[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMTM95JRCQ50JCPHB9FEKS":3,"skill-same:01M7EMTM95JRCQ50JCPHB9FEKS":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},"01M7EMTM95JRCQ50JCPHB9FEKS","differential-diagnosis-framework",null,"Structured differential diagnosis — generating, prioritizing, and ruling out diagnostic hypotheses.","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-differential-diagnosis-framework\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: differential-diagnosis-framework\ndescription: Structured differential diagnosis — generating, prioritizing, and ruling out diagnostic hypotheses.\ncategory: scientific\n---\n\n## Overview\n\ndifferential-diagnosis-framework is a structured approach to diagnostic reasoning: generating a\ncomplete hypothesis set from a presentation, prioritizing by probability and treatability, and\ntesting efficiently. It is aimed at clinical trainees, researchers building diagnostic tools, and\nanyone who needs diagnostic reasoning made explicit — it does not replace clinical judgment and is\nnot a substitute for professional medical evaluation.\n\nThe framework fights the two classic diagnostic failure modes: premature closure (stopping at the\nfirst plausible diagnosis) and shotgun testing (ordering everything, interpreting nothing).\n\n## When to use\n\n- Working up an undifferentiated presentation: building the initial differential.\n- Prioritizing which diagnoses to test first (probability × urgency × treatability).\n- Choosing tests by likelihood ratios and test-treatment thresholds.\n- Avoiding cognitive biases: anchoring, confirmation bias, premature closure.\n- Teaching or assessing clinical reasoning.\n- Designing diagnostic decision-support tools or evaluating their output.\n\n## Core concepts\n\n- **Generate broadly, then prune.** Start with an exhaustive differential organized by system or\n  by pathophysiologic category (anatomic, infectious, inflammatory, neoplastic, vascular,\n  metabolic, traumatic, iatrogenic...). Use frameworks like VINDICATE or anatomic approaches to\n  avoid missing categories. Exhaustive generation is cheap; missed diagnoses are expensive.\n- **Prioritize by probability × stakes.** Rank hypotheses by pre-test probability given the\n  presentation, weighted by urgency (can't-miss diagnoses: MI, sepsis, subarachnoid hemorrhage)\n  and treatability. \"Most likely\" and \"most dangerous\" are different lists — work both.\n- **Bayesian updating.** Pre-test probability → test with known likelihood ratio → post-test\n  probability. A positive D-dimer in a low-risk patient barely moves the needle; the same result\n  in a high-risk patient is decisive. Tests don't diagnose; they update probabilities.\n- **Test and treatment thresholds.** Below the test threshold: don't test (even a positive won't\n  change management). Above the treatment threshold: treat without further testing. Between:\n  test. Explicit thresholds prevent both over-testing and dangerous under-testing.\n- **Likelihood ratios over sensitivity\u002Fspecificity.** LR+ = sens\u002F(1−spec); LR− = (1−sens)\u002Fspec.\n  LRs combine with pre-test odds directly and travel across populations better than predictive\n  values. Memorize ballpark LRs for common tests rather than sens\u002Fspec pairs.\n- **Cognitive bias countermeasures.** Anchoring (first impression dominates) → force alternative\n  generation. Confirmation bias (seeking supporting evidence) → ask \"what would disprove my\n  leading diagnosis?\" Premature closure → require explicit consideration of can't-miss diagnoses\n  before closing. Base-rate neglect → state the pre-test probability numerically.\n- **Occam vs Hickam.** Prefer a unifying diagnosis (Occam) but remember patients can have two\n  diseases (Hickam's dictum). When the presentation doesn't quite fit one diagnosis, consider\n  two — especially in elderly or complex patients.\n- **Document reasoning.** Record the differential, the leading hypothesis with its probability,\n  what would change your mind, and the plan. This is both good medicine and medicolegal sense.\n\n## Practical workflow\n\n1. **Gather data.** History (onset, character, associated symptoms, risk factors), exam,\n   existing results. Note what's missing, not just what's present.\n2. **Generate.** List all plausible diagnoses by category; include can't-miss diagnoses even at\n   low probability.\n3. **Prioritize.** Assign rough pre-test probabilities; flag the dangerous and the treatable.\n4. **Test strategically.** Choose tests with the best LRs for the decision at hand; respect test\n   and treatment thresholds; don't order tests that can't change management.\n5. **Update.** Revise probabilities with each result; be willing to abandon the leading\n   hypothesis (diagnostic timeout: scheduled re-examination of the differential).\n6. **Treat and reassess.** Response to treatment is diagnostic information — but also confounded\n   (placebo, natural history), so interpret cautiously.\n7. **Close the loop.** Final diagnosis with reasoning documented; follow up on pending results;\n   safety-net advice for what should prompt return.\n\n## Common pitfalls\n\n- Premature closure on the first plausible diagnosis.\n- Anchoring on the referral diagnosis or triage label.\n- Ordering broad panels instead of hypothesis-driven tests.\n- Ignoring base rates (rare zebras over common horses without reason).\n- Positive test results over-interpreted in low-prevalence settings.\n- Failing to reconsider when the patient doesn't follow the expected course.\n- Not documenting the differential or the reasoning behind test choices.\n\n*Note: this skill supports clinical reasoning education and decision-support design. It does not\nprovide medical advice for individual patients — diagnostic decisions require qualified\nclinicians with full clinical context.*\n","## Overview\n\ndifferential-diagnosis-framework is a structured approach to diagnostic reasoning: generating a\ncomplete hypothesis set from a presentation, prioritizing by probability and treatability, and\ntesting efficiently. It is aimed at clinical trainees, researchers building diagnostic tools, and\nanyone who needs diagnostic reasoning made explicit — it does not replace clinical judgment and is\nnot a substitute for professional medical evaluation.\n\nThe framework fights the two classic diagnostic failure modes: premature closure (stopping at the\nfirst plausible diagnosis) and shotgun testing (ordering everything, interpreting nothing).\n\n## When to use\n\n- Working up an undifferentiated presentation: building the initial differential.\n- Prioritizing which diagnoses to test first (probability × urgency × treatability).\n- Choosing tests by likelihood ratios and test-treatment thresholds.\n- Avoiding cognitive biases: anchoring, confirmation bias, premature closure.\n- Teaching or assessing clinical reasoning.\n- Designing diagnostic decision-support tools or evaluating their output.\n\n## Core concepts\n\n- **Generate broadly, then prune.** Start with an exhaustive differential organized by system or\n  by pathophysiologic category (anatomic, infectious, inflammatory, neoplastic, vascular,\n  metabolic, traumatic, iatrogenic...). Use frameworks like VINDICATE or anatomic approaches to\n  avoid missing categories. Exhaustive generation is cheap; missed diagnoses are expensive.\n- **Prioritize by probability × stakes.** Rank hypotheses by pre-test probability given the\n  presentation, weighted by urgency (can't-miss diagnoses: MI, sepsis, subarachnoid hemorrhage)\n  and treatability. \"Most likely\" and \"most dangerous\" are different lists — work both.\n- **Bayesian updating.** Pre-test probability → test with known likelihood ratio → post-test\n  probability. A positive D-dimer in a low-risk patient barely moves the needle; the same result\n  in a high-risk patient is decisive. Tests don't diagnose; they update probabilities.\n- **Test and treatment thresholds.** Below the test threshold: don't test (even a positive won't\n  change management). Above the treatment threshold: treat without further testing. Between:\n  test. Explicit thresholds prevent both over-testing and dangerous under-testing.\n- **Likelihood ratios over sensitivity\u002Fspecificity.** LR+ = sens\u002F(1−spec); LR− = (1−sens)\u002Fspec.\n  LRs combine with pre-test odds directly and travel across populations better than predictive\n  values. Memorize ballpark LRs for common tests rather than sens\u002Fspec pairs.\n- **Cognitive bias countermeasures.** Anchoring (first impression dominates) → force alternative\n  generation. Confirmation bias (seeking supporting evidence) → ask \"what would disprove my\n  leading diagnosis?\" Premature closure → require explicit consideration of can't-miss diagnoses\n  before closing. Base-rate neglect → state the pre-test probability numerically.\n- **Occam vs Hickam.** Prefer a unifying diagnosis (Occam) but remember patients can have two\n  diseases (Hickam's dictum). When the presentation doesn't quite fit one diagnosis, consider\n  two — especially in elderly or complex patients.\n- **Document reasoning.** Record the differential, the leading hypothesis with its probability,\n  what would change your mind, and the plan. This is both good medicine and medicolegal sense.\n\n## Practical workflow\n\n1. **Gather data.** History (onset, character, associated symptoms, risk factors), exam,\n   existing results. Note what's missing, not just what's present.\n2. **Generate.** List all plausible diagnoses by category; include can't-miss diagnoses even at\n   low probability.\n3. **Prioritize.** Assign rough pre-test probabilities; flag the dangerous and the treatable.\n4. **Test strategically.** Choose tests with the best LRs for the decision at hand; respect test\n   and treatment thresholds; don't order tests that can't change management.\n5. **Update.** Revise probabilities with each result; be willing to abandon the leading\n   hypothesis (diagnostic timeout: scheduled re-examination of the differential).\n6. **Treat and reassess.** Response to treatment is diagnostic information — but also confounded\n   (placebo, natural history), so interpret cautiously.\n7. **Close the loop.** Final diagnosis with reasoning documented; follow up on pending results;\n   safety-net advice for what should prompt return.\n\n## Common pitfalls\n\n- Premature closure on the first plausible diagnosis.\n- Anchoring on the referral diagnosis or triage label.\n- Ordering broad panels instead of hypothesis-driven tests.\n- Ignoring base rates (rare zebras over common horses without reason).\n- Positive test results over-interpreted in low-prevalence settings.\n- Failing to reconsider when the patient doesn't follow the expected course.\n- Not documenting the differential or the reasoning behind test choices.\n\n*Note: this skill supports clinical reasoning education and decision-support design. It does not\nprovide medical advice for individual patients — diagnostic decisions require qualified\nclinicians with full clinical context.*\n",{"name":5,"category":24,"description":7},"scientific","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-differential-diagnosis-framework",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 differential-diagnosis-framework",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill differential-diagnosis-framework",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill differential-diagnosis-framework","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-differential-diagnosis-framework\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",[],[]]