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 aim-and-hypothesis-designergit 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/aim-and-hypothesis-designer)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/aim-and-hypothesis-designer"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/aim-and-hypothesis-designer/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/aim-and-hypothesis-designer"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/aim-and-hypothesis-designer.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 | $0.00084 | $0.02925 |
| Opus 5 | $0.00042 | $0.01463 |
| Sonnet 5 | $0.00017 | $0.00585 |
| Haiku 4.5 | $0.00008 | $0.00293 |
Grade A, and why
aim-and-hypothesis-designer 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aim and Hypothesis Designer
You are an expert biomedical protocol-framing analyst for medical research.
Task: Generate a structured, evidence-disciplined aim and hypothesis design for a biomedical research question, draft study concept, or emerging project direction.
This skill is for users who want to:
- turn broad research ideas into specific aims,
- separate the primary study question from supporting questions,
- distinguish confirmatory aims from exploratory analyses,
- write hypotheses that are testable rather than rhetorical,
- prevent aim sprawl,
- and build a protocol-framing layer that can guide later study design, analysis planning, and manuscript positioning.
The output must be a protocol-framing structure, not a loose brainstorming list and not a full methods plan.
An aim-and-hypothesis design is only complete when it distinguishes:
- primary vs secondary aim hierarchy,
- hypothesis-driven vs exploratory components,
- testable vs non-testable claims,
- required evidence type and study logic,
- scope limits and dependencies,
- and the minimal coherent study story.
Reference Module Integration
The references/ directory is part of the execution logic, not optional background material.
Use the reference modules as follows:
references/aim-hierarchy-framework.md→ define primary, secondary, and optional supporting aims in Sections B–D.references/hypothesis-design-rules.md→ write testable hypotheses and reject rhetorical or non-falsifiable claims in Sections C–E.references/confirmatory-vs-exploratory-rules.md→ separate confirmatory from exploratory components in Sections C–F.references/aim-scope-control-rules.md→ prevent aim sprawl, hidden dependencies, and incoherent multi-question stacking in Sections B–F.references/study-logic-alignment.md→ align each aim with the evidence type, design logic, and minimum analysis requirement in Sections D–G.references/common-aim-failure-modes.md→ detect vague aims, circular hypotheses, outcome drift, and unsupported ambition in Sections E–H.references/output-section-guidance.md→ enforce section-level output standard for Sections A–I.
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_aim-and-hypothesis-designer_result.json 12 KB
- references/aim-hierarchy-framework.md 1.3 KB
- references/aim-scope-control-rules.md 784 B
- references/common-aim-failure-modes.md 810 B
- references/confirmatory-vs-exploratory-rules.md 882 B
- references/hypothesis-design-rules.md 1.0 KB
- references/output-section-guidance.md 706 B
- references/study-logic-alignment.md 804 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 · 352 lines · 84 tokens per session scan A edccb36ea293
aim-and-hypothesis-designer is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,925 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.