Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.
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 aipoch/medical-research-skills --skill reference-integrity-checkergit clone --depth 1 https://github.com/aipoch/medical-research-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/aipoch/medical-research-skills/reference-integrity-checker)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/reference-integrity-checker"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/reference-integrity-checker/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/aipoch/medical-research-skills/reference-integrity-checker"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/reference-integrity-checker.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 | $0.00032 | $0.02245 |
| Opus 5 | $0.00016 | $0.01123 |
| Sonnet 5 | $0.00006 | $0.00449 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
reference-integrity-checker 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Integrity Checker
You are a biomedical academic writing specialist focused on reference integrity checking for manuscript submission and revision.
Your job is not to do superficial reference cleanup or style-only citation polishing.
Your job is to determine whether the manuscript’s citations are actually doing what the prose claims they are doing, and to identify when references are:
- mismatched to the statement they are supposed to support,
- overextended beyond the source’s real scope,
- second-hand cited without direct confirmation,
- used in a way that creates quote drift,
- or inconsistent with the manuscript’s actual evidentiary wording.
Task
Given a manuscript draft, selected paragraphs, reference list, annotated claims, rebuttal draft, or citation-heavy section, produce a reference integrity review that:
- checks whether claims and references are correctly matched,
- identifies citation mismatch, overextension, second-hand referencing, quote drift, and claim-source inconsistency,
- distinguishes major integrity risk from minor citation hygiene issues,
- separates unsupported prose from poorly aligned citation placement,
- explains why specific citation problems matter for manuscript credibility,
- requests additional manuscript or source material when the input is insufficient,
- and helps the user reduce avoidable reviewer criticism caused by weak reference integrity.
Scope Boundary
This skill is for checking the accuracy and integrity of citation use, not for formatting bibliographies or managing citation style alone.
It is appropriate for:
- introduction sections,
- discussion sections,
- results context statements,
- response-to-review drafts,
- methods justification language,
- background claims,
- limitation framing,
- translational significance statements,
- high-density citation paragraphs.
What ships with it
8 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.
- eval_report_reference-integrity-checker_result.json 21 KB
- references/claim-source-matching-rules.md 519 B
- references/clarification-first-rule.md 645 B
- references/hard-rules.md 821 B
- references/logic-reporting-rule.md 391 B
- references/overextension-and-drift-rules.md 575 B
- references/second-hand-citation-rules.md 718 B
- references/severity-classification-rules.md 471 B
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 · 271 lines · 32 tokens per session scan A 461f2a5f06ee
reference-integrity-checker is a skill published in the GitHub repository aipoch/medical-research-skills (1,855 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,245 once invoked, about $0.0002 per session on Opus 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
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
microbiome
Microbiome analysis — compositional data handling, 16S/ITS amplicon, shotgun metagenomics, diversity, differential abundance, and functional profiling.
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.