tooluniverse-drug-research
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.
npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-drug-research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill guides an AI to produce a structured, multi-section drug research report. It emphasizes a report-first approach, resolving compound identities before researching, applying inline citations for every fact, and grading evidence strength. It requires the agent to use English names in tool calls, and to ensure all sections exist with placeholder content initially, then progressively fill them with data from multiple databases. It enforces comprehensive coverage across identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties, with mandatory completeness and explicit sourcing for every data point.
How it works
- Create the report file first: a markdown file named
[DRUG]_drug_report.mdwith all 11 section headers and[Researching...]placeholders. - For each data type, query multiple databases and cross-check results; update the corresponding section in real time, replacing placeholders with content.
- Follow the Critical Workflow Requirements: resolve compound identifiers before research, use all relevant tools, and maintain inline sources for every fact.
- Maintain a strict structure: populate sections such as Identity, Chemistry, Mechanism & Targets, ADMET, Clinical Development, Safety, Pharmacogenomics, Regulatory, Literature, Conclusions, and Data Sources.
- Include tables for structured data and narrative summaries for synthesis; ensure numbers and counts are explicit and sourced.
- Document all sources and tool calls in the dedicated Data Sources section.
When to use it
Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.
What it can touch
The skill uses the tool "claude-code" to perform tasks and relies on 50+ ToolUniverse databases and multiple standard drugs information sources (e.g., PubChem, ChEMBL, DailyMed, DGIdb, PharmGKB) as part of its workflow. It requires explicit source citations for each factual claim.
Caveats
- All data points must be sourced with inline references.
- The process emphasizes a report-first approach and complete section presence, even when data is unavailable.
- The output omits any discussion of non-supported speculative conclusions and sticks to documented facts with sources.
# Drug Research Strategy Comprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature. **KEY PRINCIPLES**: 1. **Report-first approach** - Create report file FIRST, then populate progressively 2. **Compound disambiguation FIRST** - Resolve identifiers before research 3. **Citation requirements** - Every fact must have inline source attribution 4. **Evidence grading** - Grade claims by evidence strength 5. **Mandatory completeness** - All sections must exist, even if "data unavailable" 6. **English-first queries** - Always use English drug/compound names in tool calls, even if the user writes in another language. Only try original-language terms as a fallback. Respond in the user's language --- ## Critical Workflow Requirements ### 1. Report-First Approach (MANDATORY) **DO NOT** show the search process or tool outputs to the user. Instead: 1. **Create the report file FIRST** - Before any data collection, create a markdown file: - File name: `[DRUG]_drug_report.md` (e.g., `metformin_drug_report.md`) - Initialize with all 11 section headers from the template - Add placeholder text: `[Researchi
- Critical Workflow Requirements
- 1. Report-First Approach (MANDATORY)
- 2. Citation Requirements (MANDATORY)
- Citation Format
- 3. Progressive Writing Workflow
- 4. Report Detail Requirements
- Initial Report Template (Create This First)
- FDA Label Core Fields Bundle
- Critical Label Sections
- Label Extraction Strategy
- Compound Disambiguation (Phase 1)
- Identifier Resolution Chain
- Handle Naming Ambiguity
- Tool Chains by Research Path
What does the tooluniverse-drug-research skill do?
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-drug-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.