Tooluniverse Drug Research
This is a comprehensive drug profiling system that hits 50+ databases to build full investigation reports. It's built around a "report first" workflow where you create the output file immediately, then progressively fill sections as it queries ChEMBL, PubChem, FAERS, ClinicalTrials.gov, PharmGKB, and FDA databases. Everything needs inline citations and evidence grading. The mechanism reasoning is thorough, tracing from target binding through to physiological outcome. It includes extensive fallback chains when APIs fail and has detailed instructions to avoid common pitfalls like using the wrong ChEMBL endpoint. Best for clinicians, researchers, or regulatory work where you need a complete, cited drug profile rather than a quick lookup.
- skills.sh installs
- 474
- GitHub stars
- 1.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-drug-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
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 (T1-T4)
- 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
LOOK UP, DON'T GUESS
When asked about a drug, query ChEMBL/PubChem/DailyMed FIRST. Don't guess at mechanism, targets, or side effects — look them up. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.
Drug Mechanism Reasoning
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/mims-harvard/tooluniverse
- Categories
- Data Science & ML, Debugging
- First seen
- Jun 3, 2026
More from mims-harvard/tooluniverse
All 68- Tooluniverse Clinical Trial Design458
- Tooluniverse Drug Drug Interaction457
- Setup Tooluniverse448
- Tooluniverse Disease Research439
- Tooluniverse Systems Biology436
- Tooluniverse Protein Structure Retrieval435
- Tooluniverse Network Pharmacology434
- Tooluniverse Precision Oncology426
- Tooluniverse Epigenomics425
- Tooluniverse Pharmacovigilance424
- Tooluniverse Chemical Compound Retrieval419
- Create Tooluniverse Skill412
- Tooluniverse Proteomics Analysis412
- Tooluniverse Target Research412
- Tooluniverse Spatial Transcriptomics411
- Tooluniverse Rare Disease Diagnosis410
- Tooluniverse Rnaseq Deseq2409
- Tooluniverse Expression Data Retrieval407
- Tooluniverse Statistical Modeling407
- Tooluniverse Clinical Trial Matching406
- Tooluniverse Drug Repurposing400
- Tooluniverse Multi Omics Integration400
- Tooluniverse Protein Therapeutic Design400
- Tooluniverse Sdk399
Recommended
More Data Science & ML
domain-researchopenclaudia/openclaudia-skillsResearch domain WHOIS data and check marketplace listings. Use when the user says "domain lookup", "check domain", "WHOIS", "domain availability", "buy domain",463skills.sh installs
bioinformatics-fundamentalsdelphine-l/claude_globalCore bioinformatics concepts including SAM/BAM format, AGP genome assembly format, sequencing technologies (Hi-C, HiFi, Illumina), quality metrics, and common d446skills.sh installs
tooluniverse-disease-researchmims-harvard/tooluniverseGenerate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing 439skills.sh installs
core-mlrshankras/claude-code-apple-skillsCore ML, Create ML, Vision framework, Natural Language framework, on-device ML integration. Use when user wants image classification, text analysis, object dete427skills.sh installs
data-and-funnel-analyticsmanojbajaj95/claude-gtm-pluginAnalytics tracking, interpretation, funnel analysis, product metrics, and ROI measurement. Use when setting up GA4/GTM tracking, interpreting analytics data, an426skills.sh installs