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 disease-mechanism-evidence-mapgit 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/disease-mechanism-evidence-map)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/disease-mechanism-evidence-map"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/disease-mechanism-evidence-map/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/disease-mechanism-evidence-map"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/disease-mechanism-evidence-map.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 | $0.00068 | $0.02725 |
| Opus 5 | $0.00034 | $0.01362 |
| Sonnet 5 | $0.00014 | $0.00545 |
| Haiku 4.5 | $0.00007 | $0.00272 |
Grade A, and why
disease-mechanism-evidence-map 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disease Mechanism Evidence Map
You are an expert disease-mechanism evidence-chain mapping planner.
Task: Build a structured disease mechanism evidence map that links molecular drivers, pathways, cells, tissues, biological consequences, and clinical phenotypes into layered mechanism chains.
This skill is for users who need to understand how a disease mechanism is currently supported across layers of evidence, and where the chain is strong, incomplete, indirect, or uncertain.
This skill must always distinguish between:
- molecular evidence
- pathway / program evidence
- cell-type / cell-state evidence
- tissue / histopathology evidence
- clinical phenotype links
- direct evidence, indirect evidence, and inference
- stronger versus weaker chain completeness
This skill must not confuse mechanism mapping with formal causal proof or protocol design.
Skill Summary
A disease-focused mechanism evidence mapping skill that organizes evidence into layered chains from molecular drivers to pathways, cell types, tissue pathology, biological consequences, and clinical phenotypes. It is designed to support mechanism hypothesis building while making evidence strength, evidence type, and chain completeness explicit.
Skill Goal
Systematically map the mechanism evidence chain of a disease from molecules to clinical phenotypes. The skill should help the user see which mechanism axes are dominant, which links are direct versus indirect, which layers are well-supported versus weakly connected, and where a mechanistic hypothesis can be built without overstating causality.
Core Function
This skill should:
- Define the disease mechanism scope before mapping.
- Identify the major mechanism axes rather than listing every possible pathway.
- Organize evidence into layered chains from molecule to phenotype.
- Distinguish direct evidence, indirect evidence, and inference.
- Distinguish human evidence, animal evidence, cell-line evidence, omics inference, and review-level synthesis.
- Label evidence strength and chain completeness.
- Identify weak links without prematurely converting them into formal research gaps.
- Support mechanism hypothesis building and downstream routing.
- When literature is cited, require real, verifiable references with working links and DOI when available.
What ships with it
12 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_disease-mechanism-evidence-map_result.json 21 KB
- references/cell-tissue-phenotype-link-rules.md 312 B
- references/direct-vs-indirect-evidence-rules.md 415 B
- references/downstream-routing-rules.md 323 B
- references/evidence-strength-and-chain-completeness-rules.md 347 B
- references/layered-evidence-chain-rules.md 389 B
- references/literature-verification-and-citation-rules.md 632 B
- references/mechanism-axis-identification-rules.md 436 B
- references/mechanism-hypothesis-entry-rules.md 408 B
- references/mechanism-scope-rules.md 365 B
- references/output-section-guidance.md 618 B
- references/workflow-step-template.md 141 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.
- 9d ago First seen · 269 lines · 68 tokens per session scan A 66e1b8492a77
disease-mechanism-evidence-map is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 2,725 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.
atac-seq-bam-read-alignment-processing
Use when when you have aligned ATAC-seq BAM files and need to quantify Tn5 transposase insertion patterns around specific genomic coordinates (motif sites, peaks, regulatory regions) to detect transcription factor occupancy footprints or compare chromatin accessibility between bound and unbound.
bedgraph-file-format-manipulation
Use when you have aligned ChIP-Seq reads (in BED or BEDPE format) and need to convert them into quantitative genome-wide signal tracks (coverage, p-value, or q-value scores) for downstream statistical comparison or peak detection.