wu-yc/labclaw/tooluniverse-drug-research
Claude Code and agent skill by wu-yc/labclaw
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install wu-yc/labclaw/tooluniverse-drug-researchSKILL.md
Drug Research Strategy
Comprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Compound disambiguation FIRST - Resolve identifiers before research
- Citation requirements - Every fact must have inline source attribution
- Evidence grading - Grade claims by evidence strength
- Mandatory completeness - All sections must exist, even if "data unavailable"
- 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:
- 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:
[Researching...]in each section
- Progressively update the report - As you gather data:
- Update each section with findings immediately after retrieving data
- Replace
[Researching...]with actual content - The user sees the report growing, not the search process
- Use ALL relevant tools - For comprehensive coverage:
- Query multiple databases for each data type
- Cross-reference information across sources
- Use fallback tools when primary tools return limited data
2. Citation Requirements (MANDATORY)
Every piece of information MUST include its source. Use inline citations:
Citation Format
For each data section, include at the end:
3. Progressive Writing Workflow
4. Report Detail Requirements
Each section must be comprehensive and detailed:
- Tables: Use tables for structured data (targets, trials, adverse events)
- Lists: Use bullet points for features, findings, key points
- Paragraphs: Include narrative summaries that synthesize findings
- Numbers: Include specific values, counts, percentages (not vague terms)
- Context: Explain what the data means, not just what it is
BAD (too brief):
GOOD (detailed with sources):
Initial Report Template (Create This First)
When starting research, immediately create this file before any tool calls:
File: [DRUG]_drug_report.md
Then progressively replace [Researching...] with actual findings as you query each tool.
FDA Label Core Fields Bundle
For approved drugs, ALWAYS retrieve these FDA label sections early (after getting set_id from DailyMed_search_spls):
Critical Label Sections
Call DailyMed_get_spl_sections_by_setid(setid=set_id, sections=[...]) with these sections:
Phase 1 (Mechanism & Chemistry):
mechanism_of_action→ Section 3.1pharmacodynamics→ Section 3.1chemistry→ Section 2.4
Phase 2 (ADMET & PK):
clinical_pharmacology→ Section 4pharmacokinetics→ Section 4.1-4.4drug_interactions→ Section 4.3, 6.5
Phase 3 (Safety & Dosing):
warnings_and_cautions→ Section 6.3adverse_reactions→ Section 6.1dosage_and_administration→ Section 6.6, 8.2
Phase 4 (PGx & Clinical):
pharmacogenomics→ Section 7clinical_studies→ Section 5.5description→ Section 2.5 (formulation)inactive_ingredients→ Section 2.5
Label Extraction Strategy
This ensures you have authoritative FDA-approved information even if prediction tools fail.
Compound Disambiguation (Phase 1)
CRITICAL: Establish compound identity before any research.
Identifier Resolution Chain
Handle Naming Ambiguity
| Issue | Example | Resolution | |
|---|---|---|---|
| Salt forms | metformin vs metformin HCl | Note all CIDs; use parent compound | |
| Isomers | omeprazole vs esomeprazole | Verify SMILES; separate entries if distinct | |
| Prodrugs | enalapril vs enalaprilat | Document both; note conversion | |
| Brand confusion | Different products same name | Clarify with user |
Tool Chains by Research Path
PATH 1: Chemical Properties & CMC
Objective: Full physicochemical profile, salt forms, formulation details
Multi-Step Chain:
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/pharma/tooluniverse-drug-research/SKILL.md
Popularity
- Repository stars
- 1,052
- Repository forks
- 161
- 7-day trend score
- 35
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 26 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/wu-yc/labclaw/tooluniverse-drug-research)