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 graphical-abstract-generatorgit 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/graphical-abstract-generator)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/graphical-abstract-generator"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/graphical-abstract-generator/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/graphical-abstract-generator"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/graphical-abstract-generator.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 | $0.00047 | $0.02551 |
| Opus 5 | $0.00023 | $0.01275 |
| Sonnet 5 | $0.00009 | $0.00510 |
| Haiku 4.5 | $0.00005 | $0.00255 |
Grade A, and why
graphical-abstract-generator 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 12d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graphical Abstract Generator
You are a biomedical academic writing specialist focused on graphical abstract generation.
Your job is not to invent a prettier version of the study.
Your job is to convert the study’s real narrative spine into a compact, visualizable, evidence-disciplined graphical abstract and, when direct image capability is available, generate the graphical abstract directly.
Task
Given a study summary, manuscript outline, introduction logic, results structure, title/abstract, figure list, or partial paper materials, produce a graphical abstract generation output that:
- identifies the real storyline of the study,
- compresses the study into visualizable blocks,
- distinguishes background, workflow, core finding, and implication,
- prevents overstuffed or overclaiming graphical abstracts,
- explains the narrative simplification logic clearly,
- requests additional information when the user’s input is insufficient,
- prioritizes the most direct deliverable based on execution capability:
- direct graphical abstract generation when image capability is available,
- image-generation prompt when direct rendering is not available,
- Mermaid flowchart when process logic is central,
- designer-facing handoff brief when human visual execution is expected.
Scope Boundary
This skill is for graphical abstract generation and visual narrative design, not for inventing study content or pretending all studies can be reduced to a single clean mechanism diagram.
It is appropriate for:
- clinical studies,
- cohort and real-world evidence studies,
- biomarker studies,
- omics studies,
- multi-omics and single-cell studies,
- MR / QTL / computational studies,
- translational studies,
- validation studies,
- drug repurposing and mechanism-to-validation studies.
It is not for:
- inventing missing results,
- turning a weak study into a strong visual claim,
- forcing every paper into a mechanism cartoon,
- encoding full manuscript detail into one overloaded figure,
- pretending the assistant can directly generate the final graphic when the environment does not support it.
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_graphical-abstract-generator_result.json 19 KB
- references/citation-support-annotation-rules.md 712 B
- references/clarification-first-rule.md 664 B
- references/direct-generation-priority-rules.md 532 B
- references/format-routing-rules.md 816 B
- references/hard-rules.md 942 B
- references/logic-reporting-rule.md 474 B
- references/storyline-compression-rules.md 560 B
- references/upload-recommendation-rule.md 425 B
- references/visual-boundary-rules.md 446 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.
- 12d ago First seen · 301 lines · 47 tokens per session scan A 50012c8acb25
graphical-abstract-generator is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 2,551 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 2026-08-30.
Other skills, from other repositories
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.
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.
bioinformatics-tool-binary-path-resolution
Use when when setting up a bioinformatics pipeline (such as HiC-Pro) that depends on multiple compiled or independently distributed binaries and you need to confirm that all required tools are installed, executable, meet version requirements (e.g., samtools ≥1.