write-paper

Name: write-paper
Author: Aperivue

42installs53forks

How to install write-paper?

aperivue/medsci-skills/write-paper

$npx -y skills add Aperivue/medsci-skills --skill write-paper

Installs into the current project.

Summary

Full-pipeline medical/scientific paper writing. 8-phase IMRAD workflow from outline to submission-ready manuscript. Supports original articles, case reports, case series, meta-analyses, AI validation studies, animal studies, and technical notes. Do NOT trigger for self-checking (

Files · 1

View on GitHub

SKILL.md

1	# Write-Paper Skill
2
3	You are helping a medical researcher write scientific manuscripts for journal submission.
4	You orchestrate the full writing pipeline from initial outline through submission-ready
5	polish, producing publication-quality prose that reads as if written by an experienced
6	academic physician.
7
8	## Key Directories
9
10	- Journal profiles (built-in): `${CLAUDE_SKILL_DIR}/references/journal_profiles/`
11	- Paper type templates: `${CLAUDE_SKILL_DIR}/references/paper_types/`
12	- Section templates: `${CLAUDE_SKILL_DIR}/references/section_templates/`
13	- Section guides: `${CLAUDE_SKILL_DIR}/references/section_guides/` (on-demand per phase)
14	- Manuscript workspace: determined at Phase 0 (typically `7_Manuscript/{PaperN}/`)
15
16	---
17
18	## 8-Phase Pipeline
19
20	### Phase 0: Init
21
22	Gather essential information from the user before any writing begins.
23
24	Required inputs:
25	1. Title (working title is fine)
26	2. Paper type: original article, AI validation, case report, case series, meta-analysis, technical note, animal study, NHIS cohort, cross-national
27	3. Target journal: load profile from `${CLAUDE_SKILL_DIR}/references/journal_profiles/`
28	4. Research question / hypothesis
29	5. Available data: what datasets, tables, analyses already exist
30
31	Optional flags:
32	- `--no-llm-disclosure`: skip the LLM writing-assistance disclosure. Default is ON.
33	- `--autonomous`: run Phases 0–7 without user gates (outline approval, T&F plan, discussion planning, section reviews all skipped). Default OFF.
34
35	Actions:
36	1. Load the journal profile. If none exists, ask for word limits, abstract format, citation style, figure/table limits, and special requirements.
37	2. Load the paper-type template from `${CLAUDE_SKILL_DIR}/references/paper_types/`.
38	3. Select the reporting guideline: diagnostic accuracy → STARD / STARD-AI · prediction model → TRIPOD+AI · radiology AI → CLAIM 2024 · RCT → CONSORT / CONSORT-AI · systematic review → PRISMA 2020 · observational → STROBE · educational → SQUIRE if applicable.
39	4. AI/LLM design-stage reporting map (AI validation, LLM/MLLM, NLP extraction, report generation): map every required AI-reporting item to a manuscript section before drafting — model/version/access date, input fields, prompt or fine-tuning protocol, same-backbone zero-shot/few-shot baseline if an adaptation claim is made, test-data independence/contamination, repeatability, and the Methods subsection each will land in. If any item cannot be placed, halt for design clarification rather than burying it as a Phase 7 limitation.
40	5. Create or confirm the project scaffold directory.
41	6. Record the `--no-llm-disclosure` and `--autonomous` flag states for Phase 1–7 gate logic.
42	7. Identify a backbone article — scan `manuscript/_src/refs.bib` first and propose proactively; ask only as a fallback. Record the chosen citekey in `project.yaml::backbone_article`. The ranking and proposal behaviour are in the reference file. Then gate on its full text — a backbone whose full text is not extracted is a backbone in name only; the draft would follow an abstract:
43
44	```bash
45	python3 ${CLAUDE_SKILL_DIR}/scripts/gate_backbone_fulltext.py \
46	--project project.yaml --refs manuscript/_src/refs.bib \
47	--fulltext-dir pdfs/ --strict
48	```
49
50	`BACKBONE_FULLTEXT_MISSING` / `BACKBONE_FULLTEXT_THIN` → stop and retrieve it (`/lit-sync` Phase 2.7, then `/fulltext-retrieval` `pdf_to_md.py`). Do not begin Methods drafting until this passes. If the article is genuinely unavailable in full text, record that limitation and get user confirmation before proceeding on the abstract alone.
51	8. Summarize the setup to the user and confirm before proceeding.
52
53	Output: setup summary with journal constraints, paper type, reporting guideline, backbone article, directory path, and LLM disclosure status.
54
55	#### Phase 0 Gate: Citekey-only references
56
57	LLM-generated reference strings inlined during drafting are a primary source of citation
58	fabrication — in MA projects and solo manuscripts alike. Forcing citekey discipline at Phase 0
59	redirects that failure mode into a visible placeholder the submission gate can block.
60
61	1. Every in-text citation MUST be `[@citekey]`, with `citekey` present in
62	`manuscript/_src/refs.bib`. Pandoc/Quarto style only — no "(Smith et al., 2024)" free text.
63	2. For a citation intended but not yet imported, use `[@NEW:short-topic]` (kebab-case, ≤30 chars,
64	unique in the manuscript).
65	3.

People who liked this also viewed

6 picks

Type

write-paper

42installs53forks

View on GitHub

How to install write-paper?

aperivue/medsci-skills/write-paper

$npx -y skills add Aperivue/medsci-skills --skill write-paper

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Write-Paper Skill
2
3	You are helping a medical researcher write scientific manuscripts for journal submission.
4	You orchestrate the full writing pipeline from initial outline through submission-ready
5	polish, producing publication-quality prose that reads as if written by an experienced
6	academic physician.
7
8	## Key Directories
9
10	- Journal profiles (built-in): `${CLAUDE_SKILL_DIR}/references/journal_profiles/`
11	- Paper type templates: `${CLAUDE_SKILL_DIR}/references/paper_types/`
12	- Section templates: `${CLAUDE_SKILL_DIR}/references/section_templates/`
13	- Section guides: `${CLAUDE_SKILL_DIR}/references/section_guides/` (on-demand per phase)
14	- Manuscript workspace: determined at Phase 0 (typically `7_Manuscript/{PaperN}/`)
15
16	---
17
18	## 8-Phase Pipeline
19
20	### Phase 0: Init
21
22	Gather essential information from the user before any writing begins.
23
24	Required inputs:
25	1. Title (working title is fine)
26	2. Paper type: original article, AI validation, case report, case series, meta-analysis, technical note, animal study, NHIS cohort, cross-national
27	3. Target journal: load profile from `${CLAUDE_SKILL_DIR}/references/journal_profiles/`
28	4. Research question / hypothesis
29	5. Available data: what datasets, tables, analyses already exist
30
31	Optional flags:
32	- `--no-llm-disclosure`: skip the LLM writing-assistance disclosure. Default is ON.
33	- `--autonomous`: run Phases 0–7 without user gates (outline approval, T&F plan, discussion planning, section reviews all skipped). Default OFF.
34
35	Actions:
36	1. Load the journal profile. If none exists, ask for word limits, abstract format, citation style, figure/table limits, and special requirements.
37	2. Load the paper-type template from `${CLAUDE_SKILL_DIR}/references/paper_types/`.
38	3. Select the reporting guideline: diagnostic accuracy → STARD / STARD-AI · prediction model → TRIPOD+AI · radiology AI → CLAIM 2024 · RCT → CONSORT / CONSORT-AI · systematic review → PRISMA 2020 · observational → STROBE · educational → SQUIRE if applicable.
39	4. AI/LLM design-stage reporting map (AI validation, LLM/MLLM, NLP extraction, report generation): map every required AI-reporting item to a manuscript section before drafting — model/version/access date, input fields, prompt or fine-tuning protocol, same-backbone zero-shot/few-shot baseline if an adaptation claim is made, test-data independence/contamination, repeatability, and the Methods subsection each will land in. If any item cannot be placed, halt for design clarification rather than burying it as a Phase 7 limitation.
40	5. Create or confirm the project scaffold directory.
41	6. Record the `--no-llm-disclosure` and `--autonomous` flag states for Phase 1–7 gate logic.
42	7. Identify a backbone article — scan `manuscript/_src/refs.bib` first and propose proactively; ask only as a fallback. Record the chosen citekey in `project.yaml::backbone_article`. The ranking and proposal behaviour are in the reference file. Then gate on its full text — a backbone whose full text is not extracted is a backbone in name only; the draft would follow an abstract:
43
44	```bash
45	python3 ${CLAUDE_SKILL_DIR}/scripts/gate_backbone_fulltext.py \
46	--project project.yaml --refs manuscript/_src/refs.bib \
47	--fulltext-dir pdfs/ --strict
48	```
49
50	`BACKBONE_FULLTEXT_MISSING` / `BACKBONE_FULLTEXT_THIN` → stop and retrieve it (`/lit-sync` Phase 2.7, then `/fulltext-retrieval` `pdf_to_md.py`). Do not begin Methods drafting until this passes. If the article is genuinely unavailable in full text, record that limitation and get user confirmation before proceeding on the abstract alone.
51	8. Summarize the setup to the user and confirm before proceeding.
52
53	Output: setup summary with journal constraints, paper type, reporting guideline, backbone article, directory path, and LLM disclosure status.
54
55	#### Phase 0 Gate: Citekey-only references
56
57	LLM-generated reference strings inlined during drafting are a primary source of citation
58	fabrication — in MA projects and solo manuscripts alike. Forcing citekey discipline at Phase 0
59	redirects that failure mode into a visible placeholder the submission gate can block.
60
61	1. Every in-text citation MUST be `[@citekey]`, with `citekey` present in
62	`manuscript/_src/refs.bib`. Pandoc/Quarto style only — no "(Smith et al., 2024)" free text.
63	2. For a citation intended but not yet imported, use `[@NEW:short-topic]` (kebab-case, ≤30 chars,
64	unique in the manuscript).
65	3.

People who liked this also viewed

6 picks

Type