qsong-github/drugclaw/chembl
Claude Code and agent skill by qsong-github/drugclaw
- community
Checking that the SKILL.md file is still in the repository.
Query the ChEMBL database for drug molecules, bioactivity data, and drug targets via the ChEMBL REST API. Use whenever the user asks about drug properties (molecular weight, logP, Lipinski violations), drug-target interactions, bioactivity assay results, or wants to look up any entity by ChEMBL ID or drug/gene name in ChEMBL. Supports single entity or batch queries. No API key required.
Install
npx vskill@latest install qsong-github/drugclaw/chemblSKILL.md
ChEMBL Query Skill
Query ChEMBL bioactivity database for molecules, targets, and activity data. Auto-detects input type by prefix:
| Input Pattern | Detected As | Action | |
|---|---|---|---|
CHEMBL25 | ChEMBL ID (molecule) | direct fetch by ID | |
aspirin | drug name | substring search on pref_name | |
CHEMBL203 | ChEMBL ID (target) | direct fetch by ID | |
EGFR | gene/protein name | substring search on target_synonym |
API
| Function | Input | Returns | |
|---|---|---|---|
query_molecules(entities, limit) | str or list[str] — ChEMBL IDs or drug names | dict[str, list[dict]] | |
query_targets(entities, limit) | str or list[str] — ChEMBL IDs or gene names | dict[str, list[dict]] | |
query_bioactivities(chembl_ids, limit) | str or list[str] — molecule ChEMBL IDs | dict[str, list[dict]] | |
summarize_molecule(mol) | single molecule dict | compact one-line string | |
summarize_activity(act) | single activity dict | compact one-line string | |
summarize_target(tgt) | single target dict | compact one-line string |
Usage
See if __name__ == "__main__" block in chembl_query.py for runnable examples covering:
- Single molecule by ID —
query_molecules("CHEMBL25") - Batch molecule search by name —
query_molecules(["ibuprofen", "metformin"], limit=3) - Bioactivities for multiple molecules —
query_bioactivities(["CHEMBL25", "CHEMBL1642"], limit=3) - Single target by gene name —
query_targets("EGFR", limit=3) - Batch target lookup by ID —
query_targets(["CHEMBL203", "CHEMBL204"])
Key Fields
Molecule: molecule_chembl_id, pref_name, molecule_properties.full_mwt, molecule_properties.alogp, molecule_properties.num_ro5_violations
Activity: molecule_chembl_id, target_chembl_id, target_pref_name, standard_type, standard_value, standard_units
Target: target_chembl_id, pref_name, target_type, organism
Data Source
- API:
https://www.ebi.ac.uk/chembl/api/data(no key required) - Paper: https://doi.org/10.1093/nar/gkad1004
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/dti/chembl/SKILL.md
Popularity
- Repository stars
- 116
- Repository forks
- 3
- 7-day trend score
- 24
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 1 Oct 2026, a month 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/qsong-github/drugclaw/chembl)