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 litbasegit 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/litbase)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/litbase"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/litbase/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/litbase"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/litbase.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 | $0.00071 | $0.01474 |
| Opus 5 | $0.00036 | $0.00737 |
| Sonnet 5 | $0.00014 | $0.00295 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
litbase 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LitBase
An academic paper reading and research development system running inside Claude Code (or any compatible agent environment). Built for biomedical researchers who want to find papers, build structured reading notes, track discussion insights, and ultimately synthesize their literature base into a research proposal.
Paper source: Semantic Scholar — free, no login required, 200M+ papers across all disciplines.
Quick Start
Step 1 — Edit config.json with your research folder path:
{
"data_dir": "/path/to/your/research/folder",
"s2_api_key": "optional — leave empty to use free tier",
"mode": "auto"
}
Step 2 — Open this folder in Claude Code, then type /setup.
The setup command configures everything automatically — no terminal commands needed.
Commands
| Command | When to use | What it does |
|---|---|---|
/setup |
First use | Guided research profile setup; auto-configures environment |
/feed |
Daily | Updates search terms → searches Semantic Scholar → recommends papers |
/read |
Per paper | Submit a PDF path, DOI, or abstract → generates 4-section structured note |
/discuss [keyword] |
Deep dive | Locate a paper note by author/title/keyword and discuss; auto-records insights |
/recap |
Weekly review | Reading overview, framework completeness map, next-step recommendations |
/update |
Direction shift | Sync research direction changes to memory and search terms |
/sync |
Maintenance | Cross-document consistency check; literature integrity audit |
/propose |
Proposal stage | Synthesizes reading notes into a Research Foundation Document (RFD) for downstream protocol design |
Note Structure
Each paper analysis is structured in four sections:
| Section | Content |
|---|---|
| I. Paper Weight | Journal/conference rank, IF, database indexing (SSCI/Scopus/etc.), Q-rank; each author's institution, position, h-index; citation count and yearly average; overall assessment |
| II. Paper Highlights | Methodological innovation / critique of systemic problems / significance of the research object |
| III. Transferable Elements | Theory framework, method details, conceptual tools — each tagged to which part of the user's own paper it can support |
| IV. How to Use in Your Paper | Literature review positioning, suggested citation phrases (English), methodological precedent, research motivation |
What ships with it
47 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.
- .gitignore 120 B
- CLAUDE.md 4.9 KB
- commands/discuss.md 3.4 KB
- commands/feed.md 3.4 KB
- commands/propose.md 7.7 KB
- commands/read.md 5.6 KB
- commands/recap.md 2.7 KB
- commands/setup.md 5.8 KB
- commands/sync.md 2.6 KB
- commands/update.md 2.5 KB
- config.json 144 B
- core/.gitignore 120 B
- core/CLAUDE.md 5.0 KB
- core/commands/discuss.md 3.4 KB
- core/commands/feed.md 3.4 KB
- core/commands/propose.md 11 KB
- core/commands/read.md 5.6 KB
- core/commands/recap.md 2.7 KB
- core/commands/setup.md 5.8 KB
- core/commands/sync.md 2.6 KB
- core/commands/update.md 2.5 KB
- core/config.json 144 B
- core/install.sh 1.6 KB runs code
- core/memory/MEMORY.md 2.2 KB
- core/notes/reading_list.md 741 B
- core/notes/WORKFLOW.md 3.0 KB
- core/README.md 4.8 KB
- core/references/LITERATURE_HARD_RULES.md 2.5 KB
- core/references/SESSION_CARD_TEMPLATE.md 1.9 KB
- core/scripts/lookup_paper.py 4.3 KB runs code
- core/scripts/recommend.py 4.3 KB runs code
- core/scripts/rename_pdfs.py 5.9 KB runs code
- core/search_config.json 567 B
- core/settings.local.json 258 B
- eval_report_litbase_result.json 21 KB
- install.sh 1.7 KB runs code
- LITERATURE_HARD_RULES.md 2.5 KB
- lookup_paper.py 3.6 KB runs code
- memory/MEMORY.md 4.4 KB
- notes/reading_list.md 726 B
- notes/WORKFLOW.md 2.9 KB
- README.md 4.8 KB
- recommend.py 4.3 KB runs code
- rename_pdfs.py 6.1 KB runs code
- search_config.json 2.1 KB
- SESSION_CARD_TEMPLATE.md 1.9 KB
- settings.local.json 258 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 · 154 lines · 71 tokens per session scan A 8c519a1ce258
litbase is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,474 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.