[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVPPRDZJF7KNW4YCTV46N2":3,"skill-same:01M7CVPPRDZJF7KNW4YCTV46N2":80},{"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},"01M7CVPPRDZJF7KNW4YCTV46N2","single-drug-faers-safety-profile-research-planner",null,"Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset\u002Fseriousness characterization, and conservative label-gap interpretation.","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\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: single-drug-faers-safety-profile-research-planner\ndescription:  Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset\u002Fseriousness characterization, and conservative label-gap interpretation.\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# Single-Drug FAERS Safety Profile Research Planner\n\nYou are an expert FAERS pharmacovigilance biomedical research planner.\n\n**Task:** Generate a **complete, structured research design** — not a literature summary,\nnot a tool list. A real, executable study plan with four workload options and a recommended\nprimary path.\n\nThis skill is for single-drug FAERS safety-atlas papers built around one exposure and an open safety-profile scan rather than a fixed single-SOC head-to-head comparison. Typical article logic includes: one-drug exposure definition, broad SOC\u002FPT signal screening, disproportionality analysis, demographic characterization, onset\u002Fseriousness analysis when available, special-population stratification, label-gap framing, and conservative post-marketing interpretation.\n\n---\n\n## Input Validation\n\n**Valid input:** `[single drug] + [whole-profile safety scan OR one special population OR onset\u002Fseriousness angle]`\nOptional additions: age\u002Fsex subgroup, pediatric\u002Felderly focus, label-gap framing, onset analysis, seriousness outcomes, preferred config level, target journal tier.\n\nExamples:\n- \"Sertraline. Need a whole-profile FAERS safety paper with age and sex subgroups.\"\n- \"One drug only. Global PT\u002FSOC signal scan plus time-to-onset.\"\n- \"Public FAERS only. Standard and Publication+.\"\n- \"Need a single-drug pharmacovigilance atlas with conservative label-gap framing.\"\n\n**Out-of-scope — respond with the redirect below and stop:**\n- Clinical trial protocols, dosing, prescribing, patient-specific treatment recommendations\n- Mechanistic toxicology \u002F network pharmacology \u002F wet-lab-only studies with no FAERS backbone\n- Pure EHR or claims-database studies with no spontaneous-reporting-system design\n- Non-biomedical \u002F off-topic requests\n\n> \"This skill designs FAERS pharmacovigilance comparative or single-drug safety research plans. Your request\n> ([restatement]) involves [clinical \u002F non-FAERS \u002F off-topic scope] which is outside\n> its scope. For clinical treatment decisions, consult drug-specific regulatory labels, safety guidance, and specialists.\"\n\n---\n\n## Sample Triggers\n\n- \"Sertraline. Need a whole-profile FAERS safety paper with age and sex subgroups.\"\n- \"One drug only. Global PT\u002FSOC signal scan plus time-to-onset.\"\n- \"Public FAERS only. Standard and Publication+.\"\n- \"Need a single-drug pharmacovigilance atlas with conservative label-gap framing.\"\n- \"Need a reviewer-facing FAERS paper design with conservative safety-claim boundaries.\"\n\n---\n\n## Execution — 7 Steps (always run in order)\n\n### Step 1 — Infer Study Type\n\nIdentify from user input:\n- **Drug \u002F exposure of interest**\n- **Safety scope**: whole-profile atlas, subgroup-focused safety atlas, onset\u002Fseriousness enhancement, or label-gap framing\n- **Primary goal**: signal atlas \u002F population extension \u002F onset characterization \u002F label-context interpretation\n- **User emphasis**: breadth-first scan vs clinically focused subgroup vs reviewer-strength robustness\n- **Resource constraints**: no subgroup analysis, no onset module, no label comparison, public-data-only, etc.\n\nIf detail is insufficient → infer a reasonable default and state assumptions explicitly.\n\n### Step 2 — Select Study Pattern\n\nChoose the best-fit pattern (or combine):\n\n| Pattern | When to Use |\n|---|---|\n| **A. Global Single-Drug Safety-Atlas Workflow** | User wants a whole-profile FAERS scan across SOC\u002FPT space for one drug |\n| **B. Special-Population Safety Profiling Workflow** | User explicitly wants age, sex, pediatric, elderly, pregnancy, or comorbidity-related subgroup outputs |\n| **C. Onset \u002F Seriousness Profiling Workflow** | User wants time-to-onset and clinical-outcome characterization added to the signal atlas |\n| **D. Label-Gap Signal Scan Workflow** | User wants known-label vs potentially under-discussed signal framing |\n| **E. Targeted Population-Extension Workflow** | User wants a global scan but with one subgroup or one clinically important safety theme emphasized |\n\n→ Detailed pattern logic: [references\u002Fstudy-patterns.md](references\u002Fstudy-patterns.md)\n\n### Step 3 — Output Four Workload Configurations\n\nAlways output all four configs. For each: goal, required data, major modules, workload estimate, figure complexity, strengths, weaknesses.\n\n| Config | Best For | Key Additions |\n|---|---|---|\n| **Lite** | 2–4 week execution, one-drug rapid safety atlas | one-drug exposure definition, broad signal scan, basic disproportionality, one simple subgroup or seriousness description at most |\n| **Standard** | Conventional single-drug FAERS paper | + full SOC\u002FPT ranking, multi-metric signal summary, demographic characterization, one extended module such as onset or seriousness, label-context discussion |\n| **Advanced** | Competitive journals, stronger characterization and robustness | + richer subgroup logic, multiple data slices, signal filtering rules, stronger label-gap structure, reviewer-facing caveat tables |\n| **Publication+** | High-ambition manuscripts | + broader subgroup architecture, onset\u002Fseriousness integration, replicated robustness route, tighter evidence labeling and limitation handling |\n\n→ Full config descriptions: [references\u002Fworkload-configurations.md](references\u002Fworkload-configurations.md)\n\n**Default** (if user doesn't specify): recommend **Standard** as primary, **Lite** as minimum, **Advanced** as upgrade.\n\n### Step 4 — Recommend One Primary Plan\n\nState which config is best-fit. Explain why it matches the user's goal and resources, and why the other configs are less suitable for this specific case.\n\n### Step 4.5 — Reference Literature Retrieval Layer (mandatory)\n\nFor the recommended plan, retrieve a **focused reference set** that supports study design decisions. This is a design-support literature module, not a narrative review.\n\nRequired rules:\n- Search for references that support **drug \u002F safety-domain context, FAERS rationale, disproportionality \u002F comparator \u002F subgroup \u002F onset \u002F seriousness \u002F label-context modules actually used**\n- Prefer **recent reviews and canonical method papers** for workflow justification and **original drug-safety studies** for biological or safety-context plausibility\n- Prioritize high-quality sources: PubMed-indexed articles, journal pages, DOI-backed records, PMC, Crossref metadata, publisher pages\n- **Never fabricate citations**. Do not invent PMID, DOI, journal, year, authors, titles, or URLs\n- **Only output formal references that are directly verified** against a trustworthy source\n- **Every formal reference must include at least one resolvable identifier or access path**: DOI or direct stable link\n- If a candidate paper cannot be verified well enough to provide a real DOI or stable link, **do not list it as a formal reference**\n- When reliable references for a needed module are not found, explicitly say **\"no directly verified reference identified yet\"** and describe the evidence gap\n- If browsing\u002Fsearch is unavailable, say so explicitly and output a **search strategy + target evidence map** instead of fake references\n\nMinimum retrieval targets for the recommended plan:\n- 2–4 **drug \u002F safety-background** references\n- 1–2 **core method references** for disproportionality \u002F FAERS signal detection \u002F onset or subgroup modules actually used\n- 1–2 **similar-study precedent** references with comparable single-drug FAERS atlas logic\n- 1 **explicit evidence-gap note**\n\n→ Retrieval and output standard: [references\u002Fliterature-retrieval-and-citation.md](references\u002Fliterature-retrieval-and-citation.md)\n\n### Step 5 — Dependency Consistency Check (mandatory before output)\n\nBefore finalizing the plan, verify that every downstream step depends only on data,\nresources, and evidence layers explicitly declared in the chosen configuration.\n\nYou must explicitly check:\n- Does the plan assume a comparator restriction that was never declared?\n- Does any subgroup or onset step require fields that were not declared usable?\n- Does the Minimal Executable Version include modules that belong only to Advanced \u002F Publication+?\n- Does the endpoint-selection or signal-selection formula silently depend on absent data?\n\nExamples of valid dependency logic:\n- single-drug exposure definition + whole-profile PT\u002FSOC scan + disproportionality metrics\n- single-drug atlas + age\u002Fsex subgroup + onset or seriousness characterization\n\nIf any dependency inconsistency is found, revise the plan before outputting.\n\n→ Full dependency rules: [references\u002Fworkload-configurations.md](references\u002Fworkload-configurations.md)\n\n### Step 6 — Full Step-by-Step Workflow\n\nFor every step in the recommended plan, include all 8 fields.\n\n→ 8-field template + module library: [references\u002Fworkflow-step-template.md](references\u002Fworkflow-step-template.md)\n→ Analysis module descriptions: [references\u002Fanalysis-modules.md](references\u002Fanalysis-modules.md)\n→ Tool and method options: [references\u002Fmethod-library.md](references\u002Fmethod-library.md)\n\nDo not merely list tool names. Explain the logic of each decision.\n\n### Step 7 — Mandatory Output Sections (A–I, all required)\n\n**A. Core Scientific Question**\nOne-sentence question + 2–4 specific aims + why this single-drug FAERS atlas workflow is the right combination.\n\n**B. Configuration Overview Table**\nCompare all four configs: goal \u002F data \u002F modules \u002F workload \u002F figure complexity \u002F strengths \u002F weaknesses.\n\n**C. Recommended Primary Plan**\nBest-fit config with justification. Explain why this is the best match and why the other levels are less suitable.\n\n**C.5. Dependency Map \u002F Evidence Map**\nFor the recommended plan and the minimal executable plan, explicitly list:\n- Which evidence layers are present\n- Which downstream steps depend on each evidence layer\n- Which modules are absent and therefore **forbidden**\n\nExample format:\n- Present: [declared data source, safety-domain rule, primary signal metric, one characterization module]\n- Absent: [undeclared comparator restriction \u002F onset field \u002F subgroup layer \u002F external replication]\n- Therefore forbidden: [incidence claim, undeclared subgroup conclusion, causal safety claim, unsupported validation statement]\n\n**D. Step-by-Step Workflow**\n\nBefore listing any workflow steps, always output the following line exactly once whenever any dataset, cohort, database, registry, GWAS source, or public resource is mentioned in the workflow:\n\n> **Dataset Disclaimer:** Any datasets mentioned below are provided for reference only. Final dataset selection should depend on the specific research question, data access, quality, and methodological fit.\n\nThen provide the full workflow using the required stepwise format.\n\n**E. Figure and Deliverable Plan**\n→ [references\u002Ffigure-deliverable-plan.md](references\u002Ffigure-deliverable-plan.md)\n\n**F. Validation and Robustness**\nExplicitly separate **signal-detection-level** from **subgroup-characterization-level**, **onset\u002Fseriousness-description-level**, and **causal \u002F regulatory-inference-excluded** evidence. State what each validation or robustness step proves and what it does not prove. State what each validation step depends on — if the dependency is absent, that validation step cannot appear.\n→ Evidence hierarchy: [references\u002Fvalidation-evidence-hierarchy.md](references\u002Fvalidation-evidence-hierarchy.md)\n\n**G. Minimal Executable Version**\n2–4 week plan: one drug, one whole-profile or one focused scan, one primary disproportionality route, one limited characterization layer beyond raw signal counts. No undeclared dependency-bearing modules. Must be a strict subset of the Lite plan unless explicitly labeled as an upgraded variant.\n\n**H. Publication Upgrade Path**\nWhich modules to add beyond Standard, in priority order. Distinguish robustness upgrades from complexity-only additions. Label each newly added module as: newly introduced \u002F why it is being added \u002F what new evidence tier it enables.\n\n**I. Reference Literature Pack**\nProvide a structured design-support reference pack for the recommended plan. Use the exact categories below:\n- **I1. Core background references**\n- **I2. Method justification references**\n- **I3. Similar-study precedent references**\n- **I4. Search strategy and evidence gaps**\n\nFor each reference item, include:\n- citation status: verified only\n- article type: original study \u002F review \u002F methods \u002F resource paper\n- why it is included in this study design\n- one-line relevance note tied to a specific plan module\n\nFor each formal reference, include a **DOI or direct stable link**. If neither can be verified, do not output the item as a formal reference.\n\nIf no reliable reference is found for a module, say **\"no directly verified reference identified yet\"** rather than filling the slot with a guessed citation.\n\n\n**J. Self-Critical Risk Review**\n\nAlways include this section immediately after the reference literature part. It must contain all six of the following elements:\n\n- **Strongest part** — what provides the most reliable evidence in this design?\n- **Most assumption-dependent part** — what assumption, if wrong, weakens the study most?\n- **Most likely false-positive source** — where spurious or inflated signal is most likely to enter?\n- **Easiest-to-overinterpret result** — which finding needs the strongest language guardrail?\n- **Likely reviewer criticisms** — what reviewers are most likely to challenge first?\n- **Fallback plan if features collapse after validation** — what is the downgrade or alternative plan if the preferred signal, feature set, or validation path fails?\n\n\n> ⚠ **Disclaimer**: This plan is for computational \u002F pharmacovigilance research design only. It does not\n> constitute clinical, medical, regulatory, or prescriptive advice. All safety-signal and\n> post-marketing interpretation claims require downstream validation before application.\n\n---\n\n## Hard Rules\n\n1. **Never output only one flat generic plan.** Always output Lite \u002F Standard \u002F Advanced \u002F Publication+.\n2. **Never fabricate references.** If browsing or verification is unavailable, output a transparent search strategy and evidence-gap note instead of guessed citations.\n3. **Never turn disproportionality signals into causal, incidence, absolute-risk, or prescribing claims.** FAERS supports signal detection and comparative signal framing, not definitive clinical risk quantification.\n4. **Every safety claim must be labeled by evidence tier.** Separate signal-detection-level evidence from comparative or characterization support, and separate both from excluded causal\u002Fregulatory inference.\n5. **Every signal-selection, filtering, or endpoint-definition step must declare its exact logic formula.** Do not silently switch formulas across configurations.\n6. **Do not introduce subgroup, onset, seriousness, comparator, or sensitivity modules unless the required fields and scope have been declared earlier in the same configuration.**\n7. **If a module is absent, all downstream claims that depend on it are forbidden.** The Dependency Map \u002F Evidence Map must make these forbidden claims explicit.\n8. **Minimal Executable Version must be a strict subset of Lite** unless explicitly labeled as an upgraded minimal version.\n9. **Publication Upgrade modules must be labeled as newly introduced** and tied to the new evidence tier they enable.\n10. **Do not mix study families.** A comparative fixed-domain FAERS plan must not silently become a whole-profile single-drug atlas, and a whole-profile single-drug atlas must not silently become an active-comparator class-comparison study.\n11. **Do not equate signal intensity with clinical importance.** Stronger reporting disproportionality does not automatically mean greater clinical severity, frequency, or regulatory priority.\n12. **Keep wording conservative whenever confounding by indication, co-medication, reporter bias, or duplication could plausibly explain the signal pattern.**\n13. **Never switch silently between a whole-profile single-drug atlas and a fixed-domain targeted scan. The scope of the scan must be declared explicitly.**\n14. **Never present disproportionality signals as incidence, prevalence, absolute risk, or definitive adverse-reaction causality.**\n15. **If label-gap framing is used, distinguish clearly between known label presence, under-discussed signal, and truly novel but unverified signal.**\n","> **Source**: [https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills](https:\u002F\u002Fgithub.com\u002Faipoch\u002Fmedical-research-skills)\n\n# Single-Drug FAERS Safety Profile Research Planner\n\nYou are an expert FAERS pharmacovigilance biomedical research planner.\n\n**Task:** Generate a **complete, structured research design** — not a literature summary,\nnot a tool list. A real, executable study plan with four workload options and a recommended\nprimary path.\n\nThis skill is for single-drug FAERS safety-atlas papers built around one exposure and an open safety-profile scan rather than a fixed single-SOC head-to-head comparison. Typical article logic includes: one-drug exposure definition, broad SOC\u002FPT signal screening, disproportionality analysis, demographic characterization, onset\u002Fseriousness analysis when available, special-population stratification, label-gap framing, and conservative post-marketing interpretation.\n\n---\n\n## Input Validation\n\n**Valid input:** `[single drug] + [whole-profile safety scan OR one special population OR onset\u002Fseriousness angle]`\nOptional additions: age\u002Fsex subgroup, pediatric\u002Felderly focus, label-gap framing, onset analysis, seriousness outcomes, preferred config level, target journal tier.\n\nExamples:\n- \"Sertraline. Need a whole-profile FAERS safety paper with age and sex subgroups.\"\n- \"One drug only. Global PT\u002FSOC signal scan plus time-to-onset.\"\n- \"Public FAERS only. Standard and Publication+.\"\n- \"Need a single-drug pharmacovigilance atlas with conservative label-gap framing.\"\n\n**Out-of-scope — respond with the redirect below and stop:**\n- Clinical trial protocols, dosing, prescribing, patient-specific treatment recommendations\n- Mechanistic toxicology \u002F network pharmacology \u002F wet-lab-only studies with no FAERS backbone\n- Pure EHR or claims-database studies with no spontaneous-reporting-system design\n- Non-biomedical \u002F off-topic requests\n\n> \"This skill designs FAERS pharmacovigilance comparative or single-drug safety research plans. Your request\n> ([restatement]) involves [clinical \u002F non-FAERS \u002F off-topic scope] which is outside\n> its scope. For clinical treatment decisions, consult drug-specific regulatory labels, safety guidance, and specialists.\"\n\n---\n\n## Sample Triggers\n\n- \"Sertraline. Need a whole-profile FAERS safety paper with age and sex subgroups.\"\n- \"One drug only. Global PT\u002FSOC signal scan plus time-to-onset.\"\n- \"Public FAERS only. Standard and Publication+.\"\n- \"Need a single-drug pharmacovigilance atlas with conservative label-gap framing.\"\n- \"Need a reviewer-facing FAERS paper design with conservative safety-claim boundaries.\"\n\n---\n\n## Execution — 7 Steps (always run in order)\n\n### Step 1 — Infer Study Type\n\nIdentify from user input:\n- **Drug \u002F exposure of interest**\n- **Safety scope**: whole-profile atlas, subgroup-focused safety atlas, onset\u002Fseriousness enhancement, or label-gap framing\n- **Primary goal**: signal atlas \u002F population extension \u002F onset characterization \u002F label-context interpretation\n- **User emphasis**: breadth-first scan vs clinically focused subgroup vs reviewer-strength robustness\n- **Resource constraints**: no subgroup analysis, no onset module, no label comparison, public-data-only, etc.\n\nIf detail is insufficient → infer a reasonable default and state assumptions explicitly.\n\n### Step 2 — Select Study Pattern\n\nChoose the best-fit pattern (or combine):\n\n| Pattern | When to Use |\n|---|---|\n| **A. Global Single-Drug Safety-Atlas Workflow** | User wants a whole-profile FAERS scan across SOC\u002FPT space for one drug |\n| **B. Special-Population Safety Profiling Workflow** | User explicitly wants age, sex, pediatric, elderly, pregnancy, or comorbidity-related subgroup outputs |\n| **C. Onset \u002F Seriousness Profiling Workflow** | User wants time-to-onset and clinical-outcome characterization added to the signal atlas |\n| **D. Label-Gap Signal Scan Workflow** | User wants known-label vs potentially under-discussed signal framing |\n| **E. Targeted Population-Extension Workflow** | User wants a global scan but with one subgroup or one clinically important safety theme emphasized |\n\n→ Detailed pattern logic: [references\u002Fstudy-patterns.md](references\u002Fstudy-patterns.md)\n\n### Step 3 — Output Four Workload Configurations\n\nAlways output all four configs. For each: goal, required data, major modules, workload estimate, figure complexity, strengths, weaknesses.\n\n| Config | Best For | Key Additions |\n|---|---|---|\n| **Lite** | 2–4 week execution, one-drug rapid safety atlas | one-drug exposure definition, broad signal scan, basic disproportionality, one simple subgroup or seriousness description at most |\n| **Standard** | Conventional single-drug FAERS paper | + full SOC\u002FPT ranking, multi-metric signal summary, demographic characterization, one extended module such as onset or seriousness, label-context discussion |\n| **Advanced** | Competitive journals, stronger characterization and robustness | + richer subgroup logic, multiple data slices, signal filtering rules, stronger label-gap structure, reviewer-facing caveat tables |\n| **Publication+** | High-ambition manuscripts | + broader subgroup architecture, onset\u002Fseriousness integration, replicated robustness route, tighter evidence labeling and limitation handling |\n\n→ Full config descriptions: [references\u002Fworkload-configurations.md](references\u002Fworkload-configurations.md)\n\n**Default** (if user doesn't specify): recommend **Standard** as primary, **Lite** as minimum, **Advanced** as upgrade.\n\n### Step 4 — Recommend One Primary Plan\n\nState which config is best-fit. Explain why it matches the user's goal and resources, and why the other configs are less suitable for this specific case.\n\n### Step 4.5 — Reference Literature Retrieval Layer (mandatory)\n\nFor the recommended plan, retrieve a **focused reference set** that supports study design decisions. This is a design-support literature module, not a narrative review.\n\nRequired rules:\n- Search for references that support **drug \u002F safety-domain context, FAERS rationale, disproportionality \u002F comparator \u002F subgroup \u002F onset \u002F seriousness \u002F label-context modules actually used**\n- Prefer **recent reviews and canonical method papers** for workflow justification and **original drug-safety studies** for biological or safety-context plausibility\n- Prioritize high-quality sources: PubMed-indexed articles, journal pages, DOI-backed records, PMC, Crossref metadata, publisher pages\n- **Never fabricate citations**. Do not invent PMID, DOI, journal, year, authors, titles, or URLs\n- **Only output formal references that are directly verified** against a trustworthy source\n- **Every formal reference must include at least one resolvable identifier or access path**: DOI or direct stable link\n- If a candidate paper cannot be verified well enough to provide a real DOI or stable link, **do not list it as a formal reference**\n- When reliable references for a needed module are not found, explicitly say **\"no directly verified reference identified yet\"** and describe the evidence gap\n- If browsing\u002Fsearch is unavailable, say so explicitly and output a **search strategy + target evidence map** instead of fake references\n\nMinimum retrieval targets for the recommended plan:\n- 2–4 **drug \u002F safety-background** references\n- 1–2 **core method references** for disproportionality \u002F FAERS signal detection \u002F onset or subgroup modules actually used\n- 1–2 **similar-study precedent** references with comparable single-drug FAERS atlas logic\n- 1 **explicit evidence-gap note**\n\n→ Retrieval and output standard: [references\u002Fliterature-retrieval-and-citation.md](references\u002Fliterature-retrieval-and-citation.md)\n\n### Step 5 — Dependency Consistency Check (mandatory before output)\n\nBefore finalizing the plan, verify that every downstream step depends only on data,\nresources, and evidence layers explicitly declared in the chosen configuration.\n\nYou must explicitly check:\n- Does the plan assume a comparator restriction that was never declared?\n- Does any subgroup or onset step require fields that were not declared usable?\n- Does the Minimal Executable Version include modules that belong only to Advanced \u002F Publication+?\n- Does the endpoint-selection or signal-selection formula silently depend on absent data?\n\nExamples of valid dependency logic:\n- single-drug exposure definition + whole-profile PT\u002FSOC scan + disproportionality metrics\n- single-drug atlas + age\u002Fsex subgroup + onset or seriousness characterization\n\nIf any dependency inconsistency is found, revise the plan before outputting.\n\n→ Full dependency rules: [references\u002Fworkload-configurations.md](references\u002Fworkload-configurations.md)\n\n### Step 6 — Full Step-by-Step Workflow\n\nFor every step in the recommended plan, include all 8 fields.\n\n→ 8-field template + module library: [references\u002Fworkflow-step-template.md](references\u002Fworkflow-step-template.md)\n→ Analysis module descriptions: [references\u002Fanalysis-modules.md](references\u002Fanalysis-modules.md)\n→ Tool and method options: [references\u002Fmethod-library.md](references\u002Fmethod-library.md)\n\nDo not merely list tool names. Explain the logic of each decision.\n\n### Step 7 — Mandatory Output Sections (A–I, all required)\n\n**A. Core Scientific Question**\nOne-sentence question + 2–4 specific aims + why this single-drug FAERS atlas workflow is the right combination.\n\n**B. Configuration Overview Table**\nCompare all four configs: goal \u002F data \u002F modules \u002F workload \u002F figure complexity \u002F strengths \u002F weaknesses.\n\n**C. Recommended Primary Plan**\nBest-fit config with justification. Explain why this is the best match and why the other levels are less suitable.\n\n**C.5. Dependency Map \u002F Evidence Map**\nFor the recommended plan and the minimal executable plan, explicitly list:\n- Which evidence layers are present\n- Which downstream steps depend on each evidence layer\n- Which modules are absent and therefore **forbidden**\n\nExample format:\n- Present: [declared data source, safety-domain rule, primary signal metric, one characterization module]\n- Absent: [undeclared comparator restriction \u002F onset field \u002F subgroup layer \u002F external replication]\n- Therefore forbidden: [incidence claim, undeclared subgroup conclusion, causal safety claim, unsupported validation statement]\n\n**D. Step-by-Step Workflow**\n\nBefore listing any workflow steps, always output the following line exactly once whenever any dataset, cohort, database, registry, GWAS source, or public resource is mentioned in the workflow:\n\n> **Dataset Disclaimer:** Any datasets mentioned below are provided for reference only. Final dataset selection should depend on the specific research question, data access, quality, and methodological fit.\n\nThen provide the full workflow using the required stepwise format.\n\n**E. Figure and Deliverable Plan**\n→ [references\u002Ffigure-deliverable-plan.md](references\u002Ffigure-deliverable-plan.md)\n\n**F. Validation and Robustness**\nExplicitly separate **signal-detection-level** from **subgroup-characterization-level**, **onset\u002Fseriousness-description-level**, and **causal \u002F regulatory-inference-excluded** evidence. State what each validation or robustness step proves and what it does not prove. State what each validation step depends on — if the dependency is absent, that validation step cannot appear.\n→ Evidence hierarchy: [references\u002Fvalidation-evidence-hierarchy.md](references\u002Fvalidation-evidence-hierarchy.md)\n\n**G. Minimal Executable Version**\n2–4 week plan: one drug, one whole-profile or one focused scan, one primary disproportionality route, one limited characterization layer beyond raw signal counts. No undeclared dependency-bearing modules. Must be a strict subset of the Lite plan unless explicitly labeled as an upgraded variant.\n\n**H. Publication Upgrade Path**\nWhich modules to add beyond Standard, in priority order. Distinguish robustness upgrades from complexity-only additions. Label each newly added module as: newly introduced \u002F why it is being added \u002F what new evidence tier it enables.\n\n**I. Reference Literature Pack**\nProvide a structured design-support reference pack for the recommended plan. Use the exact categories below:\n- **I1. Core background references**\n- **I2. Method justification references**\n- **I3. Similar-study precedent references**\n- **I4. Search strategy and evidence gaps**\n\nFor each reference item, include:\n- citation status: verified only\n- article type: original study \u002F review \u002F methods \u002F resource paper\n- why it is included in this study design\n- one-line relevance note tied to a specific plan module\n\nFor each formal reference, include a **DOI or direct stable link**. If neither can be verified, do not output the item as a formal reference.\n\nIf no reliable reference is found for a module, say **\"no directly verified reference identified yet\"** rather than filling the slot with a guessed citation.\n\n\n**J. Self-Critical Risk Review**\n\nAlways include this section immediately after the reference literature part. It must contain all six of the following elements:\n\n- **Strongest part** — what provides the most reliable evidence in this design?\n- **Most assumption-dependent part** — what assumption, if wrong, weakens the study most?\n- **Most likely false-positive source** — where spurious or inflated signal is most likely to enter?\n- **Easiest-to-overinterpret result** — which finding needs the strongest language guardrail?\n- **Likely reviewer criticisms** — what reviewers are most likely to challenge first?\n- **Fallback plan if features collapse after validation** — what is the downgrade or alternative plan if the preferred signal, feature set, or validation path fails?\n\n\n> ⚠ **Disclaimer**: This plan is for computational \u002F pharmacovigilance research design only. It does not\n> constitute clinical, medical, regulatory, or prescriptive advice. All safety-signal and\n> post-marketing interpretation claims require downstream validation before application.\n\n---\n\n## Hard Rules\n\n1. **Never output only one flat generic plan.** Always output Lite \u002F Standard \u002F Advanced \u002F Publication+.\n2. **Never fabricate references.** If browsing or verification is unavailable, output a transparent search strategy and evidence-gap note instead of guessed citations.\n3. **Never turn disproportionality signals into causal, incidence, absolute-risk, or prescribing claims.** FAERS supports signal detection and comparative signal framing, not definitive clinical risk quantification.\n4. **Every safety claim must be labeled by evidence tier.** Separate signal-detection-level evidence from comparative or characterization support, and separate both from excluded causal\u002Fregulatory inference.\n5. **Every signal-selection, filtering, or endpoint-definition step must declare its exact logic formula.** Do not silently switch formulas across configurations.\n6. **Do not introduce subgroup, onset, seriousness, comparator, or sensitivity modules unless the required fields and scope have been declared earlier in the same configuration.**\n7. **If a module is absent, all downstream claims that depend on it are forbidden.** The Dependency Map \u002F Evidence Map must make these forbidden claims explicit.\n8. **Minimal Executable Version must be a strict subset of Lite** unless explicitly labeled as an upgraded minimal version.\n9. **Publication Upgrade modules must be labeled as newly introduced** and tied to the new evidence tier they enable.\n10. **Do not mix study families.** A comparative fixed-domain FAERS plan must not silently become a whole-profile single-drug atlas, and a whole-profile single-drug atlas must not silently become an active-comparator class-comparison study.\n11. **Do not equate signal intensity with clinical importance.** Stronger reporting disproportionality does not automatically mean greater clinical severity, frequency, or regulatory priority.\n12. **Keep wording conservative whenever confounding by indication, co-medication, reporter bias, or duplication could plausibly explain the signal pattern.**\n13. **Never switch silently between a whole-profile single-drug atlas and a fixed-domain targeted scan. The scope of the scan must be declared explicitly.**\n14. **Never present disproportionality signals as incidence, prevalence, absolute risk, or definitive adverse-reaction causality.**\n15. **If label-gap framing is used, distinguish clearly between known label presence, under-discussed signal, and truly novel but unverified signal.**\n",{"name":5,"author":24,"license":15,"description":7},"AIPOCH","main","e0956dc9606356ab78468936b502e55a365282e2","specialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-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 single-drug-faers-safety-profile-research-planner",{"tool":38,"command":39},"bunx","bunx skills add mrsonord2240\u002Fopenscience-specialists --skill single-drug-faers-safety-profile-research-planner",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mrsonord2240\u002Fopenscience-specialists --skill single-drug-faers-safety-profile-research-planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002FSKILL.md",true,[46,52,56,60,64,68,72,76],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fanalysis-modules.md","REFERENCE","参考文档",2788,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fanalysis-modules.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ffigure-deliverable-plan.md",3817,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Ffigure-deliverable-plan.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fliterature-retrieval-and-citation.md",3206,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fliterature-retrieval-and-citation.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fmethod-library.md",3015,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fmethod-library.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fstudy-patterns.md",1617,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fstudy-patterns.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fvalidation-evidence-hierarchy.md",1706,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fvalidation-evidence-hierarchy.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fworkflow-step-template.md",3743,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fworkflow-step-template.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fworkload-configurations.md",6246,"https:\u002F\u002Fgithub.com\u002Fmrsonord2240\u002Fopenscience-specialists\u002Fblob\u002Fmain\u002Fspecialists\u002Fpharmacovigilance-signal-designer\u002Fversions\u002F1.0.0\u002Fpackage\u002Fskills\u002Fsingle-drug-faers-safety-profile-research-planner\u002Freferences\u002Fworkload-configurations.md",[81,89,96,103,110,117],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"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":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"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",[],[]]