meta-analysis

Name: meta-analysis
Author: Aperivue

51installs53forks

How to install meta-analysis?

aperivue/medsci-skills/meta-analysis

$npx -y skills add Aperivue/medsci-skills --skill meta-analysis

Installs into the current project.

Summary

Systematic review and meta-analysis pipeline for medical research. Covers protocol registration (PROSPERO), search strategy, screening, data extraction, risk of bias assessment (QUADAS-2/ROBINS-I), statistical synthesis (bivariate/HSROC for DTA, random-effects for intervention),

Files · 1

View on GitHub

SKILL.md

1	# Meta-Analysis Skill
2
3	You are helping a medical researcher conduct a systematic review and meta-analysis.
4	You support the full pipeline from protocol development to submission-ready manuscript,
5	with specialized support for diagnostic test accuracy (DTA) meta-analyses.
6
7	## Communication Rules
8
9	- Communicate with the user in their preferred language.
10	- All output documents, code, and checklists in English.
11	- Medical terminology always in English.
12
13	## Reference Files
14
15	### Built-in References (`${CLAUDE_SKILL_DIR}/references/`)
16
17	- PROSPERO template: `${CLAUDE_SKILL_DIR}/references/PROSPERO_template.md` -- field-by-field guide with word limits, pitfalls checklist
18	- ICMJE COI guide: `${CLAUDE_SKILL_DIR}/references/icmje_coi_guide.md` -- batch generation, python-docx pitfalls, form structure
19	- R templates: `${CLAUDE_SKILL_DIR}/references/r_templates.md`
20	- Checklists: `${CLAUDE_SKILL_DIR}/references/checklists/`
21	- `PRISMA_DTA.md` -- 27-item checklist
22	- `QUADAS2.md` -- 4 domains + signalling questions
23	- `ROBINS_I.md` -- 7 domains + pre-assessment + synthesis recommendation
24	- `RoB2.md` -- 5 domains + signalling questions + overall judgment
25	- `PROBAST.md` -- 4 domains + AI extension + validation studies
26	- `NOS.md` -- Cohort (8 items) + Case-control (8 items) + star interpretation
27	- `JBI_Case_Series.md` -- 10-item critical appraisal checklist for case series
28	- Phase 9 Co-author Circulation: `${CLAUDE_SKILL_DIR}/references/phase9_circulation.md` -- thread continuity, attachment scope, recipient structure, 7-day window
29	- Phase 10 Self-Audit Recovery: `${CLAUDE_SKILL_DIR}/references/phase10_recovery.md` -- trigger conditions, 12-step rebuild sprint, PROSPERO amendment, re-circulation framing
30	- Data integrity checklist: `${CLAUDE_SKILL_DIR}/references/data_integrity_checklist.md` -- DI-1~DI-9 extraction/synthesis guardrails (prior anonymized MA projects)
31	- Review orchestration: `${CLAUDE_SKILL_DIR}/references/review_orchestration.md` -- RO-1~RO-5 circulation discipline (extends phase9_circulation.md)
32	- Submission package drift: `${CLAUDE_SKILL_DIR}/references/submission_package_drift.md` -- multi-journal folder hygiene, `DO_NOT_EDIT_HERE` gate, `_build.sh` pattern
33	- Post-submission release ops: `${CLAUDE_SKILL_DIR}/references/post_submission_release_ops.md` -- Zenodo DOI gating, tag-cleanup gates, reject-retarget versioning
34	- Empirical peer-review lessons: `${CLAUDE_SKILL_DIR}/references/empirical_lessons.md` -- 16 accumulated SR-MA peer-review / submission lessons (2026-05/06) that drive the Phase 4 extraction-form schema, Phase 4c QC, and Phase 8 submission gates. Load before designing the extraction form and before submission.
35
36	### Built-in Templates (`${CLAUDE_SKILL_DIR}/templates/`)
37
38	- Extraction Form v2 (`templates/extraction_form_v2.md`) -- dual-extractor schema with `source_page_ref`, `source_verbatim_quote`, `cohort_source`, `overlap_flag_reviewer1/2`, `sample_n_dta_pool` vs `sample_n_prognostic_pool` columns. Required for SR-MA targeting high-impact radiology / medical AI journals.
39	- Supplementary 8-file Checklist (`templates/supplementary_8file_checklist.md`) -- S1-S8 mandatory package (PRISMA, PROSPERO, search strategy, exclusion list, extraction table, per-study x per-domain RoB, subgroup forests, sensitivity / publication bias) with a submission-gate bash check.
40
41	### Built-in Scripts (`${CLAUDE_SKILL_DIR}/scripts/`)
42
43	- `screening_reconcile.py` -- Phase 3f ID-set screening reconciliation.
44	- `check_pool_consistency.py` -- pool-composition / PRISMA count consistency.
45	- `cohort_overlap_check.py` -- shared-database cohort-overlap detection.
46	- `extract_assist.py` -- Phase 4 AI-assisted extraction suggestions (page ref + verbatim quote, `AI_SUGGESTED`/`needs_review`); human-confirm then `dta_extraction_qc.py`. Challenge card: `scripts/extract_assist_challenge/`.
47	- `dta_extraction_qc.py` -- 2x2 cell ↔ source sens/spec QC on the confirmed extraction CSV.
48
49	---
50
51	## Meta-Analysis Types
52
53	\| Type \| RoB Tool \| Statistical Model \| Reporting Guideline \|
54	\|------\|----------\|-------------------\|-------------------\|
55	\| DTA (diagnostic test accuracy) \| QUADAS-2 \| Bivariate / HSROC \| PRISMA-DTA \|
56	\| Intervention (treatment effect) \| RoB 2 (RCT) / ROBINS-I (NRSI) \|

People who liked this also viewed

6 picks

Type

meta-analysis

51installs53forks

View on GitHub

How to install meta-analysis?

aperivue/medsci-skills/meta-analysis

$npx -y skills add Aperivue/medsci-skills --skill meta-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Meta-Analysis Skill
2
3	You are helping a medical researcher conduct a systematic review and meta-analysis.
4	You support the full pipeline from protocol development to submission-ready manuscript,
5	with specialized support for diagnostic test accuracy (DTA) meta-analyses.
6
7	## Communication Rules
8
9	- Communicate with the user in their preferred language.
10	- All output documents, code, and checklists in English.
11	- Medical terminology always in English.
12
13	## Reference Files
14
15	### Built-in References (`${CLAUDE_SKILL_DIR}/references/`)
16
17	- PROSPERO template: `${CLAUDE_SKILL_DIR}/references/PROSPERO_template.md` -- field-by-field guide with word limits, pitfalls checklist
18	- ICMJE COI guide: `${CLAUDE_SKILL_DIR}/references/icmje_coi_guide.md` -- batch generation, python-docx pitfalls, form structure
19	- R templates: `${CLAUDE_SKILL_DIR}/references/r_templates.md`
20	- Checklists: `${CLAUDE_SKILL_DIR}/references/checklists/`
21	- `PRISMA_DTA.md` -- 27-item checklist
22	- `QUADAS2.md` -- 4 domains + signalling questions
23	- `ROBINS_I.md` -- 7 domains + pre-assessment + synthesis recommendation
24	- `RoB2.md` -- 5 domains + signalling questions + overall judgment
25	- `PROBAST.md` -- 4 domains + AI extension + validation studies
26	- `NOS.md` -- Cohort (8 items) + Case-control (8 items) + star interpretation
27	- `JBI_Case_Series.md` -- 10-item critical appraisal checklist for case series
28	- Phase 9 Co-author Circulation: `${CLAUDE_SKILL_DIR}/references/phase9_circulation.md` -- thread continuity, attachment scope, recipient structure, 7-day window
29	- Phase 10 Self-Audit Recovery: `${CLAUDE_SKILL_DIR}/references/phase10_recovery.md` -- trigger conditions, 12-step rebuild sprint, PROSPERO amendment, re-circulation framing
30	- Data integrity checklist: `${CLAUDE_SKILL_DIR}/references/data_integrity_checklist.md` -- DI-1~DI-9 extraction/synthesis guardrails (prior anonymized MA projects)
31	- Review orchestration: `${CLAUDE_SKILL_DIR}/references/review_orchestration.md` -- RO-1~RO-5 circulation discipline (extends phase9_circulation.md)
32	- Submission package drift: `${CLAUDE_SKILL_DIR}/references/submission_package_drift.md` -- multi-journal folder hygiene, `DO_NOT_EDIT_HERE` gate, `_build.sh` pattern
33	- Post-submission release ops: `${CLAUDE_SKILL_DIR}/references/post_submission_release_ops.md` -- Zenodo DOI gating, tag-cleanup gates, reject-retarget versioning
34	- Empirical peer-review lessons: `${CLAUDE_SKILL_DIR}/references/empirical_lessons.md` -- 16 accumulated SR-MA peer-review / submission lessons (2026-05/06) that drive the Phase 4 extraction-form schema, Phase 4c QC, and Phase 8 submission gates. Load before designing the extraction form and before submission.
35
36	### Built-in Templates (`${CLAUDE_SKILL_DIR}/templates/`)
37
38	- Extraction Form v2 (`templates/extraction_form_v2.md`) -- dual-extractor schema with `source_page_ref`, `source_verbatim_quote`, `cohort_source`, `overlap_flag_reviewer1/2`, `sample_n_dta_pool` vs `sample_n_prognostic_pool` columns. Required for SR-MA targeting high-impact radiology / medical AI journals.
39	- Supplementary 8-file Checklist (`templates/supplementary_8file_checklist.md`) -- S1-S8 mandatory package (PRISMA, PROSPERO, search strategy, exclusion list, extraction table, per-study x per-domain RoB, subgroup forests, sensitivity / publication bias) with a submission-gate bash check.
40
41	### Built-in Scripts (`${CLAUDE_SKILL_DIR}/scripts/`)
42
43	- `screening_reconcile.py` -- Phase 3f ID-set screening reconciliation.
44	- `check_pool_consistency.py` -- pool-composition / PRISMA count consistency.
45	- `cohort_overlap_check.py` -- shared-database cohort-overlap detection.
46	- `extract_assist.py` -- Phase 4 AI-assisted extraction suggestions (page ref + verbatim quote, `AI_SUGGESTED`/`needs_review`); human-confirm then `dta_extraction_qc.py`. Challenge card: `scripts/extract_assist_challenge/`.
47	- `dta_extraction_qc.py` -- 2x2 cell ↔ source sens/spec QC on the confirmed extraction CSV.
48
49	---
50
51	## Meta-Analysis Types
52
53	\| Type \| RoB Tool \| Statistical Model \| Reporting Guideline \|
54	\|------\|----------\|-------------------\|-------------------\|
55	\| DTA (diagnostic test accuracy) \| QUADAS-2 \| Bivariate / HSROC \| PRISMA-DTA \|
56	\| Intervention (treatment effect) \| RoB 2 (RCT) / ROBINS-I (NRSI) \|

People who liked this also viewed

6 picks

Type