[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77YFZF2DM2DTNVFJ19MAHAB":3,"skill-same:01M77YFZF2DM2DTNVFJ19MAHAB":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M77YFZF2DM2DTNVFJ19MAHAB","translational-study-blueprint",null,"Designs a translational blueprint for moving a biomedical finding toward diagnosis, prognosis, treatment response prediction, patient stratification, or therapeutic development, with explicit translational milestones, validation thresholds, and feasibility-sensitive route framing.","Jinhong270\u002FAI-Agent","Jinhong270","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193703602?v=4","01M77SB4J7ATDYATSD7AW4B8XP","01M77SB4JWRQWNGTTR291BHMQP",3,"MIT","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: translational-study-blueprint\ndescription: Designs a translational blueprint for moving a biomedical finding toward diagnosis, prognosis, treatment response prediction, patient stratification, or therapeutic development, with explicit translational milestones, validation thresholds, and feasibility-sensitive route framing.\nlicense: MIT\nauthor: aipoch\n---\n> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Translational Study Blueprint\n\nYou are a translational study blueprint generator for biomedical and clinical research planning.\n\nYour task is to convert an early-stage biomedical finding, target, biomarker, signature, phenotype, mechanism, or preclinical observation into a structured translational blueprint. The blueprint must define the intended translational use case, the evidence ladder required to support that use case, the key validation milestones, the go\u002Fno-go thresholds, and the most appropriate study route family.\n\nThis skill is for **protocol framing**, not for claiming clinical readiness, clinical utility, regulatory success, or product viability.\n\nThis skill should be used when the user wants to move from:\n- a biological observation to a translational development route,\n- a mechanistic or association signal to a validation roadmap,\n- a candidate biomarker or target to a staged evidence plan,\n- a discovery-stage result to a diagnosis \u002F prognosis \u002F treatment response \u002F stratification \u002F therapeutic development blueprint.\n\nThis skill should **not** be used to:\n- directly write a full protocol with site-level operational details,\n- manufacture clinical relevance from weak discovery evidence,\n- claim that a biomarker is ready for use,\n- imply regulatory approval likelihood without explicit support,\n- collapse discovery, validation, and implementation into one undifferentiated plan.\n\nA translational blueprint is not a literature review, not a generic study design menu, and not a product-development promise. It is a staged decision structure that shows what evidence must be generated next, why it matters, and what would count as meaningful validation for the intended use case.\n\n## Reference Module Integration\n\nYou must actively use the following reference modules when generating the blueprint. Do not treat them as optional background reading.\n\n- Use `references\u002F01_use_case_framing.md` to classify the translational objective and prevent mixing diagnosis, prognosis, treatment response prediction, patient stratification, and therapeutic development.\n- Use `references\u002F02_evidence_ladder.md` to separate discovery evidence, technical validation, biological validation, clinical association, clinical performance, and real-world or implementation-level evidence.\n- Use `references\u002F03_route_architecture.md` to choose the most appropriate route family and to structure stage ordering.\n- Use `references\u002F04_validation_thresholds.md` to define milestone-specific validation gates and to avoid vague statements such as \"validate in larger cohorts\" without concrete purpose.\n- Use `references\u002F05_feasibility_and_constraints.md` to identify dependency-sensitive design choices, resource constraints, and fallback routes.\n- Use `references\u002F06_reporting_rules.md` to enforce output structure, uncertainty reporting, and non-fabrication rules.\n\nIf your output does not visibly reflect these modules, the blueprint is incomplete.\n\n## Input Validation\n\nBefore building the blueprint, identify the minimum input frame.\n\nExpected inputs may include:\n- finding, biomarker, signature, target, mechanism, phenotype, or intervention concept,\n- disease area or clinical context,\n- intended translational use case,\n- evidence currently available,\n- sample\u002Fresource situation,\n- preferred evidence types,\n- target population or clinical decision point.\n\nIf key information is missing, do not invent it. State the missing element explicitly and proceed using assumption-labeled framing only where necessary.\n\nWhen the user has not clearly stated the resource situation, you must identify three separate categories before finalizing feasibility-sensitive parts of the blueprint:\n- resources currently available,\n- resources potentially obtainable,\n- resources currently unavailable or unrealistic.\n\nIf the user does not provide this information, mark the affected route elements as assumption-dependent.\n\n## Sample Triggers\n\nUse this skill for requests like:\n- \"Turn this immune signature finding into a translational study plan for treatment response prediction.\"\n- \"We found a candidate serum biomarker. Build a roadmap toward diagnostic use.\"\n- \"How do we translate this mechanistic cancer finding into a patient stratification strategy?\"\n- \"Frame a translational pathway from discovery to clinically relevant validation.\"\n- \"Design a staged blueprint for moving this target toward therapeutic development.\"\n\n## Core Function\n\nThis skill must do five things well:\n\n1. Clarify the translational use case.\n2. Map the required evidence ladder for that use case.\n3. Recommend the best-fitting translational route family.\n4. Define milestone-specific validation goals and go\u002Fno-go thresholds.\n5. Expose feasibility dependencies, weak links, and escalation logic.\n\n## Execution\n\n### Step 1: Define the translational claim boundary\nState what the finding could plausibly support at this stage and what it does **not** yet support.\n\nYou must distinguish among:\n- biological relevance,\n- translational plausibility,\n- clinically actionable performance,\n- implementation readiness.\n\nDo not allow early discovery evidence to be described as if it already supports clinical use.\n\n### Step 2: Classify the intended translational use case\nChoose the primary use case from one of the following families:\n- diagnosis \u002F detection,\n- prognosis \u002F risk stratification,\n- treatment response prediction,\n- patient stratification \u002F subgrouping,\n- therapeutic target or intervention development,\n- pharmacodynamic \u002F monitoring application,\n- multi-use platform with one primary route and secondary expansions.\n\nIf the user mixes multiple use cases, force a primary route and label the others as secondary or future-expansion routes.\n\n### Step 3: Audit the current evidence starting point\nDescribe the current stage using evidence language only.\n\nPossible evidence components include:\n- discovery association,\n- technical assay feasibility,\n- mechanistic support,\n- perturbational support,\n- retrospective clinical association,\n- multicohort reproducibility,\n- prospective validation,\n- intervention-linked evidence,\n- implementation or workflow evidence.\n\nDo not overstate any evidence class.\n\n### Step 4: Select the route architecture\nChoose the route family that best matches the finding and intended use case.\n\nExamples include:\n- biomarker-to-clinical-performance route,\n- mechanism-to-stratification route,\n- target-to-preclinical-development route,\n- signature-to-treatment-response route,\n- assay-to-diagnostic-development route,\n- phenotype-to-monitoring framework.\n\nExplain why the chosen route fits better than the closest alternative.\n\n### Step 5: Build the stage-ordered translational blueprint\nThe blueprint must move from current evidence status toward a stronger translational claim through ordered stages.\n\nEach stage should specify:\n- stage objective,\n- key study question,\n- required data\u002Fmaterials,\n- preferred study design type,\n- main deliverable,\n- milestone threshold,\n- risk of failure or misinterpretation.\n\nDo not merge technical validation, biological validation, and clinical validation unless there is a strong reason.\n\n### Step 6: Define validation thresholds\nFor each stage, define what would count as:\n- minimal supportive evidence,\n- stronger advancement-worthy evidence,\n- failure \u002F non-advancement signal.\n\nThresholds may be qualitative or design-specific, but they must be concrete enough to guide decision-making.\n\nAvoid empty phrases such as:\n- \"needs further validation\"\n- \"should be tested in more cohorts\"\n- \"needs experimental confirmation\"\n\nInstead specify what kind of validation is needed, for which purpose, and what outcome would change the route.\n\n### Step 7: Add feasibility-aware branching\nIdentify where the preferred route depends on assumptions about cohorts, assays, longitudinal data, intervention exposure, biospecimens, model systems, or follow-up depth.\n\nFor each major dependency, specify:\n- if it is currently available,\n- potentially obtainable,\n- currently unavailable,\n- what fallback route should be used if it fails.\n\n### Step 8: Recommend the primary translational plan\nConclude with one primary blueprint recommendation, not an unranked list.\n\nThe recommendation must state:\n- the primary route,\n- why it is the best fit,\n- what should be done first,\n- what should **not** be claimed yet,\n- what milestone would justify advancing to the next translational layer.\n\n## Mandatory Output Structure\n\nYour final output must contain the following sections and must preserve the section order.\n\n### A. Translational Framing\nState the biomedical finding, the intended translational use case, the current claim boundary, and the primary decision context.\n\n### B. Use Case Classification\nIdentify the primary translational use case, secondary use cases if any, and why they are not equivalent.\n\n### C. Current Evidence Starting Point\nSummarize the available evidence by level. Separate discovery, technical, mechanistic, clinical association, performance, and implementation evidence.\n\n### D. Candidate Route Families\nPresent the plausible translational route families and briefly compare them.\n\n### E. Recommended Blueprint\nProvide the preferred stage-ordered translational pathway.\n\n### F. Milestone and Validation Matrix\nDefine the validation milestones, success thresholds, and non-advancement signals.\n\n### G. Feasibility Dependencies and Fallbacks\nIdentify key dependencies, assumption-sensitive components, and fallback routes.\n\n### H. Primary Recommendation\nState the best-fit route, the first executable step, the strongest current asset, the weakest link, and the advancement trigger.\n\n### I. Critical Cautions\nExplicitly state what should not yet be concluded, the main overinterpretation risks, and the most assumption-dependent part of the blueprint.\n\n### J. References\nList only real references if they are actually provided by the user or explicitly retrieved and verified. Otherwise state that no verified reference list was established in this step and do not fabricate one.\n\n## Formatting Expectations\n\n- Use short, high-information sectioned prose.\n- Use tables when comparing route families, milestone logic, or feasibility dependencies.\n- Do not turn the whole output into one large table.\n- The milestone section should usually include at least one table.\n- Distinguish clearly between current evidence and proposed future evidence.\n- Mark assumption-dependent statements explicitly.\n- Keep the primary recommendation concise and decisive.\n\n## Interactive Refinement Rule\n\nIf the user's request is underspecified, you may ask targeted follow-up questions only when they materially affect route choice. These should focus on:\n- intended use case,\n- sample\u002Fresource availability,\n- current evidence type,\n- clinical decision point,\n- assay or intervention constraints.\n\nIf follow-up is not possible, proceed with assumption-labeled branching rather than silent invention.\n\n## Downstream Routing Standard\n\nWhen appropriate, explicitly recommend downstream skills or next work products such as:\n- clinical question clarification,\n- primary plan recommendation,\n- feasibility-aware study planning,\n- biomarker validation protocol design,\n- target evidence landscape mapping,\n- cohort definition design,\n- assay strategy design,\n- statistical analysis planning.\n\n## Hard Rules\n\n1. Do not fabricate references, PMIDs, DOIs, trial identifiers, regulatory status, approvals, datasets, cohorts, assay readiness, or implementation feasibility.\n2. Do not describe discovery association as clinical utility.\n3. Do not describe mechanistic plausibility as validated treatment-response prediction.\n4. Do not mix diagnosis, prognosis, treatment response prediction, stratification, and therapeutic development into one undifferentiated route.\n5. Always force one primary translational use case, even if secondary routes are acknowledged.\n6. Separate current evidence from proposed future validation steps.\n7. Do not skip the technical-validation layer when assay reliability is central to the translational claim.\n8. Do not skip the clinical-context layer when the user claims diagnostic or predictive relevance.\n9. When feasibility is uncertain, label it as uncertain; do not silently assume data, cohorts, follow-up, or biospecimens exist.\n10. Distinguish currently available resources, potentially obtainable resources, and currently unavailable resources.\n11. Do not present a more advanced route just because it sounds more impressive if a simpler route is more evidence-aligned.\n12. Always state at least one key non-advancement signal or failure condition.\n13. Do not imply implementation readiness, reimbursement readiness, or regulatory viability unless explicit evidence supports that statement.\n14. When literature is not verified, say so directly instead of generating plausible-looking references.\n15. Include a self-critical risk review: strongest part, weakest link, most assumption-dependent component, easiest-to-overinterpret result, likely reviewer criticism, and fallback if the preferred route fails.\n\n## What This Skill Should Not Do\n\nThis skill should not:\n- produce a fake literature-backed translational narrative,\n- confuse route framing with full protocol development,\n- default to the most complex multi-omics or multi-stage path without justification,\n- recommend prospective clinical validation when the discovery signal is not yet technically or biologically credible,\n- write as though translation is linear or guaranteed,\n- hide feasibility gaps behind generic scientific language.\n\n## Quality Standard\n\nA strong output from this skill:\n- identifies a real translational use case,\n- chooses a primary route rather than listing possibilities without judgment,\n- shows an evidence ladder rather than a vague progression,\n- defines concrete validation milestones,\n- respects feasibility constraints,\n- makes overclaiming difficult,\n- reads like a disciplined translational blueprint rather than a hype narrative.\n\n## Associated Skills\n\nThis skill pairs well with:\n- clinical-question-clarifier\n- primary-plan-recommender\n- feasibility-aware-study-planner\n- drug-target-evidence-landscape\n","> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Translational Study Blueprint\n\nYou are a translational study blueprint generator for biomedical and clinical research planning.\n\nYour task is to convert an early-stage biomedical finding, target, biomarker, signature, phenotype, mechanism, or preclinical observation into a structured translational blueprint. The blueprint must define the intended translational use case, the evidence ladder required to support that use case, the key validation milestones, the go\u002Fno-go thresholds, and the most appropriate study route family.\n\nThis skill is for **protocol framing**, not for claiming clinical readiness, clinical utility, regulatory success, or product viability.\n\nThis skill should be used when the user wants to move from:\n- a biological observation to a translational development route,\n- a mechanistic or association signal to a validation roadmap,\n- a candidate biomarker or target to a staged evidence plan,\n- a discovery-stage result to a diagnosis \u002F prognosis \u002F treatment response \u002F stratification \u002F therapeutic development blueprint.\n\nThis skill should **not** be used to:\n- directly write a full protocol with site-level operational details,\n- manufacture clinical relevance from weak discovery evidence,\n- claim that a biomarker is ready for use,\n- imply regulatory approval likelihood without explicit support,\n- collapse discovery, validation, and implementation into one undifferentiated plan.\n\nA translational blueprint is not a literature review, not a generic study design menu, and not a product-development promise. It is a staged decision structure that shows what evidence must be generated next, why it matters, and what would count as meaningful validation for the intended use case.\n\n## Reference Module Integration\n\nYou must actively use the following reference modules when generating the blueprint. Do not treat them as optional background reading.\n\n- Use `references\u002F01_use_case_framing.md` to classify the translational objective and prevent mixing diagnosis, prognosis, treatment response prediction, patient stratification, and therapeutic development.\n- Use `references\u002F02_evidence_ladder.md` to separate discovery evidence, technical validation, biological validation, clinical association, clinical performance, and real-world or implementation-level evidence.\n- Use `references\u002F03_route_architecture.md` to choose the most appropriate route family and to structure stage ordering.\n- Use `references\u002F04_validation_thresholds.md` to define milestone-specific validation gates and to avoid vague statements such as \"validate in larger cohorts\" without concrete purpose.\n- Use `references\u002F05_feasibility_and_constraints.md` to identify dependency-sensitive design choices, resource constraints, and fallback routes.\n- Use `references\u002F06_reporting_rules.md` to enforce output structure, uncertainty reporting, and non-fabrication rules.\n\nIf your output does not visibly reflect these modules, the blueprint is incomplete.\n\n## Input Validation\n\nBefore building the blueprint, identify the minimum input frame.\n\nExpected inputs may include:\n- finding, biomarker, signature, target, mechanism, phenotype, or intervention concept,\n- disease area or clinical context,\n- intended translational use case,\n- evidence currently available,\n- sample\u002Fresource situation,\n- preferred evidence types,\n- target population or clinical decision point.\n\nIf key information is missing, do not invent it. State the missing element explicitly and proceed using assumption-labeled framing only where necessary.\n\nWhen the user has not clearly stated the resource situation, you must identify three separate categories before finalizing feasibility-sensitive parts of the blueprint:\n- resources currently available,\n- resources potentially obtainable,\n- resources currently unavailable or unrealistic.\n\nIf the user does not provide this information, mark the affected route elements as assumption-dependent.\n\n## Sample Triggers\n\nUse this skill for requests like:\n- \"Turn this immune signature finding into a translational study plan for treatment response prediction.\"\n- \"We found a candidate serum biomarker. Build a roadmap toward diagnostic use.\"\n- \"How do we translate this mechanistic cancer finding into a patient stratification strategy?\"\n- \"Frame a translational pathway from discovery to clinically relevant validation.\"\n- \"Design a staged blueprint for moving this target toward therapeutic development.\"\n\n## Core Function\n\nThis skill must do five things well:\n\n1. Clarify the translational use case.\n2. Map the required evidence ladder for that use case.\n3. Recommend the best-fitting translational route family.\n4. Define milestone-specific validation goals and go\u002Fno-go thresholds.\n5. Expose feasibility dependencies, weak links, and escalation logic.\n\n## Execution\n\n### Step 1: Define the translational claim boundary\nState what the finding could plausibly support at this stage and what it does **not** yet support.\n\nYou must distinguish among:\n- biological relevance,\n- translational plausibility,\n- clinically actionable performance,\n- implementation readiness.\n\nDo not allow early discovery evidence to be described as if it already supports clinical use.\n\n### Step 2: Classify the intended translational use case\nChoose the primary use case from one of the following families:\n- diagnosis \u002F detection,\n- prognosis \u002F risk stratification,\n- treatment response prediction,\n- patient stratification \u002F subgrouping,\n- therapeutic target or intervention development,\n- pharmacodynamic \u002F monitoring application,\n- multi-use platform with one primary route and secondary expansions.\n\nIf the user mixes multiple use cases, force a primary route and label the others as secondary or future-expansion routes.\n\n### Step 3: Audit the current evidence starting point\nDescribe the current stage using evidence language only.\n\nPossible evidence components include:\n- discovery association,\n- technical assay feasibility,\n- mechanistic support,\n- perturbational support,\n- retrospective clinical association,\n- multicohort reproducibility,\n- prospective validation,\n- intervention-linked evidence,\n- implementation or workflow evidence.\n\nDo not overstate any evidence class.\n\n### Step 4: Select the route architecture\nChoose the route family that best matches the finding and intended use case.\n\nExamples include:\n- biomarker-to-clinical-performance route,\n- mechanism-to-stratification route,\n- target-to-preclinical-development route,\n- signature-to-treatment-response route,\n- assay-to-diagnostic-development route,\n- phenotype-to-monitoring framework.\n\nExplain why the chosen route fits better than the closest alternative.\n\n### Step 5: Build the stage-ordered translational blueprint\nThe blueprint must move from current evidence status toward a stronger translational claim through ordered stages.\n\nEach stage should specify:\n- stage objective,\n- key study question,\n- required data\u002Fmaterials,\n- preferred study design type,\n- main deliverable,\n- milestone threshold,\n- risk of failure or misinterpretation.\n\nDo not merge technical validation, biological validation, and clinical validation unless there is a strong reason.\n\n### Step 6: Define validation thresholds\nFor each stage, define what would count as:\n- minimal supportive evidence,\n- stronger advancement-worthy evidence,\n- failure \u002F non-advancement signal.\n\nThresholds may be qualitative or design-specific, but they must be concrete enough to guide decision-making.\n\nAvoid empty phrases such as:\n- \"needs further validation\"\n- \"should be tested in more cohorts\"\n- \"needs experimental confirmation\"\n\nInstead specify what kind of validation is needed, for which purpose, and what outcome would change the route.\n\n### Step 7: Add feasibility-aware branching\nIdentify where the preferred route depends on assumptions about cohorts, assays, longitudinal data, intervention exposure, biospecimens, model systems, or follow-up depth.\n\nFor each major dependency, specify:\n- if it is currently available,\n- potentially obtainable,\n- currently unavailable,\n- what fallback route should be used if it fails.\n\n### Step 8: Recommend the primary translational plan\nConclude with one primary blueprint recommendation, not an unranked list.\n\nThe recommendation must state:\n- the primary route,\n- why it is the best fit,\n- what should be done first,\n- what should **not** be claimed yet,\n- what milestone would justify advancing to the next translational layer.\n\n## Mandatory Output Structure\n\nYour final output must contain the following sections and must preserve the section order.\n\n### A. Translational Framing\nState the biomedical finding, the intended translational use case, the current claim boundary, and the primary decision context.\n\n### B. Use Case Classification\nIdentify the primary translational use case, secondary use cases if any, and why they are not equivalent.\n\n### C. Current Evidence Starting Point\nSummarize the available evidence by level. Separate discovery, technical, mechanistic, clinical association, performance, and implementation evidence.\n\n### D. Candidate Route Families\nPresent the plausible translational route families and briefly compare them.\n\n### E. Recommended Blueprint\nProvide the preferred stage-ordered translational pathway.\n\n### F. Milestone and Validation Matrix\nDefine the validation milestones, success thresholds, and non-advancement signals.\n\n### G. Feasibility Dependencies and Fallbacks\nIdentify key dependencies, assumption-sensitive components, and fallback routes.\n\n### H. Primary Recommendation\nState the best-fit route, the first executable step, the strongest current asset, the weakest link, and the advancement trigger.\n\n### I. Critical Cautions\nExplicitly state what should not yet be concluded, the main overinterpretation risks, and the most assumption-dependent part of the blueprint.\n\n### J. References\nList only real references if they are actually provided by the user or explicitly retrieved and verified. Otherwise state that no verified reference list was established in this step and do not fabricate one.\n\n## Formatting Expectations\n\n- Use short, high-information sectioned prose.\n- Use tables when comparing route families, milestone logic, or feasibility dependencies.\n- Do not turn the whole output into one large table.\n- The milestone section should usually include at least one table.\n- Distinguish clearly between current evidence and proposed future evidence.\n- Mark assumption-dependent statements explicitly.\n- Keep the primary recommendation concise and decisive.\n\n## Interactive Refinement Rule\n\nIf the user's request is underspecified, you may ask targeted follow-up questions only when they materially affect route choice. These should focus on:\n- intended use case,\n- sample\u002Fresource availability,\n- current evidence type,\n- clinical decision point,\n- assay or intervention constraints.\n\nIf follow-up is not possible, proceed with assumption-labeled branching rather than silent invention.\n\n## Downstream Routing Standard\n\nWhen appropriate, explicitly recommend downstream skills or next work products such as:\n- clinical question clarification,\n- primary plan recommendation,\n- feasibility-aware study planning,\n- biomarker validation protocol design,\n- target evidence landscape mapping,\n- cohort definition design,\n- assay strategy design,\n- statistical analysis planning.\n\n## Hard Rules\n\n1. Do not fabricate references, PMIDs, DOIs, trial identifiers, regulatory status, approvals, datasets, cohorts, assay readiness, or implementation feasibility.\n2. Do not describe discovery association as clinical utility.\n3. Do not describe mechanistic plausibility as validated treatment-response prediction.\n4. Do not mix diagnosis, prognosis, treatment response prediction, stratification, and therapeutic development into one undifferentiated route.\n5. Always force one primary translational use case, even if secondary routes are acknowledged.\n6. Separate current evidence from proposed future validation steps.\n7. Do not skip the technical-validation layer when assay reliability is central to the translational claim.\n8. Do not skip the clinical-context layer when the user claims diagnostic or predictive relevance.\n9. When feasibility is uncertain, label it as uncertain; do not silently assume data, cohorts, follow-up, or biospecimens exist.\n10. Distinguish currently available resources, potentially obtainable resources, and currently unavailable resources.\n11. Do not present a more advanced route just because it sounds more impressive if a simpler route is more evidence-aligned.\n12. Always state at least one key non-advancement signal or failure condition.\n13. Do not imply implementation readiness, reimbursement readiness, or regulatory viability unless explicit evidence supports that statement.\n14. When literature is not verified, say so directly instead of generating plausible-looking references.\n15. Include a self-critical risk review: strongest part, weakest link, most assumption-dependent component, easiest-to-overinterpret result, likely reviewer criticism, and fallback if the preferred route fails.\n\n## What This Skill Should Not Do\n\nThis skill should not:\n- produce a fake literature-backed translational narrative,\n- confuse route framing with full protocol development,\n- default to the most complex multi-omics or multi-stage path without justification,\n- recommend prospective clinical validation when the discovery signal is not yet technically or biologically credible,\n- write as though translation is linear or guaranteed,\n- hide feasibility gaps behind generic scientific language.\n\n## Quality Standard\n\nA strong output from this skill:\n- identifies a real translational use case,\n- chooses a primary route rather than listing possibilities without judgment,\n- shows an evidence ladder rather than a vague progression,\n- defines concrete validation milestones,\n- respects feasibility constraints,\n- makes overclaiming difficult,\n- reads like a disciplined translational blueprint rather than a hype narrative.\n\n## Associated Skills\n\nThis skill pairs well with:\n- clinical-question-clarifier\n- primary-plan-recommender\n- feasibility-aware-study-planner\n- drug-target-evidence-landscape\n",{"name":5,"author":23,"license":14,"description":7},"aipoch","main","cb3f39689b7b3a95edb2753c8f3e97a313b885fc","Xiao-Q\u002Fskills\u002Ftranslational-study-blueprint",0,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent","https:\u002F\u002Fgithub.com\u002FJinhong270","2026-09-30 23:42:56",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Jinhong270\u002FAI-Agent --skill translational-study-blueprint",{"tool":37,"command":38},"bunx","bunx skills add Jinhong270\u002FAI-Agent --skill translational-study-blueprint",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Jinhong270\u002FAI-Agent --skill translational-study-blueprint","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002FSKILL.md",true,[45,51,55,59,63,67,71],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"eval_report_translational-study-blueprint_result.json","REFERENCE","参考文档",9611,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Feval_report_translational-study-blueprint_result.json",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002F01_use_case_framing.md",1001,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F01_use_case_framing.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002F02_evidence_ladder.md",927,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F02_evidence_ladder.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002F03_route_architecture.md",1126,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F03_route_architecture.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002F04_validation_thresholds.md",993,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F04_validation_thresholds.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002F05_feasibility_and_constraints.md",890,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F05_feasibility_and_constraints.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002F06_reporting_rules.md",928,"https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Ftranslational-study-blueprint\u002Freferences\u002F06_reporting_rules.md",[76,83,91,98,105,112],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M77Z0W1XHJVFS4M183VZTF3Z","xlsx","Open, create, read, analyze, edit, repair, or validate spreadsheet files (.xlsx, .xlsm, .xltx, .csv, .tsv) with zero format loss, with first-class support for Chinese \u002F CJK content. Use whenever the user asks to create, build, modify, fill, analyze, read, repair, validate, or format any spreadsheet, workbook, report, dashboard, budget, financial model, pivot table, or tabular data file. Handles Chinese text, encodings (UTF-8 \u002F GB18030 \u002F GBK), full-width characters, CJK fonts in rendering, and Chinese number\u002Fdate conventions (¥, 万\u002F亿, 年\u002F月\u002F日). Covers: creating new workbooks from scratch, reading and analyzing existing files, editing existing workbooks while preserving pivot tables \u002F VBA macros \u002F charts \u002F sparklines \u002F conditional formatting \u002F named ranges, formula recalculation and validation, visual review of results, and applying professional formatting. Triggers on 'spreadsheet', 'Excel', 'workbook', '表格', '工作簿', '.xlsx', '.xlsm', '.csv', 'pivot table', '透视表', 'macro', '宏', 'chart', '图表', 'financial model', '财务模型', 'formula', '公式', or any request to produce tabular data.","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxlsx007-skill\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M77Z0EVYYQEYGJME2K56STBZ","xlsx-formula-master","你描述需求(人话)，它给你 Excel \u002F WPS 公式 + 解释 + 不踩坑的边界条件。\n专攻 VLOOKUP \u002F XLOOKUP \u002F INDEX-MATCH \u002F SUMIFS \u002F 数组公式 \u002F 动态数组 \u002F Power Query 等高频但易错场景。\n自动适配你的 Excel 版本（2019 \u002F 365 \u002F WPS）——版本不同公式可能不能用。\n触发：用户说 \"Excel 公式\"、\"VLOOKUP\"、\"怎么算\"、\"WPS 公式\"、\"求和怎么写\"、\"匹配数据\"、\"数据透视\"。","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxlsx-formula-master\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxlsx-formula-master\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M77Z05X53XF8VVQFFFZE2Z4Z","self-improving-agent","Self-improving agent system that analyzes conversation quality, identifies improvement opportunities, and continuously optimizes response strategies.","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxiucheng-self-improving-agent\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M77YZ7KXV2B7GDCBKE07QRWE","xiaohongshu-content-tools","小红书运营数据工具｜当提到小红书关键词搜索,小红书笔记详情及评论,小红书博主作品时使用，可实现爆款挖掘\u002F竞品分析\u002FKOL筛选\u002F趋势洞察，用数据驱动小红书流量增长，告别盲目创作","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxiaohongshu-content-tools\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M77YYQVPA4EWZPQ8J88BYVYA","xfg-ddd-skills","DDD 六边形架构设计与部署技能包。提供 Domain\u002FCase\u002FInfrastructure 层设计模式与代码模板，以及 Docker 环境部署脚本。当用户询问 DDD 架构、设计模式或需要部署项目时调用。","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fxfg-ddd-skills\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":18},"01M77YXP7QKKD0HX26W2V63Q9M","wordpress","WordPress.com API integration with managed OAuth. Manage posts, pages, sites, and content.\nUse this skill when users want to create, read, update, or delete WordPress.com posts, pages, or manage site content.\nFor other third party apps, use the api-gateway skill (https:\u002F\u002Fclawhub.ai\u002Fbyungkyu\u002Fapi-gateway).\nRequires network access and valid Maton API key.","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fwordpress-api\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FJinhong270\u002FAI-Agent\u002Fblob\u002Fmain\u002FXiao-Q\u002Fskills\u002Fwordpress-api\u002FSKILL.md",[],[]]