Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Aperivue/medsci-skills --skill meta-analysisgit clone --depth 1 https://github.com/Aperivue/medsci-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aperivue/medsci-skills/meta-analysis)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/meta-analysis"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/meta-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/meta-analysis"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/meta-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.09100 |
| Opus 5.5 | $0.00031 | $0.03640 |
| Sonnet 5.5 | $0.00015 | $0.01820 |
| Haiku 4.5 | $0.00008 | $0.00910 |
Grade A, and why
meta-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Analysis Skill
Meta-Analysis Types
| Type | RoB Tool | Statistical Model | Reporting Guideline |
|---|---|---|---|
| DTA (diagnostic test accuracy) | QUADAS-3 (QUADAS-2 for legacy reviews) | Bivariate / HSROC | PRISMA-DTA |
| Intervention (treatment effect) | RoB 2 (RCT) / ROBINS-I (NRSI) | Random-effects (REML, Hartung-Knapp CI) | PRISMA 2020 |
| Prognostic factor (association of one factor with outcome) | QUIPS | Random-effects | PRISMA 2020 |
| Prediction model (model performance) | PROBAST | Random-effects | PRISMA 2020 |
| Observational (prevalence/association) | NOS / JBI | Random-effects | MOOSE |
If the type is ambiguous (DTA vs intervention), ask the user to clarify before proceeding.
Workflow Phases
Phase 1: Protocol Development
Goal: Produce a PROSPERO-ready protocol document. Write the protocol, extraction forms and manuscript text in English whatever language the user writes in — PROSPERO records and the target journals are English-language.
-
Research question: PIRD (Population, Index test, Reference standard, Diagnosis) for DTA; PICO (Population, Intervention, Comparator, Outcome) for intervention.
-
DTA only — do QUADAS-3 phases 1 and 2 now, not at risk-of-bias time. They are review-level and belong in the protocol: phase 1 states the synthesis question(s) (population, index test(s), target condition — a review may have more than one); phase 2 defines the ideal test accuracy trial for each (objective, participants, index test(s), definition of the target condition, analysis). Every later risk-of-bias and applicability judgement is made against that trial. Write the review-specific guidance for answering each signalling question here too, with clinical and methodological input, and publish it as a web appendix. Defining the ideal trial after seeing the studies is a judgement fitted to the results, not an assessment. See
references/checklists/QUADAS3.md.
What ships with it
59 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ai_pre_screening_template.py 9.8 KB runs code
- references/checklists/JBI_Case_Series.md 2.1 KB
- references/checklists/NOS.md 4.3 KB
- references/checklists/PRISMA_DTA.md 10.0 KB
- references/checklists/PROBAST.md 5.0 KB
- references/checklists/QUADAS2.md 8.1 KB
- references/checklists/QUADAS3.md 13 KB
- references/checklists/RoB2.md 8.1 KB
- references/checklists/ROBINS_I.md 5.6 KB
- references/data_integrity_checklist.md 5.4 KB
- references/empirical_lessons.md 7.5 KB
- references/icmje_coi_guide.md 5.9 KB
- references/LICENSES.md 1.2 KB
- references/phase10_recovery.md 6.0 KB
- references/phase3_screening_detail.md 14 KB
- references/phase4_extraction_detail.md 11 KB
- references/phase4_km_composite.md 5.2 KB
- references/phase6_statistical_synthesis.md 17 KB
- references/phase9_circulation.md 3.4 KB
- references/post_submission_release_ops.md 2.7 KB
- references/PROSPERO_template.md 9.4 KB
- references/r_templates.md 6.9 KB
- references/review_orchestration.md 3.7 KB
- references/single_arm_proportion_ma.md 7.0 KB
- references/submission_package_drift.md 2.9 KB
- scripts/check_exclusion_code_validity_challenge/fixture/protocol_negative.md 617 B
- scripts/check_exclusion_code_validity_challenge/fixture/protocol_positive.md 611 B
- scripts/check_exclusion_code_validity_challenge/fixture/screening_negative.tsv 186 B
- scripts/check_exclusion_code_validity_challenge/fixture/screening_positive.tsv 270 B
- scripts/check_exclusion_code_validity_challenge/problem.md 2.1 KB
- scripts/check_exclusion_code_validity_challenge/verify.sh 3.5 KB runs code
- scripts/check_exclusion_code_validity.py 19 KB runs code
- scripts/check_pool_consistency.py 12 KB runs code
- scripts/check_ratio_ci_symmetry_challenge/fixture/extraction_negative.csv 306 B
- scripts/check_ratio_ci_symmetry_challenge/fixture/extraction_positive.csv 177 B
- scripts/check_ratio_ci_symmetry_challenge/problem.md 2.5 KB
- scripts/check_ratio_ci_symmetry_challenge/verify.sh 3.5 KB runs code
- scripts/check_ratio_ci_symmetry.py 14 KB runs code
- scripts/cohort_overlap_check.py 9.0 KB runs code
- scripts/dta_extraction_qc.py 5.3 KB runs code
- scripts/extract_assist_challenge/expected/suggestions.tsv 1.5 KB
- scripts/extract_assist_challenge/fixture/confirmed_example.csv 200 B
- scripts/extract_assist_challenge/fixture/paper.md 534 B
- scripts/extract_assist_challenge/fixture/schema.yaml 502 B
- scripts/extract_assist_challenge/problem.md 3.0 KB
- scripts/extract_assist_challenge/verify.sh 1.8 KB runs code
- scripts/extract_assist.py 7.7 KB runs code
- scripts/extraction_consensus_log_init.py 3.2 KB runs code
- scripts/prisma_5way_consistency.py 29 KB runs code
- scripts/screening_reconcile.py 15 KB runs code
- scripts/tag_cleanup_gate.sh 3.3 KB runs code
- skill.yml 2.8 KB
- templates/extraction_form_v2.md 6.2 KB
- templates/FINAL_POOL_LOCK.yaml.template 3.1 KB
- templates/supplementary_8file_checklist.md 4.1 KB
- tests/test_pool_consistency.sh 7.2 KB runs code
- tests/test_prisma_5way_consistency.sh 22 KB runs code
- tests/test_ratio_ci_symmetry.sh 5.7 KB runs code
- tests/test_screening_reconcile.sh 18 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago Changed · +18 lines d93ba5e58010
- 20d ago Changed · +8 lines ddf417f4a9d4
- 21d ago Changed · +1 lines e3f137979a13
- 22d ago Changed 062e7dd70188
- 24d ago Changed · -166 lines · -3 tokens per session 94d29ab38b7c
- 25d ago Changed 9d2d6aa9fa32
- 1mo ago First seen · 699 lines · 80 tokens per session scan A ad348da8d8ea
meta-analysis is a skill published in the GitHub repository Aperivue/medsci-skills (349 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 9,100 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.
clinical-research
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…
sr-search-record
An automated literature-review search and screening workflow using OpenAlex, an open database and API for scholarly research, and Zotero, a reference manager.
critical-paper-reading
A paper-reading workflow for critically examining one research paper from a PDF or Zotero item. Zotero is a tool for organising research papers and references.
knowledge-module-gen
A workflow for generating knowledge-module files from a list of academic reading modules. It reads full papers from Zotero, NotebookLM, or local PDFs and records page references and execution checks.