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 evidence-level-rankergit 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/evidence-level-ranker)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/evidence-level-ranker"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/evidence-level-ranker/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/evidence-level-ranker"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/evidence-level-ranker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 233 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00048 | $0.02708 |
| Opus 5 | $0.00024 | $0.01354 |
| Sonnet 5 | $0.00010 | $0.00542 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
evidence-level-ranker 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Level Ranker | 证据等级排序器
Task
Use this skill to rank papers by evidence strength, methodological quality, and citation priority within one explicit comparison framework.
This skill should identify what kind of evidence each paper provides, how much methodological trust it deserves, how much validation or corroboration it contains, and whether it should be treated as a high-priority anchor citation, context-setting citation, mechanistic support citation, or low-priority / caution citation.
This skill must not equate study design labels with true evidentiary value automatically. A meta-analysis is not automatically decisive, an RCT is not automatically well-conducted, a cohort is not automatically weak, and a mechanism study is not automatically non-informative. The skill must rank literature based on the combination of design family, execution quality, validation depth, bias control, and claim discipline.
This skill is especially useful when the user needs to:
- prioritize citations for a manuscript, review, protocol, or slide deck;
- compare reviews, observational studies, interventional studies, mechanism papers, omics studies, and validation studies in one framework;
- identify which papers are most suitable for supporting strong claims versus background framing;
- avoid treating flashy but fragile findings as top-tier evidence.
Reference Module Integration
Use reference modules as execution dependencies, not decoration.
references/evidence-family-taxonomy.md→ use when identifying study design family in Step 2.references/methodological-quality-audit-rules.md→ use when assessing execution quality in Step 3.references/validation-depth-rules.md→ use when judging internal vs. external vs. orthogonal validation in Step 4.references/claim-discipline-rules.md→ use when separating what a paper shows from what it claims in Step 5.references/citation-priority-rules.md→ use when assigning citation roles in Step 6.references/cross-design-ranking-framework.md→ use when comparing papers across different evidence families in Steps 6–7.references/literature-integrity-rules.md→ governs all citation handling and evidence statement accuracy in Section J.references/output-section-guidance.md→ enforces section-level output format for Sections A–J.references/workflow-step-template.md→ structures the workflow explanation.
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_evidence-level-ranker_result.json 23 KB
- references/citation-priority-rules.md 552 B
- references/claim-discipline-rules.md 403 B
- references/cross-design-ranking-framework.md 671 B
- references/evidence-family-taxonomy.md 939 B
- references/literature-integrity-rules.md 448 B
- references/methodological-quality-audit-rules.md 501 B
- references/output-section-guidance.md 312 B
- references/validation-depth-rules.md 425 B
- references/workflow-step-template.md 284 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 · 255 lines · 48 tokens per session scan A 0381e4f45bf5
evidence-level-ranker is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,708 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 2026-09-03.
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.