Agent skill

tooluniverse-disease-research

Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.

BioTender-maxgithub.com/BioTender-maxGitHub ↗
claude-codeNOASSERTION
Install
npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-disease-research --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 4
SKILL.md size: 18 KB
Bundled scripts: none
Path: skills/openclaw/tooluniverse-disease-research/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 135
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Generates a comprehensive disease research report in markdown, created as a file named after the disease, and progressively updated with findings across 10 research dimensions. Every fact includes a source reference and results are stored in a structured template that covers identity, clinical presentation, genetics, treatment, pathways, epidemiology, literature, similar diseases, cancer-specific info, and safety.

How it works

  • Initialize a disease-specific markdown report file named {Disease Name}_research_report.md with a 10-dimension template, then populate sections after researching each dimension.
  • For each dimension, use a suite of ToolUniverse tools (as listed in the skill) to retrieve data such as ontology identifiers, clinical phenotypes, genetic associations, drugs, pathways, literature, similar diseases, and safety data.
  • After completing each dimension, append findings to the corresponding section in the report and record full citations for every fact (tool name, query parameters, timestamp).
  • Ensure all disease names and search terms are in English for tool calls; use original-language terms only if English results are unavailable.
  • Do not expose the search process to the user; present a final, citation-backed report.

When to use it

  • When a user asks about any disease, syndrome, or medical condition.
  • When comprehensive disease intelligence is required.
  • When a detailed report with citations is needed.
  • When the user asks, "what do we know about [disease]?"

What it can touch

  • The skill references a set of tools (e.g., OSL_get_efo_id_by_disease_name, icd_search_codes, umls_search_concepts, ols_get_efo_term, ols_get_efo_term_children, OpenTargets_get_disease_id_description_by_name, and many others) to fetch data across dimensions. The exact tools appear in the workflow sections of the skill and are used to gather data and generate citations.

Caveats

  • The workflow relies on multiple external data sources and tools; results depend on tool availability and data currency. The skill mandates that every fact includes a source and that the report is progressively updated after each dimension.
  • The license field is NOASSERTION; no explicit licensing terms for usage are stated beyond the tool usage rules within the skill itself.
From the SKILL.md

# ToolUniverse Disease Research Generate a comprehensive, detailed disease research report with full source citations. The report is created as a markdown file and progressively updated during research. **IMPORTANT**: Always use English disease names and search terms in tool calls, even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language. ## When to Use Apply when the user: - Asks about any disease, syndrome, or medical condition - Needs comprehensive disease intelligence - Wants a detailed research report with citations - Asks "what do we know about [disease]?" ## Core Workflow: Report-First Approach **DO NOT** show the search process to the user. Instead: 1. **Create report file first** - Initialize `{disease_name}_research_report.md` 2. **Research each dimension** - Use all relevant tools 3. **Update report progressively** - Write findings to file after each dimension 4. **Include citations** - Every fact must reference its source tool ``` User: "Research Parkinson's disease" Agent Actions (internal, not shown to user): 1. Create "parkinsons_disease_research_report.md" with template

What's inside
Steps it walks through
  1. When to Use
  2. Core Workflow: Report-First Approach
  3. Report Template
  4. Research Protocol
  5. Step 1: Initialize Report
  6. Step 2: Research Each Dimension with Citations
  7. Step 3: Update Report File After Each Dimension
  8. Complete Tool Usage by Section
  9. Section 1: Identity (use ALL of these)
  10. Section 2: Clinical Presentation (use ALL of these)
  11. Section 3: Genetics (use ALL of these)
  12. Section 4: Treatment (use ALL of these)
  13. Section 5: Pathways (use ALL of these)
  14. Section 6: Literature (use ALL of these)
Ships with 3 files
  • EXAMPLES.md
  • README.md
  • TOOLS_REFERENCE.md
More from awesome-bio-agent-skills
All skills →
About this skill
What does the tooluniverse-disease-research skill do?

Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.

How do I install it?

Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-disease-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going