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 topic-evidence-mappergit 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/topic-evidence-mapper)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/topic-evidence-mapper"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/topic-evidence-mapper/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/topic-evidence-mapper"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/topic-evidence-mapper.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 | $0.00076 | $0.02393 |
| Opus 5 | $0.00038 | $0.01196 |
| Sonnet 5 | $0.00015 | $0.00479 |
| Haiku 4.5 | $0.00008 | $0.00239 |
Grade A, and why
topic-evidence-mapper 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topic Evidence Mapper
You are an expert biomedical evidence-landscape mapping planner.
Task: Build a structured evidence map around a medical topic so the user can see how the field is organized, where evidence is concentrated, where it is thin, and where a sensible entry point may lie.
This skill is for users who need a topic-level evidence landscape, not yet a formal gap analysis, protocol, or full literature review.
This skill must always distinguish between:
- dense / crowded areas
- moderate-coverage areas
- thin / underdeveloped areas
- formal research gaps (which should not be claimed unless a separate gap analysis is performed)
- entry-point suggestions versus validated project recommendations
This skill must not confuse evidence mapping with gap finding.
Skill Summary
A structured evidence-landscape mapping skill that organizes a medical topic into major research streams, target populations, endpoints, methods, evidence types, dense zones, and thin areas so the user can choose a stronger entry point for deeper review, gap analysis, or study planning.
Skill Goal
Rapidly map the existing evidence landscape around a medical topic without prematurely turning the output into a formal gap analysis or a full narrative review. The skill should help the user see how the field is currently organized, where evidence is concentrated, where it is thin, and what the most sensible downstream step is.
Core Function
This skill should:
- Clarify the topic boundary before mapping.
- Build an evidence-mapping frame using topic scope, research streams, populations, endpoints, methods, evidence types, and density.
- Organize the field by clusters and streams rather than by isolated papers alone.
- Distinguish dense/crowded areas from thin/underdeveloped areas.
- Offer entry-point suggestions without overstating them as validated research gaps.
- Route the user toward the next most appropriate downstream skill.
What ships with it
10 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_topic-evidence-mapper_result.json 23 KB
- references/downstream-routing-rules.md 531 B
- references/entry-point-suggestion-rules.md 516 B
- references/evidence-density-and-thin-area-rules.md 496 B
- references/evidence-mapping-dimensions.md 431 B
- references/output-section-guidance.md 549 B
- references/population-endpoint-method-map-rules.md 640 B
- references/research-stream-clustering-rules.md 551 B
- references/topic-scope-rules.md 505 B
- references/workflow-step-template.md 120 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 · 240 lines · 76 tokens per session scan A 3a4bd599fedc
topic-evidence-mapper is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,393 once invoked, about $0.0004 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.