Nia

Index and search code repositories, documentation, papers, and HuggingFace datasets via Nia API.

5|3|Updated Jan 9, 2026
One-click install
npx skills add https://github.com/nozomio-labs/nia-plugin --skill nia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Nia
Source: https://github.com/nozomio-labs/nia-plugin/tree/main/skills/nia
Command: npx skills add https://github.com/nozomio-labs/nia-plugin --skill nia

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Nia provides direct API access to index and search code repositories, documentation, research papers, and HuggingFace datasets, helping teams maintain up-to-date context and reduce hallucinations.

Core Features & Use Cases

  • Unified endpoints for indexing (repositories, documentation, papers, datasets), listing, reading, and cross-source search.
  • Deterministic workflows: check indexed sources, fetch repository trees, read files, and perform targeted searches across sources.
  • Use cases include indexing a GitHub repo, indexing docs, searching across code and docs, and saving findings for later reference.

Quick Start

Store your API key at ~/.config/nia/api_key and try:

  • Index a repository: ./scripts/repos-index.sh "owner/repo" [branch]
  • Index documentation: ./scripts/sources-index.sh "https://docs.example.com" [limit]
  • Search across all indexed sources: ./scripts/search-universal.sh "query"

Frequently Asked Questions about Nia

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

FAQPage Schema
How do I index and search across code repositories and research papers?

Indexing HuggingFace datasets works through a unified API that lists, reads, and searches data sources alongside code and documentation. This cross-source search capability enables contextual discovery and helps reduce hallucinations by maintaining current data context.

What do I need to configure before indexing documentation and datasets?

Before indexing documentation and datasets, you must store your API key at ~/.config/nia/api_key. Additionally, ensure curl and jq are installed as dependencies to execute the indexing and search shell scripts.

How do I index a GitHub repository branch using a search API?

To index a GitHub repository branch, run the repository indexing script with the owner/repo string and optional branch name. The script uses the /v2/sources endpoint to index the repository tree for subsequent cross-source searches.

Does this API search tool work with HuggingFace datasets?

Yes, the API search tool works with HuggingFace datasets. It exposes unified endpoints for indexing and searching datasets alongside code repositories, documentation, and research papers to enable contextual discovery.

What is the best way to search across indexed code and documentation simultaneously?

The best way to search across indexed code and documentation simultaneously is by using the universal search script. It queries the /v2/search endpoint to perform cross-source searches across all previously indexed repositories and data sources.