{"id":"64ec332a-282a-4634-8809-72e0c72f557d","shortId":"yag9kJ","kind":"skill","title":"setup-medsci","tagline":"Diagnostic checklist for the MedSci Skills runtime. Verifies Python, R, Node, Claude Code, Git, Zotero, and configured MCP servers, and prints a pass/fail table with links to the right setup doc for any missing component. Read-only — does not install anything.","description":"# Setup-MedSci Skill\n\nYou are helping a medical researcher verify that their environment is correctly configured to run MedSci Skills. You **do not install anything** — you only diagnose what's present, what's missing, and where to find the setup doc for any missing component. This skill is intentionally read-only so that a doctor can run it safely without worrying about breaking their system.\n\n## Communication Rules\n\n- Communicate with the user in their preferred language (Korean or English).\n- The diagnostic table itself is in English so it can be pasted into GitHub issues for support.\n- All recommended remediation links point to `docs/setup/` markdown guides in the medsci-skills repo.\n\n## Workflow\n\n### Phase 1: Detect OS\n\nRun:\n```bash\nuname -s\n```\n\n- `Darwin` → macOS path → recommend `docs/setup/mac.md`\n- `Linux` → Linux path (uses similar tooling to Mac) → recommend `docs/setup/mac.md`\n- `MINGW*`, `MSYS*`, `CYGWIN*`, or detection failure on Windows → recommend `docs/setup/windows.md`\n\n### Phase 2: Run Diagnostic Commands\n\nFor each tool, run the command and capture both the version output and the exit code:\n\n| Tool | Command | Required version |\n|---|---|---|\n| Python | `python3 --version` (Mac/Linux) or `python --version` (Windows) | 3.11 or higher |\n| R | `Rscript --version` (writes to stderr) | 4.0 or higher |\n| Node.js | `node --version` | v20 or higher |\n| Git | `git --version` | 2.30 or higher |\n| Claude Code CLI | `claude --version` | any |\n| MCP servers | `claude mcp list` | at least one of: zotero, gdrive, pubmed, filesystem |\n\nUse `command -v <tool>` first to detect presence without running it (avoids triggering long initialization).\n\n### Phase 3: Emit Checklist Table\n\nPrint a single Markdown table to stdout in this exact format:\n\n```\n## MedSci Skills Setup Diagnostic\n\nOS detected: <macOS | Linux | Windows>\nDate: <YYYY-MM-DD>\n\n| Component | Status | Detected | Required | Action |\n|---|:---:|---|---|---|\n| Python 3.11+ | ✅ / ❌ | 3.11.9 | 3.11+ | OK / See docs/setup/mac.md Step 2 |\n| R 4.x | ✅ / ❌ | 4.3.1 | 4.0+ | OK / See docs/setup/mac.md Step 3 |\n| Node.js 20+ | ✅ / ❌ | v20.11.1 | v20+ | OK / See docs/setup/mac.md Step 4 |\n| Git | ✅ / ❌ | 2.42.0 | 2.30+ | OK / See docs/setup/<os>.md Step 5 |\n| Claude Code CLI | ✅ / ❌ | 1.5.x | any | OK / See docs/setup/<os>.md Step 6 |\n| MCP: zotero | ✅ / ❌ / ⚠️ | Connected | optional | OK / See docs/setup/mcp-setup.md |\n| MCP: gdrive | ✅ / ❌ / ⚠️ | Connected | optional | OK / See docs/setup/mcp-setup.md |\n| MCP: filesystem | ✅ / ❌ | Connected | recommended | OK / See docs/setup/mcp-setup.md |\n\nSummary: <X required components passed, Y missing>\nNext step: <one-sentence action>\n```\n\nStatus legend:\n- ✅ Present and meets minimum version\n- ❌ Missing or below minimum version\n- ⚠️ Present but optional and not connected\n\n### Phase 4: Suggest Remediation\n\nIf everything ✅: \"Your environment is ready. Try Demo 1 with `cd ~/medsci-skills/demo/01_wisconsin_bc && claude '/orchestrate --e2e'`.\"\n\nIf anything ❌ in **required** rows: print the corresponding doc link. Do **not** offer to install — direct the user to follow the doc step. The doc tells them exactly what to copy-paste.\n\nIf only **optional MCP** rows are ❌: explain that MedSci Skills work without MCP servers but `lit-sync`, `verify-refs`, and `write-paper` are smoother with Zotero MCP. Offer the `docs/setup/mcp-setup.md` link.\n\n## Reference Files\n\n- `references/setup-checklist.md` — verbatim list of every check this skill runs and the corresponding documentation link\n\n## Output Contract\n\n| Artifact | Filename | Format |\n|----------|----------|--------|\n| Diagnostic report | stdout (Markdown table) | Markdown |\n| Optional log | `~/.medsci-skills/diagnostic-YYYY-MM-DD.md` | Markdown |\n\nIf the user asks for a copyable report (e.g., for a GitHub issue), write the diagnostic to the optional log path and tell them where it is.\n\n## What This Skill Does NOT Do\n\n- **Does not install anything.** No `brew install`, `winget install`, `pip install`, `Rscript -e 'install.packages(...)'`, or any other state-changing command. Read-only diagnostics only.\n- **Does not modify `~/.claude.json` or any MCP configuration.** It only reads `claude mcp list` output.\n- **Does not check skill versions or skill content.** That is the job of `validate_skills.sh` and `manage-project status`.\n- **Does not auto-fix anything.** If a tool is missing, the user must go to the setup doc and follow the steps themselves. This is intentional — auto-installers for system Python and R are a support nightmare for non-developer users.\n\n## Anti-Hallucination\n\n- **Never fabricate version numbers.** Always run the actual command and report the exact stdout. If the command fails, report the failure verbatim — do not guess what version is \"probably\" installed.\n- **Never invent doc paths.** The five setup docs are: `docs/setup/README.md`, `docs/setup/mac.md`, `docs/setup/windows.md`, `docs/setup/mcp-setup.md`, `docs/setup/common-issues.md`. Do not link to a doc that does not exist in the repo.\n- **Never claim an MCP server works without verifying via `claude mcp list`.** A configured-but-disconnected server is ⚠️, not ✅.\n- **If `command -v` reports a tool present but the version flag fails**, mark the row ❌ and report the failure command — the install is broken, not just outdated.","tags":["setup","medsci","skills","aperivue","agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol","literature-review"],"capabilities":["skill","source-aperivue","skill-setup-medsci","topic-agent-skills","topic-biostatistics","topic-claude-code","topic-claude-skills","topic-clinical-research","topic-diagnostic-accuracy","topic-irb-protocol","topic-literature-review","topic-manuscript","topic-medical-ai","topic-medical-research","topic-meta-analysis"],"categories":["medsci-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Aperivue/medsci-skills/setup-medsci","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Aperivue/medsci-skills","source_repo":"https://github.com/Aperivue/medsci-skills","install_from":"skills.sh"}},"qualityScore":"0.499","qualityRationale":"deterministic score 0.50 from registry signals: · indexed on github topic:agent-skills · 98 github stars · SKILL.md body (5,322 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":"2026-05-18T18:56:31.795Z","embedding":null,"createdAt":"2026-05-13T12:57:46.790Z","updatedAt":"2026-05-18T18:56:31.795Z","lastSeenAt":"2026-05-18T18:56:31.795Z","tsv":"'/.claude.json':589 '/.medsci-skills/diagnostic-yyyy-mm-dd.md':525 '/medsci-skills/demo/01_wisconsin_bc':425 '/orchestrate':427 '1':160,422 '1.5':353 '2':193,321 '2.30':246,343 '2.42.0':342 '20':333 '3':283,331 '3.11':225,314,316 '3.11.9':315 '4':323,340,411 '4.0':234,326 '4.3.1':325 '5':349 '6':361 'action':312 'actual':674 'alway':671 'anti':665 'anti-hallucin':664 'anyth':45,71,430,563,625 'artifact':514 'ask':530 'auto':623,648 'auto-fix':622 'auto-instal':647 'avoid':278 'bash':164 'break':110 'brew':565 'broken':767 'captur':204 'cd':424 'chang':579 'check':503,603 'checklist':5,285 'claim':725 'claud':15,249,252,257,350,426,597,733 'cli':251,352 'code':16,212,250,351 'command':196,202,214,269,580,675,683,745,763 'communic':113,115 'compon':38,91,308,386 'configur':20,62,593,738 'configured-but-disconnect':737 'connect':364,371,378,409 'content':608 'contract':513 'copi':460 'copy-past':459 'copyabl':533 'correct':61 'correspond':436,509 'cygwin':184 'darwin':167 'date':307 'demo':421 'detect':161,186,273,303,310 'develop':662 'diagnos':74 'diagnost':4,127,195,301,517,542,584 'direct':444 'disconnect':740 'doc':34,87,437,450,453,638,699,704,716 'docs/setup':149,346,358 'docs/setup/common-issues.md':710 'docs/setup/mac.md':171,181,319,329,338,707 'docs/setup/mcp-setup.md':368,375,382,494,709 'docs/setup/readme.md':706 'docs/setup/windows.md':191,708 'doctor':102 'document':510 'e':572 'e.g':535 'e2e':428 'emit':284 'english':125,132 'environ':59,417 'everi':502 'everyth':415 'exact':296,456,679 'exist':720 'exit':211 'explain':468 'fabric':668 'fail':684,755 'failur':187,687,762 'file':497 'filenam':515 'filesystem':267,377 'find':84 'first':271 'five':702 'fix':624 'flag':754 'follow':448,640 'format':297,516 'gdrive':265,370 'git':17,243,244,341 'github':139,538 'go':634 'guess':691 'guid':151 'hallucin':666 'help':52 'higher':227,236,242,248 'initi':281 'instal':44,70,443,562,566,568,570,649,696,765 'install.packages':573 'intent':95,646 'invent':698 'issu':140,539 'job':612 'korean':123 'languag':122 'least':261 'legend':393 'link':29,146,438,495,511,713 'linux':172,173,305 'list':259,500,599,735 'lit':478 'lit-sync':477 'log':524,546 'long':280 'mac':179 'mac/linux':220 'maco':168,304 'manag':617 'manage-project':616 'mark':756 'markdown':150,290,520,522,526 'mcp':21,255,258,362,369,376,465,474,491,592,598,727,734 'md':347,359 'medic':54 'medsci':3,8,48,65,155,298,470 'medsci-skil':154 'meet':396 'mingw':182 'minimum':397,402 'miss':37,80,90,389,399,630 'modifi':588 'msys':183 'must':633 'never':667,697,724 'next':390 'nightmar':658 'node':14,238 'node.js':237,332 'non':661 'non-develop':660 'number':670 'offer':441,492 'ok':317,327,336,344,356,366,373,380 'one':262 'option':365,372,406,464,523,545 'os':162,302 'outdat':770 'output':208,512,600 'paper':486 'pass':387 'pass/fail':26 'past':137,461 'path':169,174,547,700 'phase':159,192,282,410 'pip':569 'point':147 'prefer':121 'presenc':274 'present':77,394,404,750 'print':24,287,434 'probabl':695 'project':618 'pubm':266 'python':12,217,222,313,652 'python3':218 'r':13,228,322,654 'read':40,97,582,596 'read-on':39,96,581 'readi':419 'recommend':144,170,180,190,379 'ref':482 'refer':496 'references/setup-checklist.md':498 'remedi':145,413 'repo':157,723 'report':518,534,677,685,747,760 'requir':215,311,385,432 'research':55 'right':32 'row':433,466,758 'rscript':229,571 'rule':114 'run':64,104,163,194,200,276,506,672 'runtim':10 'safe':106 'see':318,328,337,345,357,367,374,381 'server':22,256,475,728,741 'setup':2,33,47,86,300,637,703 'setup-medsci':1,46 'similar':176 'singl':289 'skill':9,49,66,93,156,299,471,505,556,604,607 'skill-setup-medsci' 'smoother':488 'source-aperivue' 'state':578 'state-chang':577 'status':309,392,619 'stderr':233 'stdout':293,519,680 'step':320,330,339,348,360,391,451,642 'suggest':412 'summari':383 'support':142,657 'sync':479 'system':112,651 'tabl':27,128,286,291,521 'tell':454,549 'tool':177,199,213,628,749 'topic-agent-skills' 'topic-biostatistics' 'topic-claude-code' 'topic-claude-skills' 'topic-clinical-research' 'topic-diagnostic-accuracy' 'topic-irb-protocol' 'topic-literature-review' 'topic-manuscript' 'topic-medical-ai' 'topic-medical-research' 'topic-meta-analysis' 'tri':420 'trigger':279 'unam':165 'use':175,268 'user':118,446,529,632,663 'v':270,746 'v20':240,335 'v20.11.1':334 'validate_skills.sh':614 'verbatim':499,688 'verifi':11,56,481,731 'verify-ref':480 'version':207,216,219,223,230,239,245,253,398,403,605,669,693,753 'via':732 'window':189,224,306 'winget':567 'without':107,275,473,730 'work':472,729 'workflow':158 'worri':108 'write':231,485,540 'write-pap':484 'x':324,354,384 'y':388 'zotero':18,264,363,490","prices":[{"id":"77307038-da38-43a1-b980-a045f2b5cabc","listingId":"64ec332a-282a-4634-8809-72e0c72f557d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Aperivue","category":"medsci-skills","install_from":"skills.sh"},"createdAt":"2026-05-13T12:57:46.790Z"}],"sources":[{"listingId":"64ec332a-282a-4634-8809-72e0c72f557d","source":"github","sourceId":"Aperivue/medsci-skills/setup-medsci","sourceUrl":"https://github.com/Aperivue/medsci-skills/tree/main/skills/setup-medsci","isPrimary":false,"firstSeenAt":"2026-05-13T12:57:46.790Z","lastSeenAt":"2026-05-18T18:56:31.795Z"}],"details":{"listingId":"64ec332a-282a-4634-8809-72e0c72f557d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Aperivue","slug":"setup-medsci","github":{"repo":"Aperivue/medsci-skills","stars":98,"topics":["agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol","literature-review","manuscript","medical-ai","medical-research","meta-analysis","physician-researcher","prisma","pubmed","radiology","reporting-guidelines","strobe","systematic-review","tripod-ai"],"license":"other","html_url":"https://github.com/Aperivue/medsci-skills","pushed_at":"2026-05-17T20:50:52Z","description":"Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication figures. Built by a physician-researcher, tested on real publications. MIT licensed.","skill_md_sha":"d68a76cfd2bc97d1733b33159063c596c38c1af6","skill_md_path":"skills/setup-medsci/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Aperivue/medsci-skills/tree/main/skills/setup-medsci"},"layout":"multi","source":"github","category":"medsci-skills","frontmatter":{"name":"setup-medsci","description":"Diagnostic checklist for the MedSci Skills runtime. Verifies Python, R, Node, Claude Code, Git, Zotero, and configured MCP servers, and prints a pass/fail table with links to the right setup doc for any missing component. Read-only — does not install anything."},"skills_sh_url":"https://skills.sh/Aperivue/medsci-skills/setup-medsci"},"updatedAt":"2026-05-18T18:56:31.795Z"}}