesign-checklists.md) for aims, eligibility,\n  endpoints, validity, power, validation, translation, ethics, and feasibility\n  gates.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for missing inputs,\n  design mismatch, unsupported assumptions, and recovery actions.\n\n## Safety and evidence limits\n\nDo not provide patient-specific diagnosis or treatment, invent literature,\nregistry\u002Fdatabase capture, event rates, sample sizes, assay feasibility,\nvalidation cohorts, or ethical approval. Mark candidate resources and\nassumptions explicitly. A protocol draft is not an IRB\u002FREC\u002FIACUC submission,\nstatistical analysis execution, or clinical decision. If a critical design\ninput is missing, ask focused questions or proceed only with a clearly labeled\nprovisional design and an explicit stop condition.\n","# Protocol Design\n\nUse this route when a researcher needs to turn a biomedical idea into a\nstudy-design plan: aims and hypotheses, design family, eligibility and\nendpoints, bias\u002Fconfounding controls, sample-size logic, validation, or a\ntranslational\u002Fspecialized protocol. This is protocol planning, not patient care,\nstatistical execution, or manuscript prose.\n\n## Route and boundary\n\n1. **Frame the question.** State the population\u002Fmodel, exposure or intervention,\n   comparator, primary outcome, time horizon, intended estimand, and whether the\n   claim is descriptive, associative, predictive, mechanistic, or causal-leaning.\n   Create one coherent primary aim; subordinate secondary and exploratory aims.\n2. **Select the study design.** Choose among experimental, clinical cohort,\n   case-control, diagnostic\u002Fprognostic, RWE, translational, omics, or genetic\n   (including MR) designs based on temporal logic, available data\u002Fspecimens,\n   recruitment, and the claim—not on habit. Define time-zero, eligibility,\n   baseline window, exposure\u002Fintervention, follow-up, censoring, and endpoints.\n3. **Stress validity and feasibility.** Separate baseline from post-baseline\n   variables; identify selection, confounding, immortal-time, measurement,\n   missingness, multiplicity, transportability, and competing-risk threats.\n   Treat effect sizes, event rates, variance, follow-up, data capture, and\n   validation resources as unknown until supported. Obtain ethics, privacy,\n   safety, recruitment, specimen, site, and operational feasibility review.\n4. **Plan power and validation.** Let the primary endpoint\u002Festimand drive\n   formal, range-based, event-driven, precision, or fixed-N feasibility\n   planning. Specify internal versus independent, temporal\u002Fsite\u002Fexternal,\n   technical\u002Forthogonal, functional, and translational validation tiers; never\n   call resampling external validation or infer causal proof from support alone.\n5. **Produce a bounded handoff.** Return assumptions, decisions, alternatives,\n   feasibility blockers, minimum credible protocol, analysis\u002Fvalidation needs,\n   and what remains unverified. Route live evidence retrieval and citation\n   verification to **evidence-insight**, executable modeling\u002Fdata checks to\n   **data-analysis**, and protocol\u002Fmanuscript\u002Fgrant prose to\n   **academic-writing**. Ethics\u002Fprivacy or operational concerns may also need\n   **operations-and-audit**.\n\n## Read the bundled references\n\n- [workflows.md](references\u002Fworkflows.md) for the end-to-end route, design\n  families, outputs, and specialist handoffs.\n- [design-checklists.md](references\u002Fdesign-checklists.md) for aims, eligibility,\n  endpoints, validity, power, validation, translation, ethics, and feasibility\n  gates.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for missing inputs,\n  design mismatch, unsupported assumptions, and recovery actions.\n\n## Safety and evidence limits\n\nDo not provide patient-specific diagnosis or treatment, invent literature,\nregistry\u002Fdatabase capture, event rates, sample sizes, assay feasibility,\nvalidation cohorts, or ethical approval. Mark candidate resources and\nassumptions explicitly. A protocol draft is not an IRB\u002FREC\u002FIACUC submission,\nstatistical analysis execution, or clinical decision. If a critical design\ninput is missing, ask focused questions or proceed only with a clearly labeled\nprovisional design and an explicit stop condition.\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\u002Fprotocol-design",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 protocol-design",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill protocol-design",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill protocol-design","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\u002Fprotocol-design\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdesign-checklists.md","REFERENCE","参考文档",8081,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Fprotocol-design\u002Freferences\u002Fdesign-checklists.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7371,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Fprotocol-design\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",8526,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmedical-research-skills\u002Fsub-skills\u002Fprotocol-design\u002Freferences\u002Fworkflows.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",[],[]]