---
title: "niaid-blueprint"
description: "Agent skills and MCP access for implementing the NIAID Blueprint for Digital Objects: FAIR assessment, dataset metadata intake and extraction, citation, validation, teaching, and model-influence disclosure."
canonical: https://agentpluginsdirectory.com/plugins/niaid-blueprint
last-updated: 2026-09-26
---

# niaid-blueprint
Agent skills and MCP access for implementing the NIAID Blueprint for Digital Objects: FAIR assessment, dataset metadata intake and extraction, citation, validation, teaching, and model-influence disclosure.
- Slug: niaid-blueprint
- Publisher: NIAID / GO FAIR US
- Repository: https://github.com/go-fair-us/ai-blueprint-core
- Manifest: niaid-blueprint/plugin.json
- Version: 0.1.0
- Category (editorial): research
- Skills: 8 (niaid-bp-citation, niaid-bp-dataset-intake, niaid-bp-fair-assess, niaid-bp-metadata-extract, niaid-bp-model-influence, niaid-bp-shaclrules, niaid-bp-teach, niaid-bp-validation)
- MCP servers: 1 (ai-blueprint)
- Stars: 1
- Repository created: 2026-05-20
- Repository last pushed: 2026-08-24
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/niaid-blueprint
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What niaid-blueprint does, in the publisher's words

AI agent tools help NIAID-funded data repositories apply the NIAID Blueprint for Digital Objects.

The Blueprint is a FAIR data program from NIAID/ODSET. It defines minimal metadata schemas, persistent identifiers (PIDs), API standards, and citation practices for research data repositories.

This project supplies LLM-driven agents, guided by structured prompt personas. The agents help repository owners and staff assess and apply Blueprint requirements in five areas:

- Metadata schema: schema.org-based metadata elements for digital objects
- Persistent identifiers: DOIs, ORCIDs, RORs, RRIDs, and ontology terms
- APIs and machine access: JSON-LD endpoints, OpenAPI documentation, structured data
- Citation guidance: PID-based citation examples in standard formats
- Outreach and training: Contact Points, training materials, Portal onboarding

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/go-fair-us/ai-blueprint-core/HEAD/README.md

## Skills

- niaid-bp-citation: Guide users through generating citation text and BibTeX entries aligned with the NIAID Blueprint for Digital Objects (Section 4). Supports original-data deposits, reused-data attribution, and repository-level citations with PID integration (DOI, RRID, ORCID). Use when the user wants citation exampl…
- niaid-bp-dataset-intake: Conducts a conversational interview to collect metadata for a schema.org Dataset and produces a valid JSON-LD document aligned with the NIAID Blueprint for Digital Objects. Covers all 16 Blueprint metadata elements across five natural groups: identity, provenance, content, access, and context. Use…
- niaid-bp-fair-assess: Conducts a structured NIAID Blueprint FAIR assessment interview across six phases (resource overview, metadata schema, persistent identifiers, APIs, citation, and outreach/training) and produces a prioritized gap report with actionable next steps. Use when a repository owner, data steward, or PI wa…
- niaid-bp-metadata-extract: Fetches a web resource URL and extracts Blueprint-aligned schema.org JSON-LD metadata (Table 1 elements) by retrieving and analyzing the target page. Produces a JSON-LD record plus metadata notes, no user interview required. Use when the user provides a dataset or resource URL for automatic extrac…
- niaid-bp-model-influence: Guide authors through developing a complete Model Influence Statement using the exact questions, fields, branching, and output structures from the Model Influence Statement Generator (https://model-influence-statement-generator.netlify.app/). Use when the user wants to create, fill out, or export a…
- niaid-bp-shaclrules: Run SHACL 1.2 Rules (SRL) with eyeleng via Deno: materialize inferred triples from DATA + RULE programs. Use when the user has an.srl file, wants SHACL Rules reasoning, says "run this SRL", "materialize rules", "eyeleng", or /niaid-bp-shaclrules. Not for Dataset pySHACL shape validation (use niaid…
- niaid-bp-teach: Teach the NIAID Blueprint for Digital Objects through stateful, multi-session lessons. Creates a persistent teaching workspace with MISSION.md, HTML lessons, learning records, glossary, and reference sheets. Grounds all claims in RESOURCES.md. Use when the user wants to learn or teach the Blueprint…
- niaid-bp-validation: Validate a schema.org Dataset graph (JSON-LD or Turtle) against NIAID Blueprint SHACL shapes using pySHACL. Emits a severity-aware conformance verdict plus structured violation results. Use when the user provides Dataset JSON-LD or Turtle for SHACL checks, wants Blueprint required-field validation,…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- ai-blueprint: transport: streamable-http; url: http://localhost:8000/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.