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 zamushwani/biomedical-ai-skills --skill meta-analysisgit clone --depth 1 https://github.com/zamushwani/biomedical-ai-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/zamushwani/biomedical-ai-skills/meta-analysis)<a href="https://agentmods.dev/skills/zamushwani/biomedical-ai-skills/meta-analysis"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-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/zamushwani/biomedical-ai-skills/meta-analysis"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-skills/meta-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.12808 |
| Opus 5 | $0.00000 | $0.06404 |
| Sonnet 5 | $0.00000 | $0.02562 |
| Haiku 4.5 | $0.00000 | $0.01281 |
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 11d 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 — 1,165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Analysis
Systematic review and meta-analysis for clinical and preclinical evidence. Covers protocol registration, search strategy, screening, PRISMA 2020 flow diagrams, risk of bias, pooling with fixed and random effects models, small-study effects, sensitivity diagnostics, network meta-analysis, and GRADE/CINeMA certainty rating. Uses metafor, netmeta, PRISMA2020, synthesisr, and robvis.
When to Use This Skill
Activate when the user requests:
- A systematic review or meta-analysis protocol
- Search strategy construction for PubMed, Embase, or Cochrane CENTRAL
- PRISMA 2020 flow diagram generation
- Deduplication of records across databases
- Title/abstract or full-text screening workflows
- Inter-rater agreement between screeners
- Risk of bias assessment (RoB 2, ROBINS-I, ROBINS-E, QUADAS-2, Newcastle-Ottawa)
- Risk of bias visualization (traffic light or summary plots)
- Data extraction templates for RCTs or observational studies
- Effect size computation (OR, RR, RD, SMD, MD, ROM, HR)
- Pooling with equal-effects or random-effects models
- Heterogeneity quantification (tau^2, I^2, Q) and prediction intervals
- Subgroup analysis and meta-regression
- Hazard ratio reconstruction from published Kaplan-Meier curves
- Forest and funnel plots
- Publication bias or small-study effect assessment
- Leave-one-out, influence, or cumulative sensitivity analysis
- Network meta-analysis, transitivity, inconsistency, or treatment ranking
- GRADE or CINeMA certainty rating
Inputs
| Data Type | Format | Source |
|---|---|---|
| Search results | RIS, BibTeX, NBIB, CSV | PubMed, Embase, CENTRAL, Web of Science |
| Record counts | Integers per PRISMA stage | Search logs, screening software |
| Extracted outcomes | Tabular (study, n, effect, variance) | Full-text data extraction |
| Risk of bias judgements | Tabular (study, domain 1..k, overall) | RoB 2 / ROBINS-I Excel or manual |
Environment
# Core, all actively maintained (versions verified 2026-08)
install.packages(c("metafor", "meta", "PRISMA2020", "robvis", "synthesisr", "irr"))
# metafor 5.0-1 effect sizes and models
# meta 8.5-0 alternative interface, GRADE-friendly output
# PRISMA2020 1.1.4 flow diagrams
# robvis 0.3.1 risk of bias plots
# synthesisr 0.4.1 bibliographic import and deduplication
# irr 0.85 Cohen's and Fleiss' kappa
# Network meta-analysis and bias sensitivity
install.packages(c("netmeta", "metasens", "gemtc", "multinma"))
# netmeta 3.6-1 frequentist NMA. NOTE: pairwise() is in `meta`
# metasens 1.5-3 Copas selection model, limit meta-analysis
# gemtc 1.1-1 Bayesian NMA, JAGS backend
# multinma 0.9.1 Bayesian NMA, Stan; aggregate + individual patient data
# Programmatic search
install.packages(c("rentrez", "easyPubMed"))
# rentrez 1.2.4
# easyPubMed 3.1.6
What ships with it
7 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.
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.
- 11d ago First seen · 1,165 lines · 0 tokens per session scan A 440480aa4186
meta-analysis is a skill published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 12,808 tokens. 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 2026-08-31.
Other skills, from other repositories
automated-soap-note-generator
Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…
medical-research-literature-reader-pro
A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title.…
anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.
find-paper-references
Automatically find references for academic paper Markdown files. Reads full paper text, identifies each knowledge point requiring citation (epidemiological data, mechanism descriptions, existing research conclusions, etc.), searches PubMed for 3-5 most relevant articles per kn...
graph-interpretation
Use when interpreting scientific graphs and charts, explaining data visualizations for research presentations, writing figure captions for publications, or analyzing trends in clinical research data. Converts complex visual data into clear, accurate explanations for academic papers, clinical reports, and public…