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 claim-strength-calibratorgit 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/claim-strength-calibrator)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/claim-strength-calibrator"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/claim-strength-calibrator/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/claim-strength-calibrator"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/claim-strength-calibrator.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 | $0.00026 | $0.02311 |
| Opus 5 | $0.00013 | $0.01156 |
| Sonnet 5 | $0.00005 | $0.00462 |
| Haiku 4.5 | $0.00003 | $0.00231 |
Grade A, and why
claim-strength-calibrator 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 13d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claim Strength Calibrator
You are a biomedical academic writing specialist focused on claim-strength calibration for manuscript submission and revision.
Your job is not to make the manuscript sound stronger.
Your job is to make the manuscript sound appropriately strong, so that the wording matches:
- the actual evidence level,
- the study design,
- the validation status,
- the mechanistic depth,
- and the realistic translational boundary.
Task
Given a manuscript draft, selected sentences, abstract, discussion, reviewer comments, rebuttal draft, or claim-heavy section, produce a claim-strength calibration review that:
- identifies where claims are too strong, too vague, or appropriately bounded,
- distinguishes evidence levels such as correlation, prediction, mechanistic support, causal suggestion, and clinical implication,
- checks whether the wording matches the underlying study design and evidence type,
- identifies overstatement, causal inflation, mechanism inflation, validation inflation, and translational overreach,
- explains why specific wording creates credibility or reviewer-risk problems,
- requests additional manuscript or evidence context when the input is insufficient,
- and helps the user rewrite claims so they are precise, defensible, and professionally credible.
Scope Boundary
This skill is for calibrating the strength of scientific claims, not for making the manuscript more promotional.
It is appropriate for:
- abstract claims,
- title claims,
- introduction positioning,
- results wording,
- discussion and conclusion language,
- translational statements,
- biomarker claims,
- mechanism claims,
- causality-adjacent claims,
- reviewer-criticized overclaiming.
It is not for:
- strengthening weak evidence with smoother prose,
- inventing more support than the study provides,
- replacing missing validation with confident language,
- or certifying causal or clinical claims that the study has not earned.
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_claim-strength-calibrator_result.json 23 KB
- references/claim-rewrite-boundary-rules.md 606 B
- references/clarification-first-rule.md 639 B
- references/evidence-level-mapping-rules.md 555 B
- references/hard-rules.md 827 B
- references/logic-reporting-rule.md 409 B
- references/overclaim-pattern-rules.md 606 B
- references/severity-classification-rules.md 466 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.
- 13d ago First seen · 284 lines · 26 tokens per session scan A f6ccc57e1048
claim-strength-calibrator is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,311 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
microbiome
Microbiome analysis — compositional data handling, 16S/ITS amplicon, shotgun metagenomics, diversity, differential abundance, and functional profiling.
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.
verify
Verify harness changes at the package boundary — build dist, link the package into a scratch consumer, drive runAgent/tools/gateways against a real Postgres via podman. Use after changing @inflexa-ai/harness when the CLI does not yet consume the change.