intake-project

Name: intake-project
Author: Aperivue

41installs53forks

How to install intake-project?

aperivue/medsci-skills/intake-project

$npx -y skills add Aperivue/medsci-skills --skill intake-project

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# Intake-Project Skill
2
3	## Purpose
4
5	This 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.
6
7	Use this skill when:
8	- a new paper or proposal folder has been created
9	- an older folder exists but is poorly organized
10	- the user asks "what is this project and what should I do next?"
11	- another skill needs a reliable project summary before proceeding
12
13	---
14
15	## Communication Rules
16
17	- Communicate with the user in their preferred language.
18	- Keep project labels and file names in the language already used by the workspace.
19	- Use English for manuscript section names, study design names, and medical/statistical terminology.
20
21	---
22
23	## Inputs
24
25	Accept any of the following:
26	- a project folder
27	- a manuscript draft
28	- an abstract or proposal
29	- tables/figures plus notes
30	- a mixed folder with PDFs, drafts, and analyses
31
32	If information is incomplete, infer cautiously from file names and contents, then label uncertain items clearly.
33
34	---
35
36	## Core Tasks
37
38	### 1. Project classification
39
40	Determine:
41	- project type: `original \| review \| meta-analysis \| case report \| technical note \| grant \| peer review \| challenge \| career-doc`
42	- primary domain: `radiology \| medical AI \| multimodal LLM \| intervention \| survival/prognostic \| diagnostic accuracy \| workflow`
43	- target output: `paper \| abstract \| grant \| review \| rebuttal \| CV`
44	- likely target journal or venue, if recoverable
45
46	### 2. State reconstruction
47
48	Identify:
49	- what already exists
50	- what is missing
51	- current phase
52	- blocking dependencies
53
54	### 3. Project memory scaffold
55
56	If missing, propose or create lightweight anchor files:
57	- `PROJECT.md`
58	- `STATUS.md`
59	- `CLAIMS.md`
60	- `DATA_DICTIONARY.md`
61	- `ANALYSIS_PLAN.md`
62	- `REVIEW_LOG.md`
63
64	Create only files that are justified by the project type.
65
66	### 4. Action plan
67
68	Produce the next 3-5 actions in dependency order.
69
70	---
71
72	## Canonical Manuscript Folder Structure
73
74	For 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.
75
76	```
77	{project_root}/
78	├── HANDOFF.md # session handoff entry point
79	├── README.md # project overview
80	├── data/ # raw data (NEVER edit; read-only)
81	├── analysis/ # reproducible scripts (00_* → 04_*)
82	├── output/ # analysis outputs: CSVs, PNGs, intermediates
83	├── irb/ # IRB/ethics docs
84	├── proposal/ # original protocol / approved proposal
85	├── reviews/ # external correspondence
86	├── manuscript/ # SOURCE manuscript + drafting
87	│ ├── manuscript_v{N}.{md,docx,pdf} # current canonical working version (top level)
88	│ ├── build_unified_docx.py # or pandoc wrapper
89	│ ├── archive/ # ALL prior versions v1 .. v{N-1}
90	│ ├── reviews/ # QC: self_review, peer_review, STROBE/PRISMA, critic
91	│ ├── figures/ # figure scripts + rendered PNG/PDF
92	│ └── tables/ # table scripts + rendered docx
93	└── submission/ # per-journal packages
94	└── {journal-slug}/ # e.g., chest/, kjr/
95	├── CHECKLIST.md
96	├── cover_letter.{md,docx,pdf}
97	├── title_page.docx # separated for double-anonymized
98	├── manuscript_anonymized.{docx,pdf}
99	├── supplement.{docx,pdf}
100	├── strobe_checklist.md # or PRISMA / CONSORT
101	├── circulation_email.md
102	└── figures/ # submission-ready DPI copies
103	```
104
105	### Rules
106
107	- `manuscript/` = source; `submission/{journal}/` = derived artifacts. Regenerate submission files from `manuscript/manuscript_v{N}.md`; never edit anonymized/title-page directly.
108	- One canonical working version at `manuscript/manuscript_v{N}.{md,docx,pdf}`. Older versions move to `manuscript/archive/` immediately on version bump.
109	- No loose files at project root. Only `HANDOFF.md`, `README.md`, folder entries.
110	- QC artifacts (self_review, peer_review, STROBE, critic reports) live in `manuscript/reviews/`, not at manuscript top level.
111	- On rejection/retarget: `cp -r submission/{old} submission/{new}`, then rewrite cover letter and reformat.
112	- Double-anonymized journals (Chest, AJRCCM): title page and anonymized manuscript MUST be separat

People who liked this also viewed

6 picks

Type

intake-project

41installs53forks

View on GitHub

How to install intake-project?

aperivue/medsci-skills/intake-project

$npx -y skills add Aperivue/medsci-skills --skill intake-project

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Intake-Project Skill
2
3	## Purpose
4
5	This 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.
6
7	Use this skill when:
8	- a new paper or proposal folder has been created
9	- an older folder exists but is poorly organized
10	- the user asks "what is this project and what should I do next?"
11	- another skill needs a reliable project summary before proceeding
12
13	---
14
15	## Communication Rules
16
17	- Communicate with the user in their preferred language.
18	- Keep project labels and file names in the language already used by the workspace.
19	- Use English for manuscript section names, study design names, and medical/statistical terminology.
20
21	---
22
23	## Inputs
24
25	Accept any of the following:
26	- a project folder
27	- a manuscript draft
28	- an abstract or proposal
29	- tables/figures plus notes
30	- a mixed folder with PDFs, drafts, and analyses
31
32	If information is incomplete, infer cautiously from file names and contents, then label uncertain items clearly.
33
34	---
35
36	## Core Tasks
37
38	### 1. Project classification
39
40	Determine:
41	- project type: `original \| review \| meta-analysis \| case report \| technical note \| grant \| peer review \| challenge \| career-doc`
42	- primary domain: `radiology \| medical AI \| multimodal LLM \| intervention \| survival/prognostic \| diagnostic accuracy \| workflow`
43	- target output: `paper \| abstract \| grant \| review \| rebuttal \| CV`
44	- likely target journal or venue, if recoverable
45
46	### 2. State reconstruction
47
48	Identify:
49	- what already exists
50	- what is missing
51	- current phase
52	- blocking dependencies
53
54	### 3. Project memory scaffold
55
56	If missing, propose or create lightweight anchor files:
57	- `PROJECT.md`
58	- `STATUS.md`
59	- `CLAIMS.md`
60	- `DATA_DICTIONARY.md`
61	- `ANALYSIS_PLAN.md`
62	- `REVIEW_LOG.md`
63
64	Create only files that are justified by the project type.
65
66	### 4. Action plan
67
68	Produce the next 3-5 actions in dependency order.
69
70	---
71
72	## Canonical Manuscript Folder Structure
73
74	For 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.
75
76	```
77	{project_root}/
78	├── HANDOFF.md # session handoff entry point
79	├── README.md # project overview
80	├── data/ # raw data (NEVER edit; read-only)
81	├── analysis/ # reproducible scripts (00_* → 04_*)
82	├── output/ # analysis outputs: CSVs, PNGs, intermediates
83	├── irb/ # IRB/ethics docs
84	├── proposal/ # original protocol / approved proposal
85	├── reviews/ # external correspondence
86	├── manuscript/ # SOURCE manuscript + drafting
87	│ ├── manuscript_v{N}.{md,docx,pdf} # current canonical working version (top level)
88	│ ├── build_unified_docx.py # or pandoc wrapper
89	│ ├── archive/ # ALL prior versions v1 .. v{N-1}
90	│ ├── reviews/ # QC: self_review, peer_review, STROBE/PRISMA, critic
91	│ ├── figures/ # figure scripts + rendered PNG/PDF
92	│ └── tables/ # table scripts + rendered docx
93	└── submission/ # per-journal packages
94	└── {journal-slug}/ # e.g., chest/, kjr/
95	├── CHECKLIST.md
96	├── cover_letter.{md,docx,pdf}
97	├── title_page.docx # separated for double-anonymized
98	├── manuscript_anonymized.{docx,pdf}
99	├── supplement.{docx,pdf}
100	├── strobe_checklist.md # or PRISMA / CONSORT
101	├── circulation_email.md
102	└── figures/ # submission-ready DPI copies
103	```
104
105	### Rules
106
107	- `manuscript/` = source; `submission/{journal}/` = derived artifacts. Regenerate submission files from `manuscript/manuscript_v{N}.md`; never edit anonymized/title-page directly.
108	- One canonical working version at `manuscript/manuscript_v{N}.{md,docx,pdf}`. Older versions move to `manuscript/archive/` immediately on version bump.
109	- No loose files at project root. Only `HANDOFF.md`, `README.md`, folder entries.
110	- QC artifacts (self_review, peer_review, STROBE, critic reports) live in `manuscript/reviews/`, not at manuscript top level.
111	- On rejection/retarget: `cp -r submission/{old} submission/{new}`, then rewrite cover letter and reformat.
112	- Double-anonymized journals (Chest, AJRCCM): title page and anonymized manuscript MUST be separat

People who liked this also viewed

6 picks

Type