{"id":"c6e97629-1a57-4e71-9131-4c5a13bdc194","shortId":"z9AR2Y","kind":"skill","title":"intake-project","tagline":"Intake and normalize a new radiology research project. Classifies project type, summarizes current state, identifies missing inputs, recommends next steps, and scaffolds lightweight project memory files.","description":"# Intake-Project Skill\n\n## Purpose\n\nThis skill is the front door for a new or messy project. It converts a folder, document bundle, or mixed set of notes into a structured project state that other skills can use safely.\n\nUse this skill when:\n- a new paper or proposal folder has been created\n- an older folder exists but is poorly organized\n- the user asks \"what is this project and what should I do next?\"\n- another skill needs a reliable project summary before proceeding\n\n---\n\n## Communication Rules\n\n- Communicate with the user in their preferred language.\n- Keep project labels and file names in the language already used by the workspace.\n- Use English for manuscript section names, study design names, and medical/statistical terminology.\n\n---\n\n## Inputs\n\nAccept any of the following:\n- a project folder\n- a manuscript draft\n- an abstract or proposal\n- tables/figures plus notes\n- a mixed folder with PDFs, drafts, and analyses\n\nIf information is incomplete, infer cautiously from file names and contents, then label uncertain items clearly.\n\n---\n\n## Core Tasks\n\n### 1. Project classification\n\nDetermine:\n- project type: `original | review | meta-analysis | case report | technical note | grant | peer review | challenge | career-doc`\n- primary domain: `radiology | medical AI | multimodal LLM | intervention | survival/prognostic | diagnostic accuracy | workflow`\n- target output: `paper | abstract | grant | review | rebuttal | CV`\n- likely target journal or venue, if recoverable\n\n### 2. State reconstruction\n\nIdentify:\n- what already exists\n- what is missing\n- current phase\n- blocking dependencies\n\n### 3. Project memory scaffold\n\nIf missing, propose or create lightweight anchor files:\n- `PROJECT.md`\n- `STATUS.md`\n- `CLAIMS.md`\n- `DATA_DICTIONARY.md`\n- `ANALYSIS_PLAN.md`\n- `REVIEW_LOG.md`\n\nCreate only files that are justified by the project type.\n\n### 4. Action plan\n\nProduce the next 3-5 actions in dependency order.\n\n---\n\n## Canonical Manuscript Folder Structure\n\nFor any manuscript project (cohort, MA, RCT, case series), enforce this structure when scaffolding or reorganizing. Map every new artifact into one of these slots — do not invent ad-hoc folders.\n\n```\n{project_root}/\n├── HANDOFF.md                         # session handoff entry point\n├── README.md                          # project overview\n├── data/                              # raw data (NEVER edit; read-only)\n├── analysis/                          # reproducible scripts (00_* → 04_*)\n├── output/                            # analysis outputs: CSVs, PNGs, intermediates\n├── irb/                               # IRB/ethics docs\n├── proposal/                          # original protocol / approved proposal\n├── reviews/                           # external correspondence\n├── manuscript/                        # SOURCE manuscript + drafting\n│   ├── manuscript_v{N}.{md,docx,pdf}  # current canonical working version (top level)\n│   ├── build_unified_docx.py          # or pandoc wrapper\n│   ├── archive/                       # ALL prior versions v1 .. v{N-1}\n│   ├── reviews/                       # QC: self_review, peer_review, STROBE/PRISMA, critic\n│   ├── figures/                       # figure scripts + rendered PNG/PDF\n│   └── tables/                        # table scripts + rendered docx\n└── submission/                        # per-journal packages\n    └── {journal-slug}/                # e.g., chest/, kjr/\n        ├── CHECKLIST.md\n        ├── cover_letter.{md,docx,pdf}\n        ├── title_page.docx            # separated for double-anonymized\n        ├── manuscript_anonymized.{docx,pdf}\n        ├── supplement.{docx,pdf}\n        ├── strobe_checklist.md        # or PRISMA / CONSORT\n        ├── circulation_email.md\n        └── figures/                   # submission-ready DPI copies\n```\n\n### Rules\n\n- **`manuscript/` = source; `submission/{journal}/` = derived artifacts.** Regenerate submission files from `manuscript/manuscript_v{N}.md`; never edit anonymized/title-page directly.\n- **One canonical working version** at `manuscript/manuscript_v{N}.{md,docx,pdf}`. Older versions move to `manuscript/archive/` immediately on version bump.\n- **No loose files at project root.** Only `HANDOFF.md`, `README.md`, folder entries.\n- **QC artifacts** (self_review, peer_review, STROBE, critic reports) live in `manuscript/reviews/`, not at manuscript top level.\n- **On rejection/retarget:** `cp -r submission/{old} submission/{new}`, then rewrite cover letter and reformat.\n- **Double-anonymized journals** (Chest, AJRCCM): title page and anonymized manuscript MUST be separate files under `submission/{journal}/`.\n\n### When to apply\n\n- At project intake: scaffold empty structure.\n- At first submission prep: create `submission/{journal}/` and populate.\n- Mid-project cleanup: when `manuscript/` has >3 versioned files or QC docs at top level, reorganize.\n- Before session handoff: reorganize if structure is drifting.\n\n**Precedent:** an STROBE cohort with a mortality endpoint reorganized v1–v6 plus QC docs from the manuscript/ top level so that a reject-retarget path to a different journal requires only `cp -r submission/chest submission/<new_journal>`.\n\n---\n\n## Workflow\n\n### Phase 1: Discover context\n\n1. Read top-level folder names and key files.\n2. Detect manuscript-like files, tables, figures, protocols, and analysis outputs.\n3. Extract:\n   - project title or working title\n   - study question\n   - dataset or cohort hints\n   - collaborators or institutions\n   - venue/journal hints\n\n### Phase 2: Classify project stage\n\nAssign one current stage:\n- `idea`\n- `data assembly`\n- `analysis planning`\n- `analysis in progress`\n- `drafting`\n- `revision`\n- `submission prep`\n- `archived/unclear`\n\n**Gate:** Present the classification (project type, stage, target output) to the user.\nConfirm before creating any files — misclassification leads to wrong scaffold and\nwrong skill routing.\n\n### Phase 3: Surface missing inputs\n\nCheck for common gaps:\n- no explicit study question\n- no target journal\n- no analysis plan\n- no variable dictionary\n- no claims-to-results map\n- no review log for revised manuscripts\n\n### Phase 4: Produce normalized summary\n\nOutput this structure:\n\n```text\n## Project Intake Summary\nProject: ...\nType: ...\nCurrent stage: ...\nLikely target: ...\n\n### What exists\n- ...\n\n### What is missing\n- ...\n\n### Risks / ambiguities\n- ...\n\n### Recommended next actions\n1. ...\n2. ...\n3. ...\n```\n\n---\n\n## Optional File Templates\n\n### `PROJECT.md`\n\n```md\n# PROJECT\n\n- Title:\n- Type:\n- Primary question:\n- Target journal/venue:\n- Lead folder:\n- Collaborators:\n- Last updated:\n```\n\n### `STATUS.md`\n\n```md\n# STATUS\n\n- Current stage:\n- Current blocker:\n- Next actions:\n  1.\n  2.\n  3.\n- Last updated:\n```\n\n---\n\n## Guardrails\n\n- Do not invent data values, outcomes, or collaborator roles.\n- Do not assume a target journal unless evidence exists in the files.\n- Do not create a large folder scaffold when the user only wants a quick assessment.\n- If a project appears to mix multiple studies, say so explicitly rather than collapsing them into one.\n\n---\n\n## Handoff Rules\n\nAfter intake:\n- route to `search-lit` if the literature basis is weak\n- route to `design-study` if the research question exists but design logic is unclear\n- route to `manage-project` if the folder should be scaffolded\n- route to `write-paper` only after the project phase is clearly `drafting`\n\n---\n\n## What This Skill Does NOT Do\n\n- It does not write full manuscript sections\n- It does not perform statistical analysis\n- It does not verify citations deeply\n- It does not replace study design review\n\n## Anti-Hallucination\n\n- **Never fabricate file paths, URLs, DOIs, or package names.** Verify existence before recommending.\n- **Never invent journal metadata, impact factors, or submission policies** without verification at the journal's website.\n- If a tool, package, or resource does not exist or you are unsure, say so explicitly rather than guessing.","tags":["intake","project","medsci","skills","aperivue","agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol"],"capabilities":["skill","source-aperivue","skill-intake-project","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/intake-project","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 (7,937 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":"2026-05-18T18:56:30.157Z","embedding":null,"createdAt":"2026-05-13T12:57:45.183Z","updatedAt":"2026-05-18T18:56:30.157Z","lastSeenAt":"2026-05-18T18:56:30.157Z","tsv":"'-1':399 '-5':291 '00':353 '04':354 '1':193,637,640,790,819 '2':242,650,681,791,820 '3':256,290,581,662,729,792,821 '4':284,763 'abstract':161,230 'accept':149 'accuraci':225 'action':285,292,789,818 'ad':329 'ad-hoc':328 'ai':219 'ajrccm':543 'alreadi':131,247 'ambigu':786 'analys':174 'analysi':203,350,356,660,692,694,745,950 'analysis_plan.md':272 'anchor':266 'anonym':440,442,540,547 'anonymized/title-page':475 'anoth':103 'anti':965 'anti-hallucin':964 'appear':864 'appli':558 'approv':367 'archiv':392 'archived/unclear':701 'artifact':319,465,508 'ask':92 'assembl':691 'assess':860 'assign':685 'assum':836 'basi':890 'block':254 'blocker':816 'build_unified_docx.py':388 'bump':495 'bundl':52 'canon':296,383,478 'career':213 'career-doc':212 'case':204,307 'cautious':180 'challeng':211 'check':733 'checklist.md':429 'chest':427,542 'circulation_email.md':452 'citat':955 'claim':752 'claims-to-result':751 'claims.md':270 'classif':195,705 'classifi':12,682 'cleanup':577 'clear':190,930 'cohort':304,602,673 'collabor':675,807,832 'collaps':874 'common':735 'communic':112,114 'confirm':714 'consort':451 'content':185 'context':639 'convert':48 'copi':458 'core':191 'correspond':371 'cover':430,534 'cp':526,631 'creat':81,264,274,569,716,848 'critic':407,514 'csvs':358 'current':16,252,382,687,776,813,815 'cv':234 'data':342,344,690,828 'data_dictionary.md':271 'dataset':671 'deepli':956 'depend':255,294 'deriv':464 'design':143,896,904,962 'design-studi':895 'detect':651 'determin':196 'diagnost':224 'dictionari':749 'differ':627 'direct':476 'discov':638 'doc':214,363,586,612 'document':51 'docx':380,417,433,443,446,485 'doi':972 'domain':216 'door':40 'doubl':439,539 'double-anonym':438,538 'dpi':457 'draft':159,172,375,697,931 'drift':598 'e.g':426 'edit':346,474 'empti':563 'endpoint':606 'enforc':309 'english':137 'entri':337,506 'everi':317 'evid':841 'exist':85,248,781,842,902,977,1004 'explicit':738,871,1011 'extern':370 'extract':663 'fabric':968 'factor':985 'figur':408,409,453,657 'file':29,126,182,267,276,468,498,552,583,649,655,718,794,845,969 'first':566 'folder':50,78,84,156,169,298,331,505,645,806,851,915 'follow':153 'front':39 'full':942 'gap':736 'gate':702 'grant':208,231 'guardrail':824 'guess':1014 'hallucin':966 'handoff':336,593,878 'handoff.md':334,503 'hint':674,679 'hoc':330 'idea':689 'identifi':18,245 'immedi':492 'impact':984 'incomplet':178 'infer':179 'inform':176 'input':20,148,732 'institut':677 'intak':2,4,31,561,772,881 'intake-project':1,30 'intermedi':360 'intervent':222 'invent':327,827,981 'irb':361 'irb/ethics':362 'item':189 'journal':237,421,424,463,541,555,571,628,743,839,982,993 'journal-slug':423 'journal/venue':804 'justifi':279 'keep':122 'key':648 'kjr':428 'label':124,187 'languag':121,130 'larg':850 'last':808,822 'lead':720,805 'letter':431,535 'level':387,523,589,617,644 'lightweight':26,265 'like':235,654,778 'lit':886 'literatur':889 'live':516 'llm':221 'log':758 'logic':905 'loos':497 'ma':305 'manag':911 'manage-project':910 'manuscript':139,158,297,302,372,374,376,441,460,521,548,579,615,653,761,943 'manuscript-lik':652 'manuscript/archive':491 'manuscript/manuscript_v':470,482 'manuscript/reviews':518 'map':316,755 'md':379,432,472,484,797,811 'medic':218 'medical/statistical':146 'memori':28,258 'messi':45 'meta':202 'meta-analysi':201 'metadata':983 'mid':575 'mid-project':574 'misclassif':719 'miss':19,251,261,731,784 'mix':54,168,866 'mortal':605 'move':489 'multimod':220 'multipl':867 'must':549 'n':378,398,471,483 'name':127,141,144,183,646,975 'need':105 'never':345,473,967,980 'new':8,43,74,318,531 'next':22,102,289,788,817 'normal':6,765 'note':57,166,207 'old':529 'older':83,487 'one':321,477,686,877 'option':793 'order':295 'organ':89 'origin':199,365 'outcom':830 'output':228,355,357,661,710,767 'overview':341 'packag':422,974,999 'page':545 'pandoc':390 'paper':75,229,923 'path':624,970 'pdf':381,434,444,447,486 'pdfs':171 'peer':209,404,511 'per':420 'per-journ':419 'perform':948 'phase':253,636,680,728,762,928 'plan':286,693,746 'plus':165,610 'png/pdf':412 'pngs':359 'point':338 'polici':988 'poor':88 'popul':573 'preced':599 'prefer':120 'prep':568,700 'present':703 'primari':215,801 'prior':394 'prisma':450 'proceed':111 'produc':287,764 'progress':696 'project':3,11,13,27,32,46,61,96,108,123,155,194,197,257,282,303,332,340,500,560,576,664,683,706,771,774,798,863,912,927 'project.md':268,796 'propos':77,163,262,364,368 'protocol':366,658 'purpos':34 'qc':401,507,585,611 'question':670,740,802,901 'quick':859 'r':527,632 'radiolog':9,217 'rather':872,1012 'raw':343 'rct':306 'read':348,641 'read-on':347 'readi':456 'readme.md':339,504 'rebutt':233 'recommend':21,787,979 'reconstruct':244 'recover':241 'reformat':537 'regener':466 'reject':622 'reject-retarget':621 'rejection/retarget':525 'reliabl':107 'render':411,416 'reorgan':315,590,594,607 'replac':960 'report':205,515 'reproduc':351 'requir':629 'research':10,900 'resourc':1001 'result':754 'retarget':623 'review':200,210,232,369,400,403,405,510,512,757,963 'review_log.md':273 'revis':698,760 'rewrit':533 'risk':785 'role':833 'root':333,501 'rout':727,882,893,908,919 'rule':113,459,879 'safe':68 'say':869,1009 'scaffold':25,259,313,562,723,852,918 'script':352,410,415 'search':885 'search-lit':884 'section':140,944 'self':402,509 'separ':436,551 'seri':308 'session':335,592 'set':55 'skill':33,36,65,71,104,726,934 'skill-intake-project' 'slot':324 'slug':425 'sourc':373,461 'source-aperivue' 'stage':684,688,708,777,814 'state':17,62,243 'statist':949 'status':812 'status.md':269,810 'step':23 'strobe':513,601 'strobe/prisma':406 'strobe_checklist.md':448 'structur':60,299,311,564,596,769 'studi':142,669,739,868,897,961 'submiss':418,455,462,467,528,530,554,567,570,634,699,987 'submission-readi':454 'submission/chest':633 'summar':15 'summari':109,766,773 'supplement':445 'surfac':730 'survival/prognostic':223 'tabl':413,414,656 'tables/figures':164 'target':227,236,709,742,779,803,838 'task':192 'technic':206 'templat':795 'terminolog':147 'text':770 'titl':544,665,668,799 'title_page.docx':435 'tool':998 'top':386,522,588,616,643 'top-level':642 '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' 'type':14,198,283,707,775,800 'uncertain':188 'unclear':907 'unless':840 'unsur':1008 'updat':809,823 'url':971 'use':67,69,132,136 'user':91,117,713,855 'v':377,397 'v1':396,608 'v6':609 'valu':829 'variabl':748 'venu':239 'venue/journal':678 'verif':990 'verifi':954,976 'version':385,395,480,488,494,582 'want':857 'weak':892 'websit':995 'without':989 'work':384,479,667 'workflow':226,635 'workspac':135 'wrapper':391 'write':922,941 'write-pap':921 'wrong':722,725","prices":[{"id":"3c7c532c-3b80-49c5-b043-1ce365629a31","listingId":"c6e97629-1a57-4e71-9131-4c5a13bdc194","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":"2026-05-13T12:57:45.183Z"}],"sources":[{"listingId":"c6e97629-1a57-4e71-9131-4c5a13bdc194","source":"github","sourceId":"Aperivue/medsci-skills/intake-project","sourceUrl":"https://github.com/Aperivue/medsci-skills/tree/main/skills/intake-project","isPrimary":false,"firstSeenAt":"2026-05-13T12:57:45.183Z","lastSeenAt":"2026-05-18T18:56:30.157Z"}],"details":{"listingId":"c6e97629-1a57-4e71-9131-4c5a13bdc194","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Aperivue","slug":"intake-project","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":"2a06251d1c9d8d5cbb083e7f5791ec37c7f77ea6","skill_md_path":"skills/intake-project/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Aperivue/medsci-skills/tree/main/skills/intake-project"},"layout":"multi","source":"github","category":"medsci-skills","frontmatter":{"name":"intake-project","description":"Intake and normalize a new radiology research project. Classifies project type, summarizes current state, identifies missing inputs, recommends next steps, and scaffolds lightweight project memory files."},"skills_sh_url":"https://skills.sh/Aperivue/medsci-skills/intake-project"},"updatedAt":"2026-05-18T18:56:30.157Z"}}