review-paper

Name: review-paper
Author: Aperivue

33installs53forks

How to install review-paper?

aperivue/medsci-skills/review-paper

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

Installs into the current project.

Summary

Scaffold and draft medical/AI literature reviews (narrative, scoping PRISMA-ScR, or systematic). Asks for the spine axis, builds a 7-part skeleton with a required Intro scope/non-overlap block, a summary-table stub, an evaluation-metrics critique subsection, and reporting-guideli

Files · 1

View on GitHub

SKILL.md

1	# Review-Paper Skill
2
3	Scaffold and draft a literature review — narrative, scoping (PRISMA-ScR), or systematic
4	(PRISMA 2020) — for medical / medical-AI research. This skill builds the structure, the
5	required scope/non-overlap framing, the summary-table stubs, and the reporting-guideline
6	wiring, then hands off to the existing QC skills. It is the review-article counterpart to
7	`write-paper` (which targets original research); for reviewing someone else's review
8	article, use `/peer-review` or `/self-review` (the RV1-RV9 probes). The structure follows
9	established review-writing conventions; it is not derived from, and does not reproduce, any
10	specific published review.
11
12	## Anti-Hallucination
13
14	- Never invent citations. Every citekey must resolve to the project's verified
15	`_src/refs.bib` (produced by `/search-lit` → `/lit-sync` → `/verify-refs`). If a claim
16	needs a reference that is not yet in the library, leave a `[NEEDS-REF: claim]` marker and
17	route it to `/search-lit`; do not fabricate a DOI, author, year, or citekey.
18	- Never invent data. Summary-table cells (study, year, metric, finding) are filled only
19	from sources the user supplies or that are verified; an unknown cell stays a placeholder.
20	- No recommendation-grade language without standing. For a scoping review especially,
21	the output maps the evidence — it does not issue clinical recommendations.
22	- Quality gate before hand-off: the draft is not "done" until `/self-review` reports 0
23	fatal findings and `/verify-refs` reports 0 FABRICATED / MISMATCH and no placeholder
24	citations remain.
25
26	## Step 0 — Format + spine axis (the structure-determining choice)
27
28	1. Confirm format with the user: narrative (SANRA) \| scoping (PRISMA-ScR + JBI) \|
29	systematic (PRISMA 2020). This decides the reporting guideline and the registration path.
30	2. Choose the spine axis — the single most consequential decision: organize the body by
31	modality (e.g. 2D → 3D), by task (generation / QA / deployment), or by
32	lifecycle stage. Every body section then follows this one axis; mixing axes is the
33	most common structural failure.
34	3. Require a scope statement + non-overlap boundary against prior/adjacent reviews — this
35	pre-empts the reviewer's first question, "why another review on this?" (user-approval
36	checkpoint: confirm the boundary with the user before scaffolding).
37
38	## Step 1 — Scaffold the 7-part macro skeleton
39
40	Load `${CLAUDE_SKILL_DIR}/references/macro_skeleton.md` and instantiate:
41
42	1. Abstract — structured for scoping/systematic; a 4-5 move version for narrative.
43	2. Introduction — clinical motivation → technology → **scope + non-overlap block
44	(required field)** → "this review…".
45	3. Background / technical principles — tight; cite once, do not re-survey the field.
46	4. Thematic body by spine axis — each section ends with a summary table (stub
47	generated to match the type, Step 2).
48	5. Frontiers / what is advancing.
49	6. Challenges / discussion — include an evaluation-metrics critique subsection (a
50	required quality signal: how the field measures itself, and where those metrics mislead).
51	7. Conclusion — measured; no recommendation-grade language for a scoping review.
52
53	## Step 2 — Summary-table stub (matched to type)
54
55	- Narrative / scoping: `study \| year \| [spine-axis value] \| method \| key finding`.
56	- Systematic: PRISMA flow + a study-characteristics table + an extraction table.
57
58	The stub ships with column headers and one placeholder row; rows are filled only from
59	verified sources (see Anti-Hallucination).
60
61	## Step 3 — Reporting + registration wiring
62
63	- Scoping → PRISMA-ScR (+ JBI charting) + OSF registration.
64	- Narrative → SANRA (a 6-item appraisal aid, not a reporting checklist — do not
65	over-enforce it).
66	- Systematic → PRISMA 2020 (+ PROSPERO registration).
67	- If `/check-reporting` does not yet carry the chosen checklist (e.g. PRISMA-ScR), track a
68	manual gap table and flag it for the user rather than silently skipping the item.
69
70	## Step 4 — QC hand-off
71
72	Run the standard manuscript QC chain, which this skill is designed to feed:
73
74	1. `/self-review` — the RV1-RV9 narrative-review probes auto-activate for a review article.
75	2. `/check-reporting` — the chosen guideline (SANRA / PRISMA-ScR / PRISMA 2020).
76	3. `/verify-refs` — every citation resolves; 0 FABRICATED / MISMATCH.
77	4. `/humanize`

People who liked this also viewed

6 picks

Type

review-paper

33installs53forks

View on GitHub

How to install review-paper?

aperivue/medsci-skills/review-paper

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Review-Paper Skill
2
3	Scaffold and draft a literature review — narrative, scoping (PRISMA-ScR), or systematic
4	(PRISMA 2020) — for medical / medical-AI research. This skill builds the structure, the
5	required scope/non-overlap framing, the summary-table stubs, and the reporting-guideline
6	wiring, then hands off to the existing QC skills. It is the review-article counterpart to
7	`write-paper` (which targets original research); for reviewing someone else's review
8	article, use `/peer-review` or `/self-review` (the RV1-RV9 probes). The structure follows
9	established review-writing conventions; it is not derived from, and does not reproduce, any
10	specific published review.
11
12	## Anti-Hallucination
13
14	- Never invent citations. Every citekey must resolve to the project's verified
15	`_src/refs.bib` (produced by `/search-lit` → `/lit-sync` → `/verify-refs`). If a claim
16	needs a reference that is not yet in the library, leave a `[NEEDS-REF: claim]` marker and
17	route it to `/search-lit`; do not fabricate a DOI, author, year, or citekey.
18	- Never invent data. Summary-table cells (study, year, metric, finding) are filled only
19	from sources the user supplies or that are verified; an unknown cell stays a placeholder.
20	- No recommendation-grade language without standing. For a scoping review especially,
21	the output maps the evidence — it does not issue clinical recommendations.
22	- Quality gate before hand-off: the draft is not "done" until `/self-review` reports 0
23	fatal findings and `/verify-refs` reports 0 FABRICATED / MISMATCH and no placeholder
24	citations remain.
25
26	## Step 0 — Format + spine axis (the structure-determining choice)
27
28	1. Confirm format with the user: narrative (SANRA) \| scoping (PRISMA-ScR + JBI) \|
29	systematic (PRISMA 2020). This decides the reporting guideline and the registration path.
30	2. Choose the spine axis — the single most consequential decision: organize the body by
31	modality (e.g. 2D → 3D), by task (generation / QA / deployment), or by
32	lifecycle stage. Every body section then follows this one axis; mixing axes is the
33	most common structural failure.
34	3. Require a scope statement + non-overlap boundary against prior/adjacent reviews — this
35	pre-empts the reviewer's first question, "why another review on this?" (user-approval
36	checkpoint: confirm the boundary with the user before scaffolding).
37
38	## Step 1 — Scaffold the 7-part macro skeleton
39
40	Load `${CLAUDE_SKILL_DIR}/references/macro_skeleton.md` and instantiate:
41
42	1. Abstract — structured for scoping/systematic; a 4-5 move version for narrative.
43	2. Introduction — clinical motivation → technology → **scope + non-overlap block
44	(required field)** → "this review…".
45	3. Background / technical principles — tight; cite once, do not re-survey the field.
46	4. Thematic body by spine axis — each section ends with a summary table (stub
47	generated to match the type, Step 2).
48	5. Frontiers / what is advancing.
49	6. Challenges / discussion — include an evaluation-metrics critique subsection (a
50	required quality signal: how the field measures itself, and where those metrics mislead).
51	7. Conclusion — measured; no recommendation-grade language for a scoping review.
52
53	## Step 2 — Summary-table stub (matched to type)
54
55	- Narrative / scoping: `study \| year \| [spine-axis value] \| method \| key finding`.
56	- Systematic: PRISMA flow + a study-characteristics table + an extraction table.
57
58	The stub ships with column headers and one placeholder row; rows are filled only from
59	verified sources (see Anti-Hallucination).
60
61	## Step 3 — Reporting + registration wiring
62
63	- Scoping → PRISMA-ScR (+ JBI charting) + OSF registration.
64	- Narrative → SANRA (a 6-item appraisal aid, not a reporting checklist — do not
65	over-enforce it).
66	- Systematic → PRISMA 2020 (+ PROSPERO registration).
67	- If `/check-reporting` does not yet carry the chosen checklist (e.g. PRISMA-ScR), track a
68	manual gap table and flag it for the user rather than silently skipping the item.
69
70	## Step 4 — QC hand-off
71
72	Run the standard manuscript QC chain, which this skill is designed to feed:
73
74	1. `/self-review` — the RV1-RV9 narrative-review probes auto-activate for a review article.
75	2. `/check-reporting` — the chosen guideline (SANRA / PRISMA-ScR / PRISMA 2020).
76	3. `/verify-refs` — every citation resolves; 0 FABRICATED / MISMATCH.
77	4. `/humanize`

People who liked this also viewed

6 picks

Type