{"id":"bf31e267-fa30-46e5-8e82-6e3584addd21","shortId":"SByB8w","kind":"skill","title":"clinical-case-report","tagline":"Structured medical case presentation for clinical rounds, conferences,\nand documentation. Generates SOAP-format or narrative case reports\nwith physiologically accurate vitals, labs, and evidence-based plans.\nUse when the brief mentions \"case report\", \"case presentation\", \"SOAP no","description":"# Clinical Case Report Skill\n\nGenerate a structured medical case presentation for clinical rounds,\nconferences, or documentation. The output follows standard medical\nformatting conventions used in hospital settings worldwide.\n\n## What you will produce\n\nA single-page HTML case report (`index.html`). Content varies by format\n(see `references/case-formats.md` — selected in Step 0):\n\n**SOAP / Conference format:**\n- **Patient identification** — age, sex, chief complaint\n- **History of Present Illness (HPI)** — chronological narrative with\n  pertinent positives and negatives\n- **Past Medical History, Medications, Allergies**\n- **Review of Systems**\n- **Physical Examination** — systematic findings by system\n- **Vital Signs** — formatted table with reference ranges and flags\n- **Investigations** — laboratory results and imaging findings\n- **Assessment** — primary diagnosis and differential (3–5 items)\n  with clinical reasoning for each\n- **Management Plan** — evidence-based, organised by problem\n\n**Brief Rounds format** (daily review, ward round, handover, ICU, post-call):\n- **ID line** — age, sex, day of admission, primary problem\n- **Interval events / current status** — what has changed since last review\n- **Active problems** — numbered list\n- **Plan-by-problem** — concise actions for each active problem\n- Full HPI and systematic physical examination are **not** included\n\n---\n\n## Step-by-step workflow\n\n### Step 0 — Load reference files\n\nBefore starting, read both reference files:\n\n1. `references/case-formats.md` — use this to choose the correct output\n   format (SOAP, Conference, or Brief Rounds) based on the user's context\n2. `references/checklist.md` — keep P0 gates in mind throughout; you\n   must pass all P0 items before emitting the final artifact\n\n### Step 1 — Parse the brief\n\nRead the user's prompt and extract:\n\n- Patient age and sex\n- Chief complaint or presenting problem\n- Any vitals, labs, or imaging the user has provided\n- Clinical context: ED, ward rounds, conference case, outpatient, etc.\n- Specialty context: cardiology, emergency, internal medicine, etc.\n\nIf the chief complaint or presenting problem is missing:\n- **SOAP / Conference**: ask one clarifying question before proceeding. Do not proceed without it.\n- **Brief Rounds**: if the admission problem or ID line is already available (e.g. \"day-3 ICU review for septic shock\"), proceed directly — a separate chief complaint is not required.\n\n### Step 2 — Build the clinical narrative\n\n**For SOAP / Conference outputs:** write the HPI as a continuous prose\nnarrative in standard clinical style:\n\n> \"This is a [age]-year-old [sex] with a history of [relevant PMH] who\n> presents with [chief complaint]. Symptoms began [timeline] and are\n> characterised by [quality, severity, radiation]. Associated symptoms\n> include [list]. Pertinent negatives include [list].\"\n\nThe HPI must be chronological. Include timeline markers\n(\"2 hours prior to presentation\", \"onset yesterday morning\").\n\n**For Brief Rounds outputs** (daily review, ward round, handover, ICU,\npost-call): skip the full HPI and examination. Instead produce:\n\n- **ID line**: \"[Age][sex], Day [N] of admission, [primary problem]\"\n- **Interval events / current status**: what has changed since last review\n- **Active problems**: numbered list\n- **Plan-by-problem**: concise action for each active problem\n\n### Step 3 — Generate physiologically consistent clinical data\n\nIf the user has not provided specific values, generate values that are\ninternally consistent with the diagnosis:\n\n**Consistency checks (typical patterns):**\n\n- A patient in shock **typically** has: HR >100, SBP <90, raised lactate,\n  impaired capillary refill — but medications (beta-blockers), age, or\n  shock type (neurogenic, spinal) can alter this pattern\n- Pneumonia **typically** presents with raised WBC, raised CRP,\n  temperature >38°C — but afebrile pneumonia exists, especially in\n  the elderly or immunocompromised\n- A STEMI **typically** shows ST elevation in contiguous leads and raised\n  high-sensitivity troponin — but early presentations may have initially\n  normal troponin; CK-MB is not universally required\n- Sepsis **typically** shows raised or low WBC, raised lactate >2,\n  temperature abnormality — but compensated early sepsis may present\n  with normal vitals\n- Lab units must match convention: creatinine in µmol/L or mg/dL\n  (state which), glucose in mmol/L, haemoglobin in g/dL\n\n**Critical rule — preserve user-provided data:**\n- Never overwrite a value the user has explicitly stated\n- If a user-provided value is atypical for the diagnosis, keep it and\n  note the atypical presentation in the assessment rather than\n  forcing canonical numbers\n- Never generate a value that contradicts the stated diagnosis\n\n### Step 4 — Write the assessment\n\nThe assessment section must contain:\n\n1. **Primary diagnosis** stated clearly on the first line\n2. **Clinical reasoning** — one sentence explaining why this is the\n   most likely diagnosis\n3. **Differential diagnosis** — exactly 3 to 5 items, each with one\n   sentence of supporting or refuting evidence\n4. **Risk stratification** — include a validated clinical score where\n   applicable (TIMI for ACS, GRACE for ACS, Killip class + Shock Index\n   for STEMI/cardiogenic shock, CURB-65 for pneumonia, qSOFA for sepsis,\n   Wells for PE, etc.). Killip class and Shock Index together are\n   accepted as sufficient risk stratification for STEMI/cardiogenic shock cases.\n\n### Step 5 — Write the management plan\n\nThe plan must be:\n\n- **Specific**: write drug names, doses, routes, and frequencies.\n  Do not write \"start antibiotics\" — write\n  \"Piperacillin-Tazobactam 4.5g IV q8h for 5 days\"\n- **Organised by problem** using numbered headers\n- **Evidence-based**: management must reflect current standard of care\n  for the diagnosis\n- **Complete**: include investigations to order, monitoring parameters,\n  consults to request, and disposition\n\nIf you are uncertain about a specific dose, write\n\"[drug name] — dose per local formulary/protocol\" rather than\ninventing a dose.\n\n### Important — Prescribing Safety\n\nGenerated plans must:\n- Be marked as educational/simulated, not a substitute for clinician judgment\n- Use \"per local formulary/protocol\" language when required patient variables\n  (weight, renal function, allergies) are missing from the brief\n- List key contraindications and unknowns before medication recommendations\n  when relevant patient data has not been provided\n- Never claim a plan is \"definitive\" or \"standard of care\" without full\n  patient context (allergy status, renal/hepatic function, pregnancy\n  status, weight, anticoagulation/bleeding risk)\n- Include a disclaimer footer in the HTML output stating the case is for\n  educational and documentation purposes only\n\n### Step 6 — Write `index.html`\n\nRequirements for the HTML output:\n\n- Professional medical document typography\n  (Georgia or system serif font preferred)\n- White background, dark text — suitable for printing\n- Vital signs and lab results in HTML `<table>` elements\n- Critical findings (ST elevation, raised troponin, low BP, etc.)\n  highlighted in a visually distinct callout box with red left border\n- @media print CSS rules so the document prints cleanly on A4/Letter\n- Tag every major section with `data-od-id` for comment-mode targeting:\n\n```html\n<section data-od-id=\"hpi\">...</section>\n<section data-od-id=\"vitals\">...</section>\n<section data-od-id=\"pmh\">...</section>\n<section data-od-id=\"examination\">...</section>\n<section data-od-id=\"investigations\">...</section>\n<section data-od-id=\"assessment\">...</section>\n<section data-od-id=\"plan\">...</section>\n```\n\n### Step 7 — Self-check against `references/checklist.md`\n\nBefore emitting `<artifact>`, run every P0 item in `references/checklist.md`.\nAll P0 items must pass. Fix any failures before emitting.","tags":["clinical","case","report","open","design","nexu-io","agent-skills","ai-agents","ai-design","byok","claude","claude-code-for-design"],"capabilities":["skill","source-nexu-io","skill-clinical-case-report","topic-agent-skills","topic-ai-agents","topic-ai-design","topic-byok","topic-claude","topic-claude-code-for-design","topic-claude-design","topic-coding-agents","topic-design-systems","topic-design-tools","topic-desktop-app","topic-figma-alternative"],"categories":["open-design"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/nexu-io/open-design/clinical-case-report","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add nexu-io/open-design","source_repo":"https://github.com/nexu-io/open-design","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 36607 github stars · SKILL.md body (7,839 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-11T06:52:18.829Z","embedding":null,"createdAt":"2026-05-08T18:52:34.939Z","updatedAt":"2026-05-11T06:52:18.829Z","lastSeenAt":"2026-05-11T06:52:18.829Z","tsv":"'-3':357 '-65':775 '/l':640 '0':93,225 '1':235,276,712 '100':537 '2':256,373,439,620,721 '3':149,503,734,738 '38':569 '4':703,751 '4.5':828 '5':150,740,802,833 '6':978 '7':1058 '90':539 'a4/letter':1041 'abnorm':622 'ac':763,766 'accept':792 'accur':25 'action':205,497 'activ':196,208,488,500 'admiss':183,347,475 'afebril':572 'age':99,179,288,397,470,550 'allergi':119,914,950 'alreadi':353 'alter':557 'antibiot':823 'anticoagulation/bleeding':957 'applic':760 'artifact':274 'ask':332 'assess':144,687,706,708 'associ':423 'atyp':674,683 'avail':354 'background':997 'base':31,161,250,843 'began':414 'beta':548 'beta-block':547 'blocker':549 'border':1030 'box':1026 'bp':1018 'brief':36,165,248,279,343,448,919 'build':374 'c':570 'call':176,459 'callout':1025 'canon':691 'capillari':543 'cardiolog':316 'care':850,945 'case':3,7,21,38,40,45,52,81,311,800,969 'chang':192,484 'characteris':418 'check':527,1061 'chief':101,291,323,367,411 'choos':240 'chronolog':108,435 'ck':605 'ck-mb':604 'claim':937 'clarifi':334 'class':768,786 'clean':1039 'clear':716 'clinic':2,10,44,55,153,305,376,392,507,722,757 'clinical-case-report':1 'clinician':900 'comment':1053 'comment-mod':1052 'compens':624 'complaint':102,292,324,368,412 'complet':854 'concis':204,496 'confer':12,57,95,246,310,331,380 'consist':506,522,526 'consult':861 'contain':711 'content':84 'context':255,306,315,949 'contigu':588 'continu':387 'contradict':698 'contraind':922 'convent':66,636 'correct':242 'creatinin':637 'critic':651,1011 'crp':567 'css':1033 'curb':774 'current':188,480,847 'daili':168,451 'dark':998 'data':508,657,931,1048 'data-od-id':1047 'day':181,356,472,834 'definit':941 'diagnosi':146,525,677,701,714,733,736,853 'differenti':148,735 'direct':364 'disclaim':961 'disposit':865 'distinct':1024 'document':14,59,974,988,1037 'dose':815,873,877,885 'drug':813,875 'e.g':355 'earli':597,625 'ed':307 'educ':972 'educational/simulated':895 'elder':578 'element':1010 'elev':586,1014 'emerg':317 'emit':271,1065,1081 'especi':575 'etc':313,320,784,1019 'event':187,479 'everi':1043,1067 'evid':30,160,750,842 'evidence-bas':29,159,841 'exact':737 'examin':124,215,465 'exist':574 'explain':726 'explicit':665 'extract':286 'failur':1079 'file':228,234 'final':273 'find':126,143,1012 'first':719 'fix':1077 'flag':137 'follow':62 'font':994 'footer':962 'forc':690 'format':18,65,87,96,131,167,244 'formulary/protocol':880,905 'frequenc':818 'full':210,462,947 'function':913,953 'g':829 'g/dl':650 'gate':260 'generat':15,48,504,517,694,889 'georgia':990 'glucos':645 'grace':764 'haemoglobin':648 'handov':172,455 'header':840 'high':593 'high-sensit':592 'highlight':1020 'histori':103,117,404 'hospit':69 'hour':440 'hpi':107,211,384,432,463 'hr':536 'html':80,965,984,1009,1056 'icu':173,358,456 'id':177,350,468,1050 'identif':98 'ill':106 'imag':142,300 'immunocompromis':580 'impair':542 'import':886 'includ':218,425,429,436,754,855,959 'index':770,789 'index.html':83,980 'initi':601 'instead':466 'intern':318,521 'interv':186,478 'invent':883 'investig':138,856 'item':151,269,741,1069,1074 'iv':830 'judgment':901 'keep':258,678 'key':921 'killip':767,785 'lab':27,298,632,1006 'laboratori':139 'lactat':541,619 'languag':906 'last':194,486 'lead':589 'left':1029 'like':732 'line':178,351,469,720 'list':199,426,430,491,920 'load':226 'local':879,904 'low':616,1017 'major':1044 'manag':157,805,844 'mark':893 'marker':438 'match':635 'may':599,627 'mb':606 'media':1031 'medic':6,51,64,116,118,546,926,987 'medicin':319 'mention':37 'mg/dl':642 'mind':262 'miss':329,916 'mmol/l':647 'mode':1054 'monitor':859 'morn':446 'must':265,433,634,710,809,845,891,1075 'n':473 'name':814,876 'narrat':20,109,377,389 'negat':114,428 'neurogen':554 'never':658,693,936 'normal':602,630 'note':681 'number':198,490,692,839 'od':1049 'old':400 'one':333,724,744 'onset':444 'order':858 'organis':162,835 'outpati':312 'output':61,243,381,450,966,985 'overwrit':659 'p0':259,268,1068,1073 'page':79 'paramet':860 'pars':277 'pass':266,1076 'past':115 'patient':97,287,531,909,930,948 'pattern':529,559 'pe':783 'per':878,903 'pertin':111,427 'physic':123,214 'physiolog':24,505 'piperacillin':826 'piperacillin-tazobactam':825 'plan':32,158,201,493,806,808,890,939 'plan-by-problem':200,492 'pmh':407 'pneumonia':560,573,777 'posit':112 'post':175,458 'post-cal':174,457 'prefer':995 'pregnanc':954 'prescrib':887 'present':8,41,53,105,294,326,409,443,562,598,628,684 'preserv':653 'primari':145,184,476,713 'print':1002,1032,1038 'prior':441 'problem':164,185,197,203,209,295,327,348,477,489,495,501,837 'proceed':337,340,363 'produc':75,467 'profession':986 'prompt':284 'prose':388 'provid':304,514,656,671,935 'purpos':975 'q8h':831 'qsofa':778 'qualiti':420 'question':335 'radiat':422 'rais':540,564,566,591,614,618,1015 'rang':135 'rather':688,881 'read':231,280 'reason':154,723 'recommend':927 'red':1028 'refer':134,227,233 'references/case-formats.md':89,236 'references/checklist.md':257,1063,1071 'refil':544 'reflect':846 'refut':749 'relev':406,929 'renal':912 'renal/hepatic':952 'report':4,22,39,46,82 'request':863 'requir':371,610,908,981 'result':140,1007 'review':120,169,195,359,452,487 'risk':752,795,958 'round':11,56,166,171,249,309,344,449,454 'rout':816 'rule':652,1034 'run':1066 'safeti':888 'sbp':538 'score':758 'section':709,1045 'see':88 'select':90 'self':1060 'self-check':1059 'sensit':594 'sentenc':725,745 'separ':366 'sepsi':611,626,780 'septic':361 'serif':993 'set':70 'sever':421 'sex':100,180,290,401,471 'shock':362,533,552,769,773,788,799 'show':584,613 'sign':130,1004 'sinc':193,485 'singl':78 'single-pag':77 'skill':47 'skill-clinical-case-report' 'skip':460 'soap':17,42,94,245,330,379 'soap-format':16 'source-nexu-io' 'specialti':314 'specif':515,811,872 'spinal':555 'st':585,1013 'standard':63,391,848,943 'start':230,822 'state':643,666,700,715,967 'status':189,481,951,955 'stemi':582 'stemi/cardiogenic':772,798 'step':92,220,222,224,275,372,502,702,801,977,1057 'step-by-step':219 'stratif':753,796 'structur':5,50 'style':393 'substitut':898 'suffici':794 'suitabl':1000 'support':747 'symptom':413,424 'system':122,128,992 'systemat':125,213 'tabl':132 'tag':1042 'target':1055 'tazobactam':827 'temperatur':568,621 'text':999 'throughout':263 'timelin':415,437 'timi':761 'togeth':790 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-design' 'topic-byok' 'topic-claude' 'topic-claude-code-for-design' 'topic-claude-design' 'topic-coding-agents' 'topic-design-systems' 'topic-design-tools' 'topic-desktop-app' 'topic-figma-alternative' 'troponin':595,603,1016 'type':553 'typic':528,534,561,583,612 'typographi':989 'uncertain':869 'unit':633 'univers':609 'unknown':924 'use':33,67,237,838,902 'user':253,282,302,511,655,663,670 'user-provid':654,669 'valid':756 'valu':516,518,661,672,696 'vari':85 'variabl':910 'visual':1023 'vital':26,129,297,631,1003 'ward':170,308,453 'wbc':565,617 'weight':911,956 'well':781 'white':996 'without':341,946 'workflow':223 'worldwid':71 'write':382,704,803,812,821,824,874,979 'year':399 'year-old':398 'yesterday':445 'µmol':639","prices":[{"id":"d1a9687d-5cff-48b3-8374-1cb35dab2ad3","listingId":"bf31e267-fa30-46e5-8e82-6e3584addd21","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"nexu-io","category":"open-design","install_from":"skills.sh"},"createdAt":"2026-05-08T18:52:34.939Z"}],"sources":[{"listingId":"bf31e267-fa30-46e5-8e82-6e3584addd21","source":"github","sourceId":"nexu-io/open-design/clinical-case-report","sourceUrl":"https://github.com/nexu-io/open-design/tree/main/skills/clinical-case-report","isPrimary":false,"firstSeenAt":"2026-05-08T18:52:34.939Z","lastSeenAt":"2026-05-11T06:52:18.829Z"}],"details":{"listingId":"bf31e267-fa30-46e5-8e82-6e3584addd21","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"nexu-io","slug":"clinical-case-report","github":{"repo":"nexu-io/open-design","stars":36607,"topics":["agent-skills","ai-agents","ai-design","byok","claude","claude-code-for-design","claude-design","coding-agents","design-systems","design-tools","desktop-app","figma-alternative","generative-ai","hermes-agent","local-first","nextjs","no-code","prototyping","ui-generator","vibe-coding"],"license":"apache-2.0","html_url":"https://github.com/nexu-io/open-design","pushed_at":"2026-05-11T06:48:43Z","description":"🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Runs on Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen / Copilot / Hermes / Kimi CLI.","skill_md_sha":"cd32be08da85b6cd0d064aa3215d01732eeff91d","skill_md_path":"skills/clinical-case-report/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/nexu-io/open-design/tree/main/skills/clinical-case-report"},"layout":"multi","source":"github","category":"open-design","frontmatter":{"name":"clinical-case-report","description":"Structured medical case presentation for clinical rounds, conferences,\nand documentation. Generates SOAP-format or narrative case reports\nwith physiologically accurate vitals, labs, and evidence-based plans.\nUse when the brief mentions \"case report\", \"case presentation\", \"SOAP note\",\n\"clinical case\", \"ward rounds\", \"case summary\", or \"patient presentation\"."},"skills_sh_url":"https://skills.sh/nexu-io/open-design/clinical-case-report"},"updatedAt":"2026-05-11T06:52:18.829Z"}}