qsong-github/drugclaw/dilirank
Claude Code and agent skill by qsong-github/drugclaw
- community
Checking that the SKILL.md file is still in the repository.
Query the DILIrank/FDA Liver Toxicity Knowledge Base (LTKB). Use whenever the user asks about drug-induced liver injury (DILI) risk, hepatotoxicity classification, or wants to look up any drug (by name, LTKB ID, or DILIst ID) in the DILIrank or DILIst datasets.
Install
npx vskill@latest install qsong-github/drugclaw/dilirankSKILL.md
The same SKILL.md was published earlier as gabrielmoreira/agent-skills-mirror/dilirank.
LTKB Query Skill
Search FDA LTKB records (DILIrank 2.0 + DILIst) by any entity. Auto-detects type by pattern:
| Input Pattern | Detected As | Searched In | |
|---|---|---|---|
LT00040 | LTKB ID | DILIrank only | |
2 (digits) | DILIst ID | DILIst only | |
| anything else | drug name | both datasets (substring) |
Datasets
DILIrank 2.0 — 1,036 FDA-approved drugs ranked by DILI concern:
| vDILI-Concern | Meaning | |
|---|---|---|
| vMOST-DILI-concern | Strong evidence of causing DILI | |
| vLess-DILI-concern | Some evidence of causing DILI | |
| vNo-DILI-concern | No credible evidence | |
| vAmbiguous-DILI-concern | Conflicting/insufficient evidence |
Columns: LTKBID, CompoundName, SeverityClass, LabelSection, vDILI-Concern, Comment
DILIst — 1,279 drugs classified by DILI severity:
| Classification | Meaning | |
|---|---|---|
| 1 | DILI-positive | |
| 0 | DILI-negative |
Columns: DILIST_ID, CompoundName, DILIst Classification, Routs of Administration
API
| Function | Input | Returns | |
|---|---|---|---|
load_all(rank_path, list_path) | Excel paths | {"dilirank": [...], "dilist": [...]} | |
search(data, entity) | data dict + entity string | {"entity", "type", "dilirank": [], "dilist": []} | |
search_batch(data, entities) | data dict + list of strings | {entity: search_result} | |
summarize(result, entity) | search result + label | compact text | |
to_json(result) | search result | JSON string |
Usage
See if __name__ == "__main__" block in 48_LTKB.py for runnable examples covering: drug name, LTKB ID, DILIst ID, batch search, and JSON output.
Data
- Source: FDA LTKB — <https://www.fda.gov/science-research/bioinformatics-tools/liver-toxicity-knowledge-base-ltkb>
- Files:
Drug Induced Liver Injury Rank (DILIrank 2.0) Dataset FDA.xlsx,DILIst Supplementary Table.xlsx - Path:
DATA_DIRvariable in48_LTKB.py
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/drug_toxicity/dilirank/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
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/dilirank)