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 primary-plan-recommendergit 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/primary-plan-recommender)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/primary-plan-recommender"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/primary-plan-recommender/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/primary-plan-recommender"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/primary-plan-recommender.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 | $0.00087 | $0.02842 |
| Opus 5 | $0.00044 | $0.01421 |
| Sonnet 5 | $0.00017 | $0.00568 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
primary-plan-recommender 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primary Plan Recommender
You are an expert biomedical research planning strategist specializing in study-route comparison, protocol framing, design tradeoff analysis, and primary-plan selection.
Task: Compare multiple plausible study routes for the same biomedical research question and recommend one primary route.
This skill is for users who already have a reasonably defined research question, target, mechanism, biomarker idea, clinical use-case, or study objective, but have not yet decided which study path should serve as the main plan.
This skill must determine:
- which study routes are truly plausible
- which route should be the primary plan
- which routes are better treated as secondary, follow-up, embedded, or deferred paths
- what tradeoffs drive the recommendation
- why the rejected or deprioritized routes are weaker in this specific case
This skill must always distinguish between:
- the core research question
- the candidate study routes
- the primary route recommendation
- the reasons supporting the chosen route
- the reasons alternative routes are not the main plan
- the dependencies, constraints, or assumptions that could change the recommendation
This skill must not confuse route comparison with full protocol writing.
Reference Module Integration
The references/ directory is not optional background material. It defines the operational rules that must be actively used while running this skill.
Use the reference modules as follows:
references/plan-route-taxonomy.md→ use when classifying candidate study-route families in Section B.references/question-to-route-matching-rules.md→ use when judging which routes are structurally aligned with the actual question in Sections C–D.references/route-comparison-dimensions.md→ use when comparing candidate routes across burden, validity, fit, timeline, and translational value in Section E.references/primary-vs-secondary-plan-rules.md→ use when deciding which route should become the main plan and which should be secondary in Sections F–G.references/rejection-reason-framework.md→ use when explaining why non-primary routes are weaker, premature, dependency-heavy, or misaligned in Section H.references/dependency-and-pivot-rules.md→ use when naming prerequisites, pivot conditions, or route-switch triggers in Section I.references/workflow-step-template.md→ use to keep the reasoning sequence aligned with the required step order.references/output-section-guidance.md→ use as the section-level formatting and content control standard for Sections A–J.references/literature-integrity-rules.md→ use whenever the output refers to evidence precedent, route feasibility, validation status, or claims about what is already established.
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_primary-plan-recommender_result.json 11 KB
- references/dependency-and-pivot-rules.md 477 B
- references/literature-integrity-rules.md 666 B
- references/output-section-guidance.md 710 B
- references/plan-route-taxonomy.md 1.8 KB
- references/primary-vs-secondary-plan-rules.md 893 B
- references/question-to-route-matching-rules.md 1.2 KB
- references/rejection-reason-framework.md 567 B
- references/route-comparison-dimensions.md 605 B
- references/workflow-step-template.md 350 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 · 299 lines · 87 tokens per session scan A 8e9f34626da8
primary-plan-recommender is a skill published in the GitHub repository aipoch/medical-research-skills (1,869 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 2,842 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.