gnomad-graphql-skill — Codex skill: what it does, how to install
This skill sends focused gnomAD GraphQL requests for variant frequency, gene constraint, and transcript context. Use it when an agent needs a concise summary.
npx skills add openai/plugins --skill gnomad-graphql-skill -a codexWhat gnomad-graphql-skill does
The skill routes gnomAD GraphQL work through scripts/gnomad_graphql.py. The script reads one JSON object from stdin with either query or query_path; optional fields include variables, max_items, max_depth, timeout_sec, save_raw, and raw_output_path.
By default, the agent returns a compact summary of the script JSON. It is suited to targeted requests for variant frequency, gene constraint, and transcript consequence context. Keep nested results bounded, and place long GraphQL documents in query_path.
Set save_raw=true when the complete payload is needed; the response then includes raw_output_path. Errors such as invalid_json, network_error, and graphql_error are returned explicitly, so a failed request is a reason to check the query format or gnomAD access.
What it helps with
- look up a variant frequency in gnomAD
- inspect constraint data for a gene
- retrieve transcript consequence context
- summarize a focused GraphQL response
- save the complete response to a file
Example prompts for the agent
- Look up the frequency of variant `1-55516888-G-GA` in dataset `gnomad_r4` and return a concise summary.
- Run a focused gnomAD GraphQL query for gene constraint using `query_path`.
- Repeat the gnomAD request and save the complete JSON with `save_raw=true`.
How to install gnomad-graphql-skill
1Skills CLI (Vercel)
npx skills add openai/plugins --skill gnomad-graphql-skill -a codex2Manually: put the files in place
.agents/skills/gnomad-graphql-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill gnomad-graphql-skill -a claude-code2Manually: put the files in place
~/.claude/skills/gnomad-graphql-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gnomad-graphql-skill/
Manually: put the files in place
.cursor/skills/gnomad-graphql-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins gnomad-graphql-skill2Manually: put the files in place
.github/skills/gnomad-graphql-skill/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/life-science-research/skills/gnomad-graphql-skillManually: put the files in place
.devin/skills/gnomad-graphql-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 gnomad-graphql-skill
How do I install gnomad-graphql-skill in Codex?
Run npx skills add openai/plugins --skill gnomad-graphql-skill, then run npx skills add openai/plugins --skill gnomad-graphql-skill -a codex. The installed skill file is .agents/skills/gnomad-graphql-skill/SKILL.md.
What does gnomad-graphql-skill do?
It sends focused GraphQL requests to gnomAD for variant frequency, gene constraint, and transcript context, then returns a concise summary or the complete JSON when requested.
What input does the script require?
The script expects JSON with either query or query_path. You can add variables for parameterized requests, while save_raw=true stores the complete response and returns its file path.
