RepoDB Query Skill

SkillDatabases & data

Query the RepoDB drug repurposing database. Use whenever the user asks about drug-disease associations, drug repurposing candidates, or wants to look up any entity (drug name, indication, DrugBank ID, UMLS CUI, NCT ID) in RepoDB.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the RepoDB Query Skill skill

What this skill tells your AI

The instructions your AI receives, as published by qsong-github/drugclaw in skills/drug_repurposing/repodb/SKILL.md and read by ahel’s review.

Search RepoDB records by any entity. Auto-detects type by prefix:

Input Pattern	Detected As	Match Logic
`DB00584`	DrugBank ID	exact on `drugbank_id`
`C0020538`	UMLS CUI	exact on `ind_id`
`NCT00001234`	Trial ID	exact on `NCT`
anything else	free text	substring on `drug_name` OR `ind_name`

API

Function	Input	Returns
`load_repodb(path)`	CSV path	DataFrame
`search(df, entity)`	single entity string	DataFrame
`search_batch(df, entities)`	list of entity strings	dict[str, DataFrame]
`summarize(hits, entity)`	DataFrame + label	compact text
`to_json(hits)`	DataFrame	list[dict]

Usage

See if __name__ == "__main__" block in repodb_query.py for runnable examples covering: drug name, DrugBank ID, UMLS CUI, indication name, batch search, and JSON output.

Data

Source: full.csv (comma or tab separated, auto-detected)
Columns: drug_name, drugbank_id, ind_name, ind_id, NCT, status, phase, DetailedStatus
Path: DATA_PATH variable in repodb_query.py

Signals

GitHub stars: 116
Forks: 3
Last commit: Aug 2026

Advanced

Item type: skill
Key: repodb-query
Source: github.com/qsong-github/drugclaw

github.com/qsong-github/drugclaw

RepoDB Query Skill

What this skill tells your AI

API

Usage

Data

Signals

Related picks