[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVAFXMJPK6AH8Q855G24FJ":3,"skill-same:01M7EVAFXMJPK6AH8Q855G24FJ":47},{"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":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EVAFXMJPK6AH8Q855G24FJ","pharmacovigilance-signals",null,"Drug safety signal detection — disproportionality analysis, case-series evaluation, and signal validation.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-pharmacovigilance-signals\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pharmacovigilance-signals\ndescription: Drug safety signal detection — disproportionality analysis, case-series evaluation, and signal validation.\ncategory: scientific\n---\n\n## Overview\n\npharmacovigilance-signals covers the detection and evaluation of adverse-drug-reaction signals\nfrom spontaneous reporting systems (FAERS, EudraVigilance, VigiBase): disproportionality\nstatistics, case-series clinical review, and the validation workflow that separates real safety\nissues from reporting artifacts. Signal detection is hypothesis generation — every signal needs\nclinical and epidemiologic follow-up.\n\n## When to use\n\n- Screening spontaneous-report databases for drug-event associations.\n- Disproportionality analysis: PRR, ROR, IC (BCPNN), EBGM.\n- Evaluating a signal: case review, temporality, dechallenge\u002Frechallenge.\n- Distinguishing true signals from notoriety, Weber, and masking effects.\n- Signal prioritization for regulatory or clinical action.\n- Designing post-signal pharmacoepidemiology studies.\n\n## Core concepts\n\n- **Spontaneous reporting.** Voluntary reports of suspected adverse reactions — massive,\n  global, but with no denominator, underreporting (typically >90% of events unreported),\n  and reporting biases. Strength: detects rare, serious, unexpected events trials can't.\n  Weakness: everything quantitative is fragile.\n- **Disproportionality statistics.** PRR (proportional reporting ratio), ROR (reporting odds\n  ratio), IC (information component, BCPNN), EBGM (empirical Bayes). They ask: is this\n  drug-event pair reported more often than expected vs all other drugs\u002Fevents? Thresholds\n  (e.g. PRR ≥2, χ² ≥4, n ≥3) are screening filters, not proof. Shrinkage methods (IC, EBGM)\n  handle small counts better.\n- **Reporting biases.** Weber effect (reporting peaks after launch then declines); notoriety\n  bias (media coverage spikes reports); stimulated reporting (regulatory actions prompt\n  reports); confounding by indication (the disease, not the drug, causes the event);\n  masking (a drug with many reports of one event suppresses disproportionality for others).\n  Every signal must be examined for these before being believed.\n- **Case-series evaluation.** The clinical core: review individual reports for temporality\n  (plausible time-to-onset), dechallenge (event resolves on stopping), rechallenge (recurs on\n  restarting — strong evidence, rarely available), dose relationship, alternative causes, and\n  reporter quality. A handful of well-documented cases beats a thousand thin ones.\n- **Causality assessment.** WHO-UMC or Naranjo scales structure individual-case judgment\n  (certain\u002Fprobable\u002Fpossible\u002Funlikely). They're guides, not algorithms — clinical judgment\n  integrates the pattern.\n- **Signal prioritization.** Seriousness, unexpectedness (not in label), strength of evidence,\n  public-health impact, and preventability. Prioritize signals that are serious, unlabeled,\n  and actionable — not just statistically striking.\n- **Validation.** Disproportionality signals require confirmation: targeted\n  pharmacoepidemiology (cohort\u002Fcase-control in EHR\u002Fclaims), literature review, mechanistic\n  plausibility, and sometimes de novo studies. A signal is not a finding until validated.\n- **Data quality.** Duplicate reports (same event reported by patient, doctor, manufacturer),\n  missing data, coding variation (MedDRA granularity — group related preferred terms or miss\n  the signal). Deduplicate and standardize before analysis.\n\n## Practical workflow\n\n1. **Define the question.** Drug(s), event(s) with MedDRA terms (group synonyms), time window,\n   database.\n2. **Clean.** Deduplicate, standardize coding, handle missing fields transparently.\n3. **Screen.** Disproportionality statistics with shrinkage; stratify by age\u002Fsex\u002Freporter\n   where relevant; flag threshold-crossers.\n4. **Triage for bias.** Check Weber\u002Fnotoriety patterns, indication confounding, masking —\n   discard or down-weight artifactual signals.\n5. **Clinical review.** Case series: temporality, dechallenge\u002Frechallenge, alternatives,\n   WHO-UMC causality on key cases.\n6. **Prioritize.** Seriousness × unexpectedness × evidence strength × actionability.\n7. **Validate and act.** Pharmacoepi follow-up, literature, mechanistic review; communicate\n   with appropriate uncertainty; monitor after action.\n\nExample (R sketch):\n```r\n# 2x2: a=drug+event, b=drug+other, c=other+event, d=other+other\nPRR \u003C- (a\u002F(a+b)) \u002F (c\u002F(c+d)); ROR \u003C- (a*d)\u002F(b*c)\n# use shrinkage methods (e.g. PhViD::BCPNN) for routine screening\n```\n\n## Common pitfalls\n\n- Treating disproportionality as incidence or risk (no denominator!).\n- Ignoring notoriety\u002FWeber effects (media-driven pseudo-signals).\n- Confounding by indication mistaken for drug effect.\n- MedDRA splitting hiding signals across synonymous terms.\n- Duplicate reports inflating counts.\n- Acting on unvalidated signals — or ignoring validated ones.\n- Small-count signals without shrinkage (wild PRRs from n=2).\n","## Overview\n\npharmacovigilance-signals covers the detection and evaluation of adverse-drug-reaction signals\nfrom spontaneous reporting systems (FAERS, EudraVigilance, VigiBase): disproportionality\nstatistics, case-series clinical review, and the validation workflow that separates real safety\nissues from reporting artifacts. Signal detection is hypothesis generation — every signal needs\nclinical and epidemiologic follow-up.\n\n## When to use\n\n- Screening spontaneous-report databases for drug-event associations.\n- Disproportionality analysis: PRR, ROR, IC (BCPNN), EBGM.\n- Evaluating a signal: case review, temporality, dechallenge\u002Frechallenge.\n- Distinguishing true signals from notoriety, Weber, and masking effects.\n- Signal prioritization for regulatory or clinical action.\n- Designing post-signal pharmacoepidemiology studies.\n\n## Core concepts\n\n- **Spontaneous reporting.** Voluntary reports of suspected adverse reactions — massive,\n  global, but with no denominator, underreporting (typically >90% of events unreported),\n  and reporting biases. Strength: detects rare, serious, unexpected events trials can't.\n  Weakness: everything quantitative is fragile.\n- **Disproportionality statistics.** PRR (proportional reporting ratio), ROR (reporting odds\n  ratio), IC (information component, BCPNN), EBGM (empirical Bayes). They ask: is this\n  drug-event pair reported more often than expected vs all other drugs\u002Fevents? Thresholds\n  (e.g. PRR ≥2, χ² ≥4, n ≥3) are screening filters, not proof. Shrinkage methods (IC, EBGM)\n  handle small counts better.\n- **Reporting biases.** Weber effect (reporting peaks after launch then declines); notoriety\n  bias (media coverage spikes reports); stimulated reporting (regulatory actions prompt\n  reports); confounding by indication (the disease, not the drug, causes the event);\n  masking (a drug with many reports of one event suppresses disproportionality for others).\n  Every signal must be examined for these before being believed.\n- **Case-series evaluation.** The clinical core: review individual reports for temporality\n  (plausible time-to-onset), dechallenge (event resolves on stopping), rechallenge (recurs on\n  restarting — strong evidence, rarely available), dose relationship, alternative causes, and\n  reporter quality. A handful of well-documented cases beats a thousand thin ones.\n- **Causality assessment.** WHO-UMC or Naranjo scales structure individual-case judgment\n  (certain\u002Fprobable\u002Fpossible\u002Funlikely). They're guides, not algorithms — clinical judgment\n  integrates the pattern.\n- **Signal prioritization.** Seriousness, unexpectedness (not in label), strength of evidence,\n  public-health impact, and preventability. Prioritize signals that are serious, unlabeled,\n  and actionable — not just statistically striking.\n- **Validation.** Disproportionality signals require confirmation: targeted\n  pharmacoepidemiology (cohort\u002Fcase-control in EHR\u002Fclaims), literature review, mechanistic\n  plausibility, and sometimes de novo studies. A signal is not a finding until validated.\n- **Data quality.** Duplicate reports (same event reported by patient, doctor, manufacturer),\n  missing data, coding variation (MedDRA granularity — group related preferred terms or miss\n  the signal). Deduplicate and standardize before analysis.\n\n## Practical workflow\n\n1. **Define the question.** Drug(s), event(s) with MedDRA terms (group synonyms), time window,\n   database.\n2. **Clean.** Deduplicate, standardize coding, handle missing fields transparently.\n3. **Screen.** Disproportionality statistics with shrinkage; stratify by age\u002Fsex\u002Freporter\n   where relevant; flag threshold-crossers.\n4. **Triage for bias.** Check Weber\u002Fnotoriety patterns, indication confounding, masking —\n   discard or down-weight artifactual signals.\n5. **Clinical review.** Case series: temporality, dechallenge\u002Frechallenge, alternatives,\n   WHO-UMC causality on key cases.\n6. **Prioritize.** Seriousness × unexpectedness × evidence strength × actionability.\n7. **Validate and act.** Pharmacoepi follow-up, literature, mechanistic review; communicate\n   with appropriate uncertainty; monitor after action.\n\nExample (R sketch):\n```r\n# 2x2: a=drug+event, b=drug+other, c=other+event, d=other+other\nPRR \u003C- (a\u002F(a+b)) \u002F (c\u002F(c+d)); ROR \u003C- (a*d)\u002F(b*c)\n# use shrinkage methods (e.g. PhViD::BCPNN) for routine screening\n```\n\n## Common pitfalls\n\n- Treating disproportionality as incidence or risk (no denominator!).\n- Ignoring notoriety\u002FWeber effects (media-driven pseudo-signals).\n- Confounding by indication mistaken for drug effect.\n- MedDRA splitting hiding signals across synonymous terms.\n- Duplicate reports inflating counts.\n- Acting on unvalidated signals — or ignoring validated ones.\n- Small-count signals without shrinkage (wild PRRs from n=2).\n",{"name":5,"category":24,"description":7},"scientific","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-pharmacovigilance-signals",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill pharmacovigilance-signals",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill pharmacovigilance-signals",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill pharmacovigilance-signals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-pharmacovigilance-signals\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\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":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\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":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]