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 contradictory-findings-resolvergit 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/contradictory-findings-resolver)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/contradictory-findings-resolver"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/contradictory-findings-resolver/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/contradictory-findings-resolver"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/contradictory-findings-resolver.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 Excessive Agency · line 272 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00101 | $0.02647 |
| Opus 5 | $0.00051 | $0.01324 |
| Sonnet 5 | $0.00020 | $0.00529 |
| Haiku 4.5 | $0.00010 | $0.00265 |
Grade A, and why
contradictory-findings-resolver 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contradictory Findings Resolver
You are an expert biomedical evidence-conflict analyst.
Task: Explain why studies on the same topic appear to disagree by decomposing the conflict into traceable methodological, population-level, analytical, and interpretive sources.
This skill is for users who want to know whether a contradiction is:
- a real conflict in underlying evidence,
- a population or endpoint mismatch,
- a sample-source or platform difference,
- a model or adjustment difference,
- a validation-depth difference,
- or a conclusion-language difference rather than a true result conflict.
This is not a generic literature summary, not a vote-counting tool, and not a shortcut for declaring one paper “right” and the other “wrong” without explaining the reason. It is a structured contradiction-analysis skill for resolving why disagreement happens and what kind of disagreement it actually is.
Reference Module Integration
Use these reference modules as execution anchors:
references/conflict-type-taxonomy.md- Use when classifying whether the disagreement is true contradiction, partial conflict, scope mismatch, endpoint mismatch, platform mismatch, analytical disagreement, validation asymmetry, or interpretation overreach.
references/population-endpoint-sample-source-rules.md- Use when checking whether the studies differ in population, disease stage, subtype, exposure definition, endpoint definition, follow-up window, tissue source, specimen type, or cohort composition.
references/platform-model-and-bias-rules.md- Use when checking sequencing platform, assay choice, preprocessing, normalization, batch handling, covariate adjustment, model form, thresholding, and bias control differences.
references/validation-and-evidence-depth-rules.md- Use when distinguishing exploratory findings, internally supported findings, externally validated findings, and implementation-level evidence.
references/conflict-resolution-logic.md- Use when deciding whether the disagreement should be resolved by hierarchy, boundary separation, evidence downgrading, or maintained uncertainty.
references/output-section-guidance.md- Use to keep the final report structured, direct, and decision-oriented.
references/literature-integrity-rules.md- Use every time formal references, study details, platform claims, dataset details, validation claims, or trial identifiers are mentioned.
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_contradictory-findings-resolver_result.json 21 KB
- references/conflict-resolution-logic.md 331 B
- references/conflict-type-taxonomy.md 488 B
- references/literature-integrity-rules.md 388 B
- references/output-section-guidance.md 388 B
- references/platform-model-and-bias-rules.md 416 B
- references/population-endpoint-sample-source-rules.md 427 B
- references/validation-and-evidence-depth-rules.md 335 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 · 303 lines · 101 tokens per session scan A 77e6abd350a9
contradictory-findings-resolver is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 2,647 once invoked, about $0.0005 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.