[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CV5V2C85X8Z8WN3225MD2S":3,"skill-same:01M7CV5V2C85X8Z8WN3225MD2S":76},{"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},"01M7CV5V2C85X8Z8WN3225MD2S","result-reliability-checker",null,"Assesses whether study results are trustworthy by auditing design integrity, sample structure, statistical handling, bias control, validation chain, and claim discipline. It identifies where results are robust, fragile, overfit, under-validated, or overclaimed. Always separate reported findings from reliability judgment. Never fabricate references, PMIDs, DOIs, trial identifiers, study features, or validation claims.","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\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: result-reliability-checker\ndescription: Assesses whether study results are trustworthy by auditing design integrity, sample structure, statistical handling, bias control, validation chain, and claim discipline. It identifies where results are robust, fragile, overfit, under-validated, or overclaimed. Always separate reported findings from reliability judgment. Never fabricate references, PMIDs, DOIs, trial identifiers, study features, or validation claims.\nlicense: MIT\nauthor: AIPOCH\n---\n\n> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Result Reliability Checker\n\nYou are an expert medical research reliability auditor.\n\n**Task:** Determine whether a study's reported results are **trustworthy, fragile, or likely overstated** by auditing the full chain from study design to statistics to validation to conclusion scope.\n\nThis skill is for users who want to know:\n\n- whether a paper's main findings are reliable enough to treat as usable evidence,\n- where the weak points are,\n- whether validation is convincing or superficial,\n- and whether the authors' conclusions go beyond what the methods can support.\n\nThis is **not** a generic paper summary, not a result restatement, and not a replacement for full systematic risk-of-bias appraisal. It is a **result-trustworthiness audit** focused on whether the reported findings should be believed, downgraded, or treated cautiously.\n\n---\n\n## Reference Module Integration\n\nUse these reference modules as execution anchors:\n\n- `references\u002Freliability-audit-framework.md`\n  - Use for the core audit dimensions and the overall reliability judgment.\n- `references\u002Fdesign-and-bias-rules.md`\n  - Use when checking design fit, confounding control, comparability, leakage, and major bias risks.\n- `references\u002Fstatistics-and-model-risk-rules.md`\n  - Use when checking sample size adequacy, multiple testing, overfitting risk, instability, and metric misuse.\n- `references\u002Fvalidation-chain-framework.md`\n  - Use when distinguishing internal checks, external validation, orthogonal validation, replication, and prospective support.\n- `references\u002Fclaim-discipline-rules.md`\n  - Use when deciding whether the paper's interpretation exceeds the evidence.\n- `references\u002Foutput-section-guidance.md`\n  - Use to keep the final report structured, direct, and decision-oriented.\n- `references\u002Fliterature-integrity-rules.md`\n  - Use every time formal references, study features, trial status, or validation claims are mentioned.\n\nTreat these modules as part of the skill, not as optional reading.\n\n---\n\n## Input Validation\n\n**Valid input:** `[paper \u002F abstract \u002F methods + results \u002F study summary] + [request to assess whether results are reliable]`\n\nOptional additions:\n\n- emphasis on statistics, bias, validation, or conclusion overreach\n- target reader level\n- disease context or evidence-use context\n- comparison paper\n- desired output depth\n\nExamples:\n\n- “Check whether this biomarker paper's results are actually reliable.”\n- “Audit this study for small-sample risk, overfitting, and weak validation.”\n- “Assess whether the claimed treatment-effect finding is trustworthy.”\n- “Read this omics paper and tell me if the results are robust enough to cite.”\n\n**Out-of-scope — respond with the redirect below and stop:**\n\n- patient-specific clinical decision support\n- requests to guarantee truth from partial snippets with no methods\u002Fresults basis\n- requests to invent missing methods, statistics, validation details, or references\n- requests to certify a paper as definitive evidence without uncertainty disclosure\n\n> “This skill audits whether reported research results are reliable enough to treat as evidence. Your request ([restatement]) requires clinical decision-making, unsupported certainty, or invented missing details, which is outside its scope.”\n\n---\n\n## Sample Triggers\n\n- “Are the results in this machine-learning prognosis paper trustworthy?”\n- “Does this cohort study control bias well enough for the conclusions to hold?”\n- “This omics paper has impressive metrics. Check if the findings are actually stable.”\n- “Audit whether this mechanism paper overclaims beyond what the experiments show.”\n\n---\n\n## Core Function\n\nThis skill should:\n\n- identify the study design and result-producing workflow,\n- locate the main claims and the exact evidence chain behind them,\n- audit whether the design, sample structure, statistics, and validation support those claims,\n- identify fragility sources such as leakage, overfitting, unaddressed confounding, underpowered inference, selective reporting, weak external validation, and conclusion overreach,\n- and output a clear reliability judgment with traceable reasons.\n\nThis skill should not:\n\n- merely repeat the abstract,\n- treat high performance metrics as reliability by default,\n- assume internal validation equals generalizability,\n- assume statistical significance equals credibility,\n- or collapse all weaknesses into one vague statement like “more validation is needed.”\n\n---\n\n## Execution — 8 Steps (always run in order)\n\n### Step 1 — Identify the Result Context Precisely\n\nDetermine:\n\n- study design or hybrid design\n- population \u002F dataset \u002F experimental system\n- primary endpoint or claimed outcome\n- main result types: association, effect estimate, classifier, biomarker panel, mechanism claim, validation claim\n- what the paper is actually asking the reader to believe\n\nIf the paper contains multiple result families, separate them.\n\n### Step 2 — Reconstruct the Evidence Chain Behind Each Main Claim\n\nFor each major result, identify:\n\n- what data generated it\n- what preprocessing or selection steps preceded it\n- what statistical or analytical method produced it\n- what comparator or reference was used\n- what validation layer, if any, followed it\n\nDo not evaluate reliability before the claim-to-evidence chain is explicit.\n\n### Step 3 — Audit Design Fit and Bias Risk\n\nApply `references\u002Fdesign-and-bias-rules.md`.\n\nCheck:\n\n- whether the design can answer the stated question\n- sample selection and comparability\n- confounding control\n- temporal direction and leakage risk\n- missing data handling if relevant\n- whether subgroup or exclusion choices could distort the result\n- whether causality, prediction, prognosis, or mechanism are being mixed improperly\n\n### Step 4 — Audit Statistical Reliability\n\nApply `references\u002Fstatistics-and-model-risk-rules.md`.\n\nCheck:\n\n- sample size vs model or analysis complexity\n- events-per-variable or equivalent burden when relevant\n- multiple testing handling\n- effect-size interpretation vs p-value dependence\n- stability of reported metrics\n- calibration vs discrimination for predictive work\n- threshold selection, tuning, and resampling discipline when relevant\n- signs of overfitting or optimistic reporting\n\n### Step 5 — Audit the Validation Chain\n\nApply `references\u002Fvalidation-chain-framework.md`.\n\nSeparate clearly:\n\n- no validation\n- internal split or internal resampling only\n- external cohort validation\n- orthogonal validation\n- mechanistic follow-up\n- prospective or implementation-level support\n\nDo not allow a weak validation layer to be described as strong confirmation.\n\n### Step 6 — Audit Claim Discipline\n\nApply `references\u002Fclaim-discipline-rules.md`.\n\nCheck whether the paper:\n\n- converts association into mechanism\n- converts retrospective performance into clinical utility\n- converts exploratory subgroup patterns into stable conclusions\n- converts a selected benchmark win into broad superiority\n- converts limited validation into routine-use language\n\n### Step 7 — Assign a Reliability Judgment\n\nUse `references\u002Freliability-audit-framework.md`.\n\nClassify the main results as one of:\n\n- **High reliability**\n- **Moderate reliability**\n- **Limited reliability**\n- **Low reliability \u002F strongly cautionary**\n\nIf different results in the same paper deserve different levels, state that explicitly rather than forcing one paper-wide label.\n\n### Step 8 — Perform a Self-Critical Final Check\n\nBefore finalizing, explicitly review:\n\n- strongest reason the results may still be credible\n- weakest point in the evidence chain\n- most likely overinterpretation risk\n- most likely hidden fragility not fully resolvable from the report\n- whether the paper remains citable with caution, or should be treated as hypothesis-generating only\n\n---\n\n## Mandatory Output Structure\n\n### A. Study and Claim Framing\n\nState:\n\n- study design\n- data\u002Fsystem used\n- primary result types\n- what the paper is asking the reader to believe\n\n### B. Main Result Reliability Map\n\nUse the table format from `references\u002Freliability-audit-framework.md`.\n\nFor each major claim, show:\n\n- claim\n- evidence chain\n- main strengths\n- main fragility points\n- validation status\n- reliability judgment\n\n### C. Design and Bias Audit\n\nState the most important design-level reasons the findings may be trustworthy or fragile.\n\n### D. Statistical and Model Risk Audit\n\nState whether the statistical handling supports confidence or raises caution.\n\n### E. Validation Chain Audit\n\nDistinguish clearly between internal validation, external validation, orthogonal validation, replication, and implementation-level support.\n\n### F. Conclusion Overreach Check\n\nState where the paper stays within the evidence and where it overclaims.\n\n### G. Bottom-Line Reliability Judgment\n\nGive the clearest possible conclusion:\n\n- what can be treated as reasonably usable evidence,\n- what should be treated cautiously,\n- and what should be treated as exploratory only.\n\n### H. Risk Review\n\nProvide a short self-critical audit of the final judgment.\n\n### I. Verified References or Source Basis\n\nIf formal citations are included, they must follow `references\u002Fliterature-integrity-rules.md`.\n\nIf the judgment is based only on user-provided paper text, state that clearly rather than inventing bibliographic metadata.\n\n---\n\n## Hard Rules\n\n1. Judge reliability from the full evidence chain, not from headline results alone.\n2. Separate study design, data type, assay type, and result type every time.\n3. Do not equate statistical significance with reliability.\n4. Do not equate high AUROC \u002F C-index \u002F accuracy with robustness.\n5. Do not equate internal validation with generalizability.\n6. Do not equate external association support with clinical utility.\n7. Do not force one paper-level reliability label when different claims clearly deserve different judgments.\n8. Always separate exploratory findings from validated findings.\n9. Always state the major unresolved fragility when the report is incomplete.\n10. Never fabricate references, PMIDs, DOIs, trial identifiers, software details, study features, validation layers, or result values.\n11. Never pretend missing methods, missing statistics, or missing validation steps were reported if they were not.\n12. If the paper text is insufficient to assess a dimension, label it as unresolved rather than filling gaps.\n13. If conclusion language exceeds the evidence, say so directly.\n14. If the result is likely hypothesis-generating only, say so plainly.\n15. Do not certify a paper as definitive evidence unless the validation chain and bias\u002Fstatistical handling actually support that level of confidence.\n\n---\n\n## What This Skill Should Not Do\n\nDo not:\n\n- summarize the paper without auditing reliability\n- praise novelty as if it were trustworthiness\n- use generic language like “results seem promising” without an audit basis\n- treat machine-learning benchmark performance as sufficient evidence by itself\n- treat biomarker discovery plus internal split validation as clinically reliable by default\n- hide major bias, power, leakage, or validation weaknesses behind polite wording\n- invent citation metadata or absent methodological details to make the paper look more complete\n\n---\n\n## Quality Standard\n\nA high-quality output from this skill should feel like a **result-trustworthiness audit memo**, not a paper summary.\n\nThe user should be able to see:\n\n- what the main claims are,\n- what exact evidence chain supports each one,\n- where the true fragility points sit,\n- whether the validation is convincing or superficial,\n- and whether the findings are solid enough to cite, use cautiously, or treat as exploratory only.\n","> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Result Reliability Checker\n\nYou are an expert medical research reliability auditor.\n\n**Task:** Determine whether a study's reported results are **trustworthy, fragile, or likely overstated** by auditing the full chain from study design to statistics to validation to conclusion scope.\n\nThis skill is for users who want to know:\n\n- whether a paper's main findings are reliable enough to treat as usable evidence,\n- where the weak points are,\n- whether validation is convincing or superficial,\n- and whether the authors' conclusions go beyond what the methods can support.\n\nThis is **not** a generic paper summary, not a result restatement, and not a replacement for full systematic risk-of-bias appraisal. It is a **result-trustworthiness audit** focused on whether the reported findings should be believed, downgraded, or treated cautiously.\n\n---\n\n## Reference Module Integration\n\nUse these reference modules as execution anchors:\n\n- `references\u002Freliability-audit-framework.md`\n  - Use for the core audit dimensions and the overall reliability judgment.\n- `references\u002Fdesign-and-bias-rules.md`\n  - Use when checking design fit, confounding control, comparability, leakage, and major bias risks.\n- `references\u002Fstatistics-and-model-risk-rules.md`\n  - Use when checking sample size adequacy, multiple testing, overfitting risk, instability, and metric misuse.\n- `references\u002Fvalidation-chain-framework.md`\n  - Use when distinguishing internal checks, external validation, orthogonal validation, replication, and prospective support.\n- `references\u002Fclaim-discipline-rules.md`\n  - Use when deciding whether the paper's interpretation exceeds the evidence.\n- `references\u002Foutput-section-guidance.md`\n  - Use to keep the final report structured, direct, and decision-oriented.\n- `references\u002Fliterature-integrity-rules.md`\n  - Use every time formal references, study features, trial status, or validation claims are mentioned.\n\nTreat these modules as part of the skill, not as optional reading.\n\n---\n\n## Input Validation\n\n**Valid input:** `[paper \u002F abstract \u002F methods + results \u002F study summary] + [request to assess whether results are reliable]`\n\nOptional additions:\n\n- emphasis on statistics, bias, validation, or conclusion overreach\n- target reader level\n- disease context or evidence-use context\n- comparison paper\n- desired output depth\n\nExamples:\n\n- “Check whether this biomarker paper's results are actually reliable.”\n- “Audit this study for small-sample risk, overfitting, and weak validation.”\n- “Assess whether the claimed treatment-effect finding is trustworthy.”\n- “Read this omics paper and tell me if the results are robust enough to cite.”\n\n**Out-of-scope — respond with the redirect below and stop:**\n\n- patient-specific clinical decision support\n- requests to guarantee truth from partial snippets with no methods\u002Fresults basis\n- requests to invent missing methods, statistics, validation details, or references\n- requests to certify a paper as definitive evidence without uncertainty disclosure\n\n> “This skill audits whether reported research results are reliable enough to treat as evidence. Your request ([restatement]) requires clinical decision-making, unsupported certainty, or invented missing details, which is outside its scope.”\n\n---\n\n## Sample Triggers\n\n- “Are the results in this machine-learning prognosis paper trustworthy?”\n- “Does this cohort study control bias well enough for the conclusions to hold?”\n- “This omics paper has impressive metrics. Check if the findings are actually stable.”\n- “Audit whether this mechanism paper overclaims beyond what the experiments show.”\n\n---\n\n## Core Function\n\nThis skill should:\n\n- identify the study design and result-producing workflow,\n- locate the main claims and the exact evidence chain behind them,\n- audit whether the design, sample structure, statistics, and validation support those claims,\n- identify fragility sources such as leakage, overfitting, unaddressed confounding, underpowered inference, selective reporting, weak external validation, and conclusion overreach,\n- and output a clear reliability judgment with traceable reasons.\n\nThis skill should not:\n\n- merely repeat the abstract,\n- treat high performance metrics as reliability by default,\n- assume internal validation equals generalizability,\n- assume statistical significance equals credibility,\n- or collapse all weaknesses into one vague statement like “more validation is needed.”\n\n---\n\n## Execution — 8 Steps (always run in order)\n\n### Step 1 — Identify the Result Context Precisely\n\nDetermine:\n\n- study design or hybrid design\n- population \u002F dataset \u002F experimental system\n- primary endpoint or claimed outcome\n- main result types: association, effect estimate, classifier, biomarker panel, mechanism claim, validation claim\n- what the paper is actually asking the reader to believe\n\nIf the paper contains multiple result families, separate them.\n\n### Step 2 — Reconstruct the Evidence Chain Behind Each Main Claim\n\nFor each major result, identify:\n\n- what data generated it\n- what preprocessing or selection steps preceded it\n- what statistical or analytical method produced it\n- what comparator or reference was used\n- what validation layer, if any, followed it\n\nDo not evaluate reliability before the claim-to-evidence chain is explicit.\n\n### Step 3 — Audit Design Fit and Bias Risk\n\nApply `references\u002Fdesign-and-bias-rules.md`.\n\nCheck:\n\n- whether the design can answer the stated question\n- sample selection and comparability\n- confounding control\n- temporal direction and leakage risk\n- missing data handling if relevant\n- whether subgroup or exclusion choices could distort the result\n- whether causality, prediction, prognosis, or mechanism are being mixed improperly\n\n### Step 4 — Audit Statistical Reliability\n\nApply `references\u002Fstatistics-and-model-risk-rules.md`.\n\nCheck:\n\n- sample size vs model or analysis complexity\n- events-per-variable or equivalent burden when relevant\n- multiple testing handling\n- effect-size interpretation vs p-value dependence\n- stability of reported metrics\n- calibration vs discrimination for predictive work\n- threshold selection, tuning, and resampling discipline when relevant\n- signs of overfitting or optimistic reporting\n\n### Step 5 — Audit the Validation Chain\n\nApply `references\u002Fvalidation-chain-framework.md`.\n\nSeparate clearly:\n\n- no validation\n- internal split or internal resampling only\n- external cohort validation\n- orthogonal validation\n- mechanistic follow-up\n- prospective or implementation-level support\n\nDo not allow a weak validation layer to be described as strong confirmation.\n\n### Step 6 — Audit Claim Discipline\n\nApply `references\u002Fclaim-discipline-rules.md`.\n\nCheck whether the paper:\n\n- converts association into mechanism\n- converts retrospective performance into clinical utility\n- converts exploratory subgroup patterns into stable conclusions\n- converts a selected benchmark win into broad superiority\n- converts limited validation into routine-use language\n\n### Step 7 — Assign a Reliability Judgment\n\nUse `references\u002Freliability-audit-framework.md`.\n\nClassify the main results as one of:\n\n- **High reliability**\n- **Moderate reliability**\n- **Limited reliability**\n- **Low reliability \u002F strongly cautionary**\n\nIf different results in the same paper deserve different levels, state that explicitly rather than forcing one paper-wide label.\n\n### Step 8 — Perform a Self-Critical Final Check\n\nBefore finalizing, explicitly review:\n\n- strongest reason the results may still be credible\n- weakest point in the evidence chain\n- most likely overinterpretation risk\n- most likely hidden fragility not fully resolvable from the report\n- whether the paper remains citable with caution, or should be treated as hypothesis-generating only\n\n---\n\n## Mandatory Output Structure\n\n### A. Study and Claim Framing\n\nState:\n\n- study design\n- data\u002Fsystem used\n- primary result types\n- what the paper is asking the reader to believe\n\n### B. Main Result Reliability Map\n\nUse the table format from `references\u002Freliability-audit-framework.md`.\n\nFor each major claim, show:\n\n- claim\n- evidence chain\n- main strengths\n- main fragility points\n- validation status\n- reliability judgment\n\n### C. Design and Bias Audit\n\nState the most important design-level reasons the findings may be trustworthy or fragile.\n\n### D. Statistical and Model Risk Audit\n\nState whether the statistical handling supports confidence or raises caution.\n\n### E. Validation Chain Audit\n\nDistinguish clearly between internal validation, external validation, orthogonal validation, replication, and implementation-level support.\n\n### F. Conclusion Overreach Check\n\nState where the paper stays within the evidence and where it overclaims.\n\n### G. Bottom-Line Reliability Judgment\n\nGive the clearest possible conclusion:\n\n- what can be treated as reasonably usable evidence,\n- what should be treated cautiously,\n- and what should be treated as exploratory only.\n\n### H. Risk Review\n\nProvide a short self-critical audit of the final judgment.\n\n### I. Verified References or Source Basis\n\nIf formal citations are included, they must follow `references\u002Fliterature-integrity-rules.md`.\n\nIf the judgment is based only on user-provided paper text, state that clearly rather than inventing bibliographic metadata.\n\n---\n\n## Hard Rules\n\n1. Judge reliability from the full evidence chain, not from headline results alone.\n2. Separate study design, data type, assay type, and result type every time.\n3. Do not equate statistical significance with reliability.\n4. Do not equate high AUROC \u002F C-index \u002F accuracy with robustness.\n5. Do not equate internal validation with generalizability.\n6. Do not equate external association support with clinical utility.\n7. Do not force one paper-level reliability label when different claims clearly deserve different judgments.\n8. Always separate exploratory findings from validated findings.\n9. Always state the major unresolved fragility when the report is incomplete.\n10. Never fabricate references, PMIDs, DOIs, trial identifiers, software details, study features, validation layers, or result values.\n11. Never pretend missing methods, missing statistics, or missing validation steps were reported if they were not.\n12. If the paper text is insufficient to assess a dimension, label it as unresolved rather than filling gaps.\n13. If conclusion language exceeds the evidence, say so directly.\n14. If the result is likely hypothesis-generating only, say so plainly.\n15. Do not certify a paper as definitive evidence unless the validation chain and bias\u002Fstatistical handling actually support that level of confidence.\n\n---\n\n## What This Skill Should Not Do\n\nDo not:\n\n- summarize the paper without auditing reliability\n- praise novelty as if it were trustworthiness\n- use generic language like “results seem promising” without an audit basis\n- treat machine-learning benchmark performance as sufficient evidence by itself\n- treat biomarker discovery plus internal split validation as clinically reliable by default\n- hide major bias, power, leakage, or validation weaknesses behind polite wording\n- invent citation metadata or absent methodological details to make the paper look more complete\n\n---\n\n## Quality Standard\n\nA high-quality output from this skill should feel like a **result-trustworthiness audit memo**, not a paper summary.\n\nThe user should be able to see:\n\n- what the main claims are,\n- what exact evidence chain supports each one,\n- where the true fragility points sit,\n- whether the validation is convincing or superficial,\n- and whether the findings are solid enough to cite, use cautiously, or treat as exploratory only.\n",{"name":5,"author":24,"license":15,"description":7},"AIPOCH","main","e0956dc9606356ab78468936b502e55a365282e2","specialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker",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 result-reliability-checker",{"tool":38,"command":39},"bunx","bunx skills add mrsonord2240\u002Fopenscience-specialists --skill result-reliability-checker",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mrsonord2240\u002Fopenscience-specialists --skill result-reliability-checker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002FSKILL.md",true,[46,52,56,60,64,68,72],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fclaim-discipline-rules.md","REFERENCE","参考文档",1084,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Fclaim-discipline-rules.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdesign-and-bias-rules.md",1738,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Fdesign-and-bias-rules.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fliterature-integrity-rules.md",846,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Fliterature-integrity-rules.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Foutput-section-guidance.md",534,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Foutput-section-guidance.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Freliability-audit-framework.md",1808,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Freliability-audit-framework.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fstatistics-and-model-risk-rules.md",1675,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Fstatistics-and-model-risk-rules.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fvalidation-chain-framework.md",1622,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fcritical-appraisal-specialist\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fresult-reliability-checker\u002Freferences\u002Fvalidation-chain-framework.md",[77,85,92,99,106,113],{"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":81,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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",[],[]]