ipd-skill

Query the IPD REST API for HLA allele and cell metadata summaries.

5.3k|765|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/openai/plugins --skill ipd-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ipd-skill
Source: https://github.com/openai/plugins/tree/main/plugins/life-science-research/skills/ipd-skill
Command: npx skills add https://github.com/openai/plugins --skill ipd-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Researchers working with immunogenetics data often need quick, compact summaries of HLA alleles and cell records from the IPD (Immuno Polymorphism Database) without downloading and parsing large raw API responses manually.

Core Features & Use Cases

  • Compact IPD Queries: Submit REST requests to the public IPD API endpoints (allele, cell, allele/download) and receive trimmed, readable summaries instead of full payloads.
  • Controlled Output Size: Limit record counts, nesting depth, and string lengths so responses stay concise in conversation context.
  • Optional Raw Export: Save full JSON or text responses to disk only when explicitly requested via save_raw.
  • Use Case: A researcher asks for the first 10 HLA alleles matching "A*01"; the Skill queries the IPD allele endpoint with project=HLA and returns a compact markdown summary of matching records.

Quick Start

Ask the assistant to list the first 10 HLA alleles from the IPD database using the ipd-skill.

Frequently Asked Questions about ipd-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query the IPD database for HLA alleles?

Send a JSON object to scripts/rest_request.py with base_url set to the IPD API, path set to allele, and params including project=HLA and a limit. The script returns a compact list of matching allele records.

What IPD API endpoints does this skill support?

The skill targets the public IPD query API at ebi.ac.uk, with the most stable routes being allele, cell, and allele/download. Other paths can be passed but these three are the recommended endpoints.

Can I filter HLA alleles by name in the IPD API?

Yes, pass a query parameter such as contains(name,"A*01") inside params along with project=HLA. The response is compacted to the requested max_items and max_depth.

How do I get the full raw JSON response instead of a summary?

Set save_raw to true in the input JSON and optionally provide raw_output_path. The full response is written to disk and the path is returned in the raw_output_path field.

Why does the IPD request return an invalid_input error?

The input must be a single JSON object with required string fields base_url and path, and optional fields must match expected types such as boolean save_raw or positive integer max_items. Method must be GET or POST.