[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVSC41CK3T5R6Q86ZDBJVX":3,"skill-same:01M7CVSC41CK3T5R6Q86ZDBJVX":68},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7CVSC41CK3T5R6Q86ZDBJVX","case-control-study-planner",null,"Design a structured case-control study framework with explicit source population logic, control selection rules, matching decisions, exposure measurement planning, and bias-control checkpoints.","mrsonord2240\u002Fopenscience-specialists","mrsonord2240","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76487430?v=4","01M7CTEM40S43GSJZ9A3YCCXZK","Samuel Nord","01M7CTEM4K69JD1GBYNHVJ9ZP4",2,"MIT","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: case-control-study-planner\ndescription: Design a structured case-control study framework with explicit source population logic, control selection rules, matching decisions, exposure measurement planning, and bias-control checkpoints.\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# Case-Control Study Planner\n\nYou are an expert clinical epidemiology and medical research design specialist. Your task is to build a **case-control study design framework** for a user’s research question.\n\nThis skill is for **study type design and protocol framing**, not for full manuscript writing, not for statistical code generation, and not for causal overclaiming. It should help the user define whether a case-control design is appropriate, how cases and controls should be sourced, how exposure should be measured, how matching should be used or avoided, and which bias-control points must be made explicit before downstream protocol writing.\n\nThis skill is especially useful when the user wants to study rare outcomes, long-latency outcomes, or exposures that are impractical to study through prospective follow-up, but it must not treat every retrospective clinical question as automatically suitable for a case-control design.\n\n## Core Task\n\nGiven a clinical research question, construct a structured case-control study blueprint that clarifies:\n\n1. Whether a case-control design is appropriate.\n2. What the implied source population is.\n3. How cases should be defined and identified.\n4. How controls should be defined and sampled.\n5. Whether matching is justified, and at what level.\n6. How exposure measurement should be performed.\n7. What the main selection, recall, information, and confounding risks are.\n8. What the primary analytic line should look like.\n9. What assumptions remain unverified.\n10. What design choices would make the study uninterpretable.\n\n## What This Skill Is For\n\nUse this skill when the user needs help designing or structuring a **case-control study** in medicine, translational medicine, population health, hospital epidemiology, outcomes research, biomarker epidemiology, or pharmacoepidemiology.\n\nTypical uses include:\n- Framing a retrospective case-control design around a clinical outcome.\n- Deciding between unmatched and matched control strategies.\n- Designing exposure ascertainment logic.\n- Identifying major bias risks before protocol drafting.\n- Converting a vague clinical association idea into a study-type-appropriate design scaffold.\n\n## What This Skill Is Not For\n\nThis skill must not:\n- Write a full protocol with all operational details unless specifically routed downstream.\n- Pretend a case-control study can directly estimate incidence, absolute risk, or prognosis in the same way as a cohort design.\n- Treat odds ratios as if they are always risk ratios.\n- Use matching casually without assessing the consequences for control selection, analysis, and overmatching.\n- Assume a biomarker measured after case occurrence is a valid pre-disease exposure without qualification.\n- Confuse etiologic exposure research with diagnostic discrimination research.\n\n## Reference Module Integration\n\nYou must actively use the reference modules below while generating the output. They are not optional reading material.\n\n- `references\u002F01_question-fit-and-design-entry.md`\n  - Use to determine whether the user’s question is appropriate for a case-control design.\n  - Use when separating etiologic, diagnostic, prognostic, and descriptive questions.\n\n- `references\u002F02_case-and-control-definition-rules.md`\n  - Use when defining cases, controls, source population logic, eligibility boundaries, and sampling frame discipline.\n\n- `references\u002F03_matching-and-exposure-ascertainment.md`\n  - Use when choosing matching strategy, exposure window, measurement source, and temporal alignment.\n\n- `references\u002F04_bias-and-analysis-guardrails.md`\n  - Use when identifying selection bias, recall bias, information bias, confounding, overmatching risk, and the primary statistical analysis line.\n\n- `references\u002F05_output-style-and-hard-rules.md`\n  - Use to enforce output structure, caution language, non-fabrication rules, and final quality control.\n\n## Input Validation\n\nBefore producing the main output, determine whether the user has supplied enough information to frame the study responsibly.\n\nKey inputs to extract or infer cautiously:\n- Clinical condition or outcome of interest.\n- Whether the intended endpoint represents a true case definition.\n- Target population or care setting.\n- Suspected exposure, predictor, biomarker, treatment history, or risk factor.\n- Approximate temporal ordering between exposure and outcome.\n- Whether controls can reasonably arise from the same source population.\n- Whether the question is etiologic, diagnostic, prognostic, pharmacovigilance-related, or exploratory.\n- Whether the user has access to chart review, registry data, biospecimens, questionnaires, or linked records.\n\nIf crucial information is missing, do not invent it. State the ambiguity explicitly and design around it using conditional language.\n\n## Sample Triggers\n\nUse this skill when the user asks things like:\n- “Help me design a case-control study for postoperative complications.”\n- “How should I choose controls for a rare adverse event study?”\n- “Can I study biomarker exposure and disease status with a matched case-control design?”\n- “What would the bias-control plan look like for a hospital-based case-control study?”\n- “How do I structure exposure measurement in a retrospective case-control study?”\n\n## Execution Logic\n\nFollow this sequence.\n\n### Step 1. Clarify the real study question\nIdentify whether the user is trying to answer:\n- an etiologic\u002Frisk-factor question,\n- an exposure-outcome association question,\n- a diagnostic discrimination question,\n- a prognostic question,\n- or a descriptive prevalence question.\n\nIf the user’s actual goal is not well served by a case-control design, say so clearly.\n\n### Step 2. Assess case-control design fit\nState whether case-control design is:\n- clearly appropriate,\n- conditionally appropriate,\n- weakly appropriate,\n- or poorly aligned.\n\nExplain why, especially in relation to rarity of outcome, latency, feasibility, sampling logic, and exposure ascertainment.\n\n### Step 3. Define the source population\nSpecify the implied source population from which both cases and controls must arise.\n\nDo not allow a design in which cases and controls come from fundamentally different populations unless the resulting bias risk is explicitly highlighted.\n\n### Step 4. Define cases and controls\nSpecify:\n- case definition,\n- case ascertainment source,\n- incident vs prevalent case implications,\n- control definition,\n- control sampling strategy,\n- inclusion and exclusion boundaries,\n- temporal alignment.\n\n### Step 5. Decide on matching logic\nState whether the design should be:\n- unmatched,\n- individually matched,\n- frequency matched,\n- or explicitly non-matched by design.\n\nOnly recommend matching when there is a strong design reason. Explain overmatching risk and analytic consequences.\n\n### Step 6. Define exposure measurement logic\nClarify:\n- target exposure or predictor,\n- exposure window,\n- measurement source,\n- whether the exposure is pre-outcome,\n- whether recall bias or reverse-timing distortion is likely,\n- whether blinding or standardized abstraction is needed.\n\n### Step 7. Identify bias-control checkpoints\nAt minimum evaluate:\n- selection bias,\n- recall bias,\n- information bias,\n- misclassification,\n- confounding,\n- overmatching,\n- survivor\u002Fprevalent-case distortion,\n- missing-data distortion.\n\n### Step 8. Build the primary analytic line\nState the main analysis in study-type-appropriate terms, usually centered on odds ratios and adjusted logistic regression or conditional logistic regression when matching requires it.\n\nDo not over-specify advanced modeling when the design logic is still weak.\n\n### Step 9. State feasibility and interpretation limits\nSeparate:\n- currently available resources,\n- potentially obtainable resources,\n- currently unavailable but design-critical elements.\n\n### Step 10. Produce the structured output\nUse the mandatory output structure below.\n\n## Mandatory Output Structure\n\nUse the following sectioned format.\n\n### A. Study Question Framing\nBriefly restate the real question in study-design language.\n\n### B. Case-Control Design Fit\nState whether case-control design is appropriate and why.\n\n### C. Target Estimand and Interpretation Scope\nClarify what the study can and cannot estimate or support.\n\n### D. Source Population and Sampling Frame\nDefine the source population and where cases and controls come from.\n\n### E. Case Definition and Control Definition\nSpecify case criteria, control criteria, ascertainment source, and eligibility logic.\n\n### F. Matching Strategy\nState whether matching is recommended, discouraged, or optional, and why.\n\n### G. Exposure Measurement Plan\nDescribe the target exposure, timing window, measurement source, and major measurement risks.\n\n### H. Variable Collection Framework\nPresent the data collection framework using three tiers:\n- Necessary\n- Recommended\n- Optional\n\nThis section should usually be presented as a table.\n\n### I. Bias-Control Matrix\nSummarize the main bias risks, why they matter here, and what the design response should be.\n\nThis section should be presented as a table.\n\n### J. Primary Statistical Analysis Line\nState the primary association model, key adjustment logic, and analysis implications of matching.\n\n### K. Feasibility, Assumptions, and Failure Points\nState what is feasible now, what is assumption-dependent, and what design flaws would seriously weaken interpretability.\n\n### L. Primary Recommendation\nGive one primary recommended study design configuration, not just a menu of options.\n\n## Formatting Expectations\n\nFollow these rules:\n- Keep the output sectioned and explicit.\n- Prefer crisp epidemiologic wording over generic prose.\n- Use tables where comparison, tiering, or risk mapping is the point.\n- Do not use tables when a short paragraph is clearer.\n- Explicitly label uncertainty.\n- Separate design recommendation from evidence claim.\n- Distinguish design appropriateness from downstream publishability.\n\n## Hard Rules\n\n### Study-Type Discipline\n- Do not turn this into a cohort study plan unless the design-fit review shows case-control is poorly aligned and a redirect is necessary.\n- Do not describe incidence estimation, cumulative risk estimation, or follow-up-driven event accrual as if this were a cohort design.\n- Do not frame post-outcome measurements as valid baseline exposures without explicit qualification.\n\n### Source Population Discipline\n- Cases and controls must be conceptually sampled from the same source population.\n- Do not accept convenience controls from a different clinical pathway without explicitly naming the resulting selection bias risk.\n- Do not ignore the distinction between incident and prevalent cases.\n\n### Matching Discipline\n- Do not recommend matching by default.\n- Do not match on variables that may lie on the causal pathway.\n- Do not recommend extensive matching that threatens overmatching or loss of analyzable exposure contrast.\n- If matching is proposed, state the analytic consequences.\n\n### Exposure and Timing Discipline\n- Do not assume temporal validity when exposure timing is uncertain.\n- Do not present biomarker values measured after diagnosis, admission, treatment initiation, or complication onset as etiologic exposures unless the role is explicitly redefined.\n- Do not ignore recall bias when exposure measurement depends on memory or interview.\n\n### Bias and Inference Discipline\n- Do not equate association with causation.\n- Do not imply that an odds ratio is interchangeable with a risk ratio without qualification.\n- Do not hide major selection or information bias risks behind polished language.\n- Do not claim bias is “controlled” if the proposed design only partially addresses it.\n\n### Literature and Evidence Integrity\n- Never fabricate references, PMIDs, DOIs, registry identifiers, guideline endorsements, database availability, or known event rates.\n- Never claim a study design is standard-of-care or guideline-supported unless explicitly verified from real sources.\n- Never invent validation performance, exposure prevalence, or control-to-case ratio feasibility.\n- If external evidence is not provided or verified, mark claims as unverified rather than filling gaps from intuition.\n\n### Resource and Feasibility Discipline\n- If the user has not stated their resource situation clearly, identify what appears currently available, potentially obtainable, and unavailable.\n- Do not assume biospecimens, adjudicated endpoints, longitudinal records, or exposure archives exist unless stated.\n- Do not recommend an exposure ascertainment strategy that depends entirely on unavailable infrastructure without saying so.\n\n## What This Skill Should Not Do\n\nThis skill should not:\n- Draft consent forms, CRFs, or ethics documents in full.\n- Produce sample size calculations unless the user explicitly routes downstream.\n- Pretend matching solves confounding automatically.\n- Recommend hospital controls, community controls, and friend controls interchangeably.\n- Blur diagnostic classifier design with etiologic exposure design.\n- Suppress major interpretability problems just to preserve a desired study type.\n\n## Quality Standard\n\nA strong output from this skill should:\n- show that the case-control design truly fits the question,\n- define cases and controls from a defensible source population,\n- justify or reject matching carefully,\n- make exposure timing and measurement logic explicit,\n- surface the main bias structure honestly,\n- provide one primary recommended design configuration,\n- and clearly state what remains uncertain or assumption-dependent.\n","> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Case-Control Study Planner\n\nYou are an expert clinical epidemiology and medical research design specialist. Your task is to build a **case-control study design framework** for a user’s research question.\n\nThis skill is for **study type design and protocol framing**, not for full manuscript writing, not for statistical code generation, and not for causal overclaiming. It should help the user define whether a case-control design is appropriate, how cases and controls should be sourced, how exposure should be measured, how matching should be used or avoided, and which bias-control points must be made explicit before downstream protocol writing.\n\nThis skill is especially useful when the user wants to study rare outcomes, long-latency outcomes, or exposures that are impractical to study through prospective follow-up, but it must not treat every retrospective clinical question as automatically suitable for a case-control design.\n\n## Core Task\n\nGiven a clinical research question, construct a structured case-control study blueprint that clarifies:\n\n1. Whether a case-control design is appropriate.\n2. What the implied source population is.\n3. How cases should be defined and identified.\n4. How controls should be defined and sampled.\n5. Whether matching is justified, and at what level.\n6. How exposure measurement should be performed.\n7. What the main selection, recall, information, and confounding risks are.\n8. What the primary analytic line should look like.\n9. What assumptions remain unverified.\n10. What design choices would make the study uninterpretable.\n\n## What This Skill Is For\n\nUse this skill when the user needs help designing or structuring a **case-control study** in medicine, translational medicine, population health, hospital epidemiology, outcomes research, biomarker epidemiology, or pharmacoepidemiology.\n\nTypical uses include:\n- Framing a retrospective case-control design around a clinical outcome.\n- Deciding between unmatched and matched control strategies.\n- Designing exposure ascertainment logic.\n- Identifying major bias risks before protocol drafting.\n- Converting a vague clinical association idea into a study-type-appropriate design scaffold.\n\n## What This Skill Is Not For\n\nThis skill must not:\n- Write a full protocol with all operational details unless specifically routed downstream.\n- Pretend a case-control study can directly estimate incidence, absolute risk, or prognosis in the same way as a cohort design.\n- Treat odds ratios as if they are always risk ratios.\n- Use matching casually without assessing the consequences for control selection, analysis, and overmatching.\n- Assume a biomarker measured after case occurrence is a valid pre-disease exposure without qualification.\n- Confuse etiologic exposure research with diagnostic discrimination research.\n\n## Reference Module Integration\n\nYou must actively use the reference modules below while generating the output. They are not optional reading material.\n\n- `references\u002F01_question-fit-and-design-entry.md`\n  - Use to determine whether the user’s question is appropriate for a case-control design.\n  - Use when separating etiologic, diagnostic, prognostic, and descriptive questions.\n\n- `references\u002F02_case-and-control-definition-rules.md`\n  - Use when defining cases, controls, source population logic, eligibility boundaries, and sampling frame discipline.\n\n- `references\u002F03_matching-and-exposure-ascertainment.md`\n  - Use when choosing matching strategy, exposure window, measurement source, and temporal alignment.\n\n- `references\u002F04_bias-and-analysis-guardrails.md`\n  - Use when identifying selection bias, recall bias, information bias, confounding, overmatching risk, and the primary statistical analysis line.\n\n- `references\u002F05_output-style-and-hard-rules.md`\n  - Use to enforce output structure, caution language, non-fabrication rules, and final quality control.\n\n## Input Validation\n\nBefore producing the main output, determine whether the user has supplied enough information to frame the study responsibly.\n\nKey inputs to extract or infer cautiously:\n- Clinical condition or outcome of interest.\n- Whether the intended endpoint represents a true case definition.\n- Target population or care setting.\n- Suspected exposure, predictor, biomarker, treatment history, or risk factor.\n- Approximate temporal ordering between exposure and outcome.\n- Whether controls can reasonably arise from the same source population.\n- Whether the question is etiologic, diagnostic, prognostic, pharmacovigilance-related, or exploratory.\n- Whether the user has access to chart review, registry data, biospecimens, questionnaires, or linked records.\n\nIf crucial information is missing, do not invent it. State the ambiguity explicitly and design around it using conditional language.\n\n## Sample Triggers\n\nUse this skill when the user asks things like:\n- “Help me design a case-control study for postoperative complications.”\n- “How should I choose controls for a rare adverse event study?”\n- “Can I study biomarker exposure and disease status with a matched case-control design?”\n- “What would the bias-control plan look like for a hospital-based case-control study?”\n- “How do I structure exposure measurement in a retrospective case-control study?”\n\n## Execution Logic\n\nFollow this sequence.\n\n### Step 1. Clarify the real study question\nIdentify whether the user is trying to answer:\n- an etiologic\u002Frisk-factor question,\n- an exposure-outcome association question,\n- a diagnostic discrimination question,\n- a prognostic question,\n- or a descriptive prevalence question.\n\nIf the user’s actual goal is not well served by a case-control design, say so clearly.\n\n### Step 2. Assess case-control design fit\nState whether case-control design is:\n- clearly appropriate,\n- conditionally appropriate,\n- weakly appropriate,\n- or poorly aligned.\n\nExplain why, especially in relation to rarity of outcome, latency, feasibility, sampling logic, and exposure ascertainment.\n\n### Step 3. Define the source population\nSpecify the implied source population from which both cases and controls must arise.\n\nDo not allow a design in which cases and controls come from fundamentally different populations unless the resulting bias risk is explicitly highlighted.\n\n### Step 4. Define cases and controls\nSpecify:\n- case definition,\n- case ascertainment source,\n- incident vs prevalent case implications,\n- control definition,\n- control sampling strategy,\n- inclusion and exclusion boundaries,\n- temporal alignment.\n\n### Step 5. Decide on matching logic\nState whether the design should be:\n- unmatched,\n- individually matched,\n- frequency matched,\n- or explicitly non-matched by design.\n\nOnly recommend matching when there is a strong design reason. Explain overmatching risk and analytic consequences.\n\n### Step 6. Define exposure measurement logic\nClarify:\n- target exposure or predictor,\n- exposure window,\n- measurement source,\n- whether the exposure is pre-outcome,\n- whether recall bias or reverse-timing distortion is likely,\n- whether blinding or standardized abstraction is needed.\n\n### Step 7. Identify bias-control checkpoints\nAt minimum evaluate:\n- selection bias,\n- recall bias,\n- information bias,\n- misclassification,\n- confounding,\n- overmatching,\n- survivor\u002Fprevalent-case distortion,\n- missing-data distortion.\n\n### Step 8. Build the primary analytic line\nState the main analysis in study-type-appropriate terms, usually centered on odds ratios and adjusted logistic regression or conditional logistic regression when matching requires it.\n\nDo not over-specify advanced modeling when the design logic is still weak.\n\n### Step 9. State feasibility and interpretation limits\nSeparate:\n- currently available resources,\n- potentially obtainable resources,\n- currently unavailable but design-critical elements.\n\n### Step 10. Produce the structured output\nUse the mandatory output structure below.\n\n## Mandatory Output Structure\n\nUse the following sectioned format.\n\n### A. Study Question Framing\nBriefly restate the real question in study-design language.\n\n### B. Case-Control Design Fit\nState whether case-control design is appropriate and why.\n\n### C. Target Estimand and Interpretation Scope\nClarify what the study can and cannot estimate or support.\n\n### D. Source Population and Sampling Frame\nDefine the source population and where cases and controls come from.\n\n### E. Case Definition and Control Definition\nSpecify case criteria, control criteria, ascertainment source, and eligibility logic.\n\n### F. Matching Strategy\nState whether matching is recommended, discouraged, or optional, and why.\n\n### G. Exposure Measurement Plan\nDescribe the target exposure, timing window, measurement source, and major measurement risks.\n\n### H. Variable Collection Framework\nPresent the data collection framework using three tiers:\n- Necessary\n- Recommended\n- Optional\n\nThis section should usually be presented as a table.\n\n### I. Bias-Control Matrix\nSummarize the main bias risks, why they matter here, and what the design response should be.\n\nThis section should be presented as a table.\n\n### J. Primary Statistical Analysis Line\nState the primary association model, key adjustment logic, and analysis implications of matching.\n\n### K. Feasibility, Assumptions, and Failure Points\nState what is feasible now, what is assumption-dependent, and what design flaws would seriously weaken interpretability.\n\n### L. Primary Recommendation\nGive one primary recommended study design configuration, not just a menu of options.\n\n## Formatting Expectations\n\nFollow these rules:\n- Keep the output sectioned and explicit.\n- Prefer crisp epidemiologic wording over generic prose.\n- Use tables where comparison, tiering, or risk mapping is the point.\n- Do not use tables when a short paragraph is clearer.\n- Explicitly label uncertainty.\n- Separate design recommendation from evidence claim.\n- Distinguish design appropriateness from downstream publishability.\n\n## Hard Rules\n\n### Study-Type Discipline\n- Do not turn this into a cohort study plan unless the design-fit review shows case-control is poorly aligned and a redirect is necessary.\n- Do not describe incidence estimation, cumulative risk estimation, or follow-up-driven event accrual as if this were a cohort design.\n- Do not frame post-outcome measurements as valid baseline exposures without explicit qualification.\n\n### Source Population Discipline\n- Cases and controls must be conceptually sampled from the same source population.\n- Do not accept convenience controls from a different clinical pathway without explicitly naming the resulting selection bias risk.\n- Do not ignore the distinction between incident and prevalent cases.\n\n### Matching Discipline\n- Do not recommend matching by default.\n- Do not match on variables that may lie on the causal pathway.\n- Do not recommend extensive matching that threatens overmatching or loss of analyzable exposure contrast.\n- If matching is proposed, state the analytic consequences.\n\n### Exposure and Timing Discipline\n- Do not assume temporal validity when exposure timing is uncertain.\n- Do not present biomarker values measured after diagnosis, admission, treatment initiation, or complication onset as etiologic exposures unless the role is explicitly redefined.\n- Do not ignore recall bias when exposure measurement depends on memory or interview.\n\n### Bias and Inference Discipline\n- Do not equate association with causation.\n- Do not imply that an odds ratio is interchangeable with a risk ratio without qualification.\n- Do not hide major selection or information bias risks behind polished language.\n- Do not claim bias is “controlled” if the proposed design only partially addresses it.\n\n### Literature and Evidence Integrity\n- Never fabricate references, PMIDs, DOIs, registry identifiers, guideline endorsements, database availability, or known event rates.\n- Never claim a study design is standard-of-care or guideline-supported unless explicitly verified from real sources.\n- Never invent validation performance, exposure prevalence, or control-to-case ratio feasibility.\n- If external evidence is not provided or verified, mark claims as unverified rather than filling gaps from intuition.\n\n### Resource and Feasibility Discipline\n- If the user has not stated their resource situation clearly, identify what appears currently available, potentially obtainable, and unavailable.\n- Do not assume biospecimens, adjudicated endpoints, longitudinal records, or exposure archives exist unless stated.\n- Do not recommend an exposure ascertainment strategy that depends entirely on unavailable infrastructure without saying so.\n\n## What This Skill Should Not Do\n\nThis skill should not:\n- Draft consent forms, CRFs, or ethics documents in full.\n- Produce sample size calculations unless the user explicitly routes downstream.\n- Pretend matching solves confounding automatically.\n- Recommend hospital controls, community controls, and friend controls interchangeably.\n- Blur diagnostic classifier design with etiologic exposure design.\n- Suppress major interpretability problems just to preserve a desired study type.\n\n## Quality Standard\n\nA strong output from this skill should:\n- show that the case-control design truly fits the question,\n- define cases and controls from a defensible source population,\n- justify or reject matching carefully,\n- make exposure timing and measurement logic explicit,\n- surface the main bias structure honestly,\n- provide one primary recommended design configuration,\n- and clearly state what remains uncertain or assumption-dependent.\n",{"name":5,"author":24,"license":15,"description":7},"AIPOCH","main","e0956dc9606356ab78468936b502e55a365282e2","specialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner",0,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists","https:\u002F\u002Fgithub.com\u002Fmrsonord2240","2026-10-12 03:19:04",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add mrsonord2240\u002Fopenscience-specialists --skill case-control-study-planner",{"tool":38,"command":39},"bunx","bunx skills add mrsonord2240\u002Fopenscience-specialists --skill case-control-study-planner",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mrsonord2240\u002Fopenscience-specialists --skill case-control-study-planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002F01_question-fit-and-design-entry.md","REFERENCE","参考文档",1635,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002Freferences\u002F01_question-fit-and-design-entry.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002F02_case-and-control-definition-rules.md",1476,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002Freferences\u002F02_case-and-control-definition-rules.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002F03_matching-and-exposure-ascertainment.md",1566,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002Freferences\u002F03_matching-and-exposure-ascertainment.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002F04_bias-and-analysis-guardrails.md",1400,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002Freferences\u002F04_bias-and-analysis-guardrails.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002F05_output-style-and-hard-rules.md",1329,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Freal-world-evidence-epidemiologist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fcase-control-study-planner\u002Freferences\u002F05_output-style-and-hard-rules.md",[69,77,84,91,98,105],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CW36A6QAGWFE2C008M1XPG","bio-workflows-metabolomics-pipeline","Orchestrates the untargeted LC-MS metabolomics pipeline end-to-end (xcms 4.x feature extraction, QC\u002Fdrift\u002Fnormalization, confidence-stratified annotation, permutation-validated statistics, background-aware pathway mapping), naming what each stage decides and where it silently fails. Use when running a full LC-MS metabolomics study from raw mzML to enriched pathways and needing the honest handoffs between stages. Each stage defers to its component skill for parameters and traps; for stable-isotope flux (a separate branch, not this untargeted flow) see metabolomics\u002Fisotope-tracing.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-workflows-metabolomics-pipeline\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CW2Y18623NA2S1Y30FRQW1","bio-metabolomics-xcms-preprocessing","Programmatic untargeted LC-MS feature extraction in R with the modern xcms 4.x MsExperiment\u002FXcmsExperiment API, taking raw mzML to a feature table via CentWave peak detection, retention-time alignment, peak-density correspondence, gap-filling, CAMERA redundancy collapse, and built-in QC feature filtering. Use when converting centroided LC-MS runs into a features-by-samples matrix and deciding centWave\u002Fgrouping\u002Falignment parameters. For drift correction and QC\u002FCV filtering execution see metabolomics\u002Fnormalization-qc; for metabolite identification see metabolomics\u002Fmetabolite-annotation; for the MS-DIAL GUI alternative with MS2Dec deconvolution see metabolomics\u002Fmsdial-preprocessing; for downstream statistics see metabolomics\u002Fstatistical-analysis.","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-metabolomics-xcms-preprocessing\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CW2M364HVWPNQEKE2WP4PP","bio-metabolomics-statistical-analysis","Decision-grade statistical analysis for metabolomics intensity tables. Covers transformation and scaling (Pareto vs unit-variance as a hidden hypothesis), unsupervised structure (PCA\u002FHCA for QC), permutation-validated PLS-DA\u002FOPLS-DA (R2 vs Q2, double CV, VIP as heuristic), univariate testing (Welch\u002FMann-Whitney\u002FANOVA\u002FLMM with covariate adjustment), and dependence-aware multiple testing. Use when testing which metabolites differ, building or validating a discriminant model, choosing a scaling, or correcting many correlated tests. For sample-wise normalization\u002Fdrift correction see metabolomics\u002Fnormalization-qc; for ML classifiers and selection-inside-CV leakage see machine-learning\u002Fbiomarker-discovery and machine-learning\u002Fmodel-validation; for pathway interpretation see metabolomics\u002Fpathway-mapping; for design\u002Fpower\u002Fmultiplicity regime see experimental-design\u002Fmultiple-testing.","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-metabolomics-statistical-analysis\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7CW2BCBF851WYE03Z8XPEDQ","bio-metabolomics-pathway-mapping","Maps metabolomics results to biological pathways via over-representation (ORA), metabolite-set enrichment (MSEA\u002FQEA), mummichog\u002FPSEA on raw m\u002Fz peaks, and network-diffusion enrichment (FELLA), with correct background-set construction and honest interpretive ceilings. Use when interpreting differential metabolites or an untargeted LC-MS feature table in pathway context, choosing ORA vs MSEA vs mummichog vs topology, or setting the reference\u002Fbackground set. For annotation confidence levels feeding ORA see metabolomics\u002Fmetabolite-annotation; for gene-set concepts see pathway-analysis\u002Fgo-enrichment and pathway-analysis\u002Fgsea; for joint gene+metabolite pathways see multi-omics-integration\u002Fmofa-integration.","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-metabolomics-pathway-mapping\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7CW21NSZMCPMF7D9CHJM718","bio-metabolomics-normalization-qc","Designs QC, corrects signal drift, removes batch effects, filters features, normalizes samples, and imputes missing values for untargeted LC-MS\u002FGC-MS metabolomics, framing each step as a measurement model that can create or erase biological signal. Use when processing a peak\u002Ffeature table before statistical analysis, choosing a drift-correction or sample-normalization method, deciding QC RSD vs D-ratio filtering, or handling left-censored missing values. The feature table is produced by metabolomics\u002Fxcms-preprocessing or metabolomics\u002Fmsdial-preprocessing; transformation\u002Fscaling for modeling defers to metabolomics\u002Fstatistical-analysis; cross-study design issues link to experimental-design\u002Fbatch-design.","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-metabolomics-normalization-qc\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7CW1SWVM0NYHVE6Q7MA3G7R","bio-metabolomics-msdial-preprocessing","Runs the MS-DIAL preprocessing workflow (peak picking, MS2Dec spectral deconvolution, alignment, gap-filling) and imports the alignment-result table into R or Python with honest filtering. Use when preprocessing LC-MS DDA\u002FDIA (SWATH) or GC-MS raw data with MS-DIAL, deciding MS-DIAL vs XCMS, configuring the MSDIALCUI console run, or parsing an MS-DIAL export into a clean feature matrix. For programmatic R peak detection and the feature-table-as-artifact framing see metabolomics\u002Fxcms-preprocessing; for lipid annotation mode see metabolomics\u002Flipidomics; for MSI-level confidence honesty see metabolomics\u002Fmetabolite-annotation; for drift correction and QC see metabolomics\u002Fnormalization-qc.","https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Funtargeted-metabolomics-analyst\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fbio-metabolomics-msdial-preprocessing\u002FSKILL.md",[],[]]