hmdb-skill — Codex skill: search HMDB
A skill for searching metabolites, proteins, diseases, and pathways in the HMDB database. Submits compact requests and returns concise summaries.
npx skills add openai/plugins --skill hmdb-skill -a codexWhat hmdb-skill does
hmdb-skill uses scripts/rest_request.py for all HMDB queries. The unearth/q endpoint handles searches with query, category, and format=json parameters. Results are capped at 10 items via per_page=10 and max_items=10 to keep responses compact.
By default, the skill returns markdown summaries from the JSON response. If you need the full payload, set save_raw=true and the skill reports the file path. In long conversations, the skill resubmits requests instead of caching old results, ensuring fresh data from HMDB.
To install on Codex, run npx skills add openai/plugins --skill hmdb-skill; the skill then lives in .agents/skills/hmdb-skill/.
What it helps with
- find a molecule or metabolite in HMDB by name
- look up protein or enzyme information
- search for a disease in the database
- explore a biochemical pathway
- get a concise search result summary
Example prompts for the agent
- Find the structure of serotonin in HMDB
- Show me pathways related to glycolysis in HMDB
- Search HMDB for diabetes and give me a brief report
How to install hmdb-skill
1Skills CLI (Vercel)
npx skills add openai/plugins --skill hmdb-skill -a codex2Manually: put the files in place
.agents/skills/hmdb-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill hmdb-skill -a claude-code2Manually: put the files in place
~/.claude/skills/hmdb-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/hmdb-skill/
Manually: put the files in place
.cursor/skills/hmdb-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins hmdb-skill2Manually: put the files in place
.github/skills/hmdb-skill/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/life-science-research/skills/hmdb-skillManually: put the files in place
.devin/skills/hmdb-skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set201
The whole set →Similar
Questions about hmdb-skill
How do I install hmdb-skill in Codex?
Run npx skills add openai/plugins --skill hmdb-skill. The skill installs to .agents/skills/hmdb-skill/SKILL.md.
What does hmdb-skill do?
It submits search queries to the HMDB database for metabolites, proteins, diseases, and pathways, returning compact markdown summaries. Each search is limited to 10 results.
How do I get the full response instead of a summary?
Set save_raw=true in the request parameters; the skill will save the full payload and report the file path.