A scientific-literature extraction tool for finding dataset details in a paper or other research reference. GEO is a public repository of gene-expression and other biological datasets; the tool can extract its dataset identifiers and related metadata.

Use it with a PDF, URL, DOI, PubMed ID, or text to identify GEO accessions, collect metadata, download datasets, and create a handoff for later omics analysis.

It saves researchers from manually searching papers and repositories for the data needed in a downstream biological analysis. It can also download the referenced GEO data when requested.

literature — Skill for Claude Code and Codex by TianGzlab

Install

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.

Any agent

npx skills add TianGzlab/OmicsClaw --skill literature

Clone the repo

git clone --depth 1 https://github.com/TianGzlab/OmicsClaw

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/literature.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/literature)

Your own site

<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/literature"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/literature.svg" alt="Measured on agentmods" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,209 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

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 →

high Rogue Agent · line 3
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00058	$0.01209
Opus 5	$0.00029	$0.00605
Sonnet 5	$0.00012	$0.00242
Haiku 4.5	$0.00006	$0.00121

Measured 8d ago against content hash a5ae01bb5336, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

literature 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 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (core/__init__.py, core/downloader.py, core/extractor.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/literature/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

literature

When to use

The user provides a scientific paper reference (PDF path, URL, DOI, PubMed ID, or raw text excerpt) and wants OmicsClaw to extract GEO accessions, dataset metadata, and (optionally) download referenced GEO datasets — so a downstream analysis skill can be invoked on real data.

--input-type defaults to auto (sniffs from input shape). --no-download skips the GEO download step (metadata only).

For dispatching a NL query to an analysis skill use orchestrator. For scaffolding a new skill from a paper use omics-skill-builder.

Inputs & Outputs

Inputs

Input kinds: file, freeform
File types: .pdf

Outputs

extracted_metadata.json
report.md
result.json
<--data-dir>/<GSEid>/...
Produces artifact literature.dataset_handoff as extracted_metadata.json (json)

Flow

Parse --input (or --demo); raise parser.error('the following arguments are required: --input (unless --demo is used)') at literature_parse.py:38 when missing.
Detect input type (URL / DOI / PubMed / PDF / text) via --input-type auto or honour the explicit value.
Call parse_input (skills/literature/core/parser.py); fetch / parse content.
Call extract_metadata (skills/literature/core/extractor.py) → identify GEO accessions, dataset metadata, study type.
If GEO accessions found AND not --no-download: call download_geo_dataset (skills/literature/core/downloader.py) → save to --data-dir.
Write extracted_metadata.json (literature_parse.py:80) + report.md (:193) + result.json (:147).

Gotchas

--input REQUIRED unless --demo — uses parser.error (exit 2). literature_parse.py:38 calls parser.error('the following arguments are required: --input (unless --demo is used)'). Different from most file-pipeline skills which raise ValueError.
--input-type auto heuristics are positional, not URL-aware. core/parser.py:35-55 checks the bare-DOI regex ^10\.\d{4,}/\S+ first; URLs always hit the startswith("http") branch and resolve to url, even when they wrap a DOI (https://doi.org/10.1038/...). For PDF / file paths use --input-type file explicitly — Path.exists() has to succeed for auto-detection to pick file.
GEO download requires internet access. download_geo_dataset issues HTTP requests to GEO FTP. Air-gapped runs must pass --no-download or the run will hang / time out.
PDF parsing requires pypdf / similar. If the PDF parser dependency is missing, the run errors out — verify skills/literature/requirements.txt is satisfied.
extracted_metadata.json is at output_dir/ ROOT, not tables/. This skill does NOT follow the tables/<file>.csv convention used by analysis skills.
Empty / unparseable input ⇒ exit 1 (not 2). literature_parse.py:64 calls sys.exit(1) on internal parse failure (distinct from the parser.error exit-2 path for missing args).

Read the full file on GitHub · 100 lines

Files

What ships with it

11 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.

Changes

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.

8d ago First seen · 100 lines · 58 tokens per session scan A a5ae01bb5336

Subscribe to this mod's changes

literature is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,209 once invoked, about $0.0003 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.

Data and AI Documents Literature PDF Research Single-Cell bioinformatics doi geo knowledge-graph llm-agent metadata multi-agents multi-omics pubmed

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

alterlab-markitdown

Convert files and Office documents to clean, LLM-friendly Markdown with Microsoft MarkItDown (markitdown CLI/Python), supporting PDF, DOCX, PPTX, XLSX, images (EXIF + OCR), audio (transcription), HTML, CSV, JSON, XML, ZIP archives, EPUB e-books, and YouTube transcript URLs, with optional AI image descriptions. Use…

AlterLab-IEU/AlterLab-Academic-Skills · 147 tokens

sec-report

SEC (size-exclusion chromatography) analysis with peak detection, oligomer classification, and publication-quality PDF report generation via Typst templates. Triggers on "SEC", "size exclusion", "chromatography", "oligomer analysis", "protein assembly", "SEC report".

Runchuan-BU/BioClaw · 59 tokens

report-template

Publication-quality PDF report generation using Typst templates. Produces professional scientific reports with colored section bands, styled tables, figure captions, callout boxes, and page headers/footers.

Runchuan-BU/BioClaw · 40 tokens

ai-science-vision-rag

ColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL, no OCR. Use for PDF/document QA over figures and tables, multimodal retrieval, or Recall@k/MRR eval.

Pavel-Kravchenko/Bioinformatics · 65 tokens

liteparse

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…

K-Dense-AI/scientific-agent-skills · 86 tokens

literature

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

literature

When to use

Inputs & Outputs

Flow

Gotchas

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

markitdown

alterlab-markitdown

sec-report

report-template

ai-science-vision-rag

liteparse