Query canonical TarKG drug-target triplets. Use when the user asks about drug-target interactions, relation labels, disease/pathway context, or quick lookups for drugs/targets in TarKG.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add BioTender-max/awesome-bio-agent-skills --skill tarkg --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Tarkg?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/biotender-max-tarkg)More formats (shields.io, HTML) on the badges page.
---
name: TarKG
description: >
Query canonical TarKG drug-target triplets. Use when the user asks about
drug-target interactions, relation labels, disease/pathway context, or
quick lookups for drugs/targets in TarKG.
---
# TarKG Query Skill
Query the canonical packaged TarKG TSV output.
## Data
- Path: `resources_metadata/dti/TarKG/tarkg.tsv`
- Columns: `drug`, `target`, `relation`, `disease`, `pathway`
## API
| Function | Input | Returns |
|---|---|---|
| `load_tarkg(path)` | TSV path | `list[dict]` |
| `query_entity(entity, rows, limit)` | single entity string | `dict` |
| `query_entities(entities, path, limit)` | list of entity strings | `list[dict]` |
`query_entity` returns keys used by `retrieve.py`: `matched`, `node_info`,
`outgoing_edges`, `incoming_edges`, `candidates`.
## Usage
Run `example.py` directly for demo queries against the canonical TSV.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.