skills.rest
denson
densonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ariadne-document-intelligence

Ingest documents into Ariadne Core collections for semantic search and provenance tracking.

Updated Apr 10, 2026
Search Tags:#provenance#metadata#collections#semantic-search#document-ingestion#vector-embeddings
One-click install
npx skills add https://github.com/denson/ariadne-core --skill ariadne-document-intelligence
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ariadne-document-intelligence
Source: https://github.com/denson/ariadne-core/tree/main/skills/ariadne-document-intelligence
Command: npx skills add https://github.com/denson/ariadne-core --skill ariadne-document-intelligence

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

In AI workflows, users waste tokens parsing and querying unstructured documents. This skill enables agents to ingest, index, and retrieve documents efficiently using Ariadne Core, reducing token usage and increasing recall with structured provenance.

Core Features & Use Cases

  • Ingest documents from files or directories into named collections to enable fast, targeted search.
  • Semantic search across ingested content with filters, provenance metadata, and per-document history.
  • Manage collections and tags to organize content for repeatable retrieval and auditing.

Quick Start

Tell the agent to connect Ariadne Core, ingest a sample PDF into a descriptive collection (e.g., vendor-contracts), and run a search over the ingested content.

Frequently Asked Questions about ariadne-document-intelligence

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

FAQPage Schema
How do I ingest documents into collections for semantic search?▼

You can ingest documents from files or directories into named collections to enable fast, targeted semantic search. This process applies chunking and vector embeddings to prepare the content for efficient retrieval.

What is document provenance tracking and why do I need it for AI workflows?▼

Document provenance tracking records the origin and history of ingested content. It is needed in AI workflows to reduce token waste, increase retrieval recall, and provide per-document auditing metadata for search results.

Can I use tags and metadata to filter my semantic search results?▼

Yes, you can manage collections and tags to organize content for repeatable retrieval. Semantic search supports applying filters and provenance metadata to narrow down results across multiple formats.

What is the best way to reduce token usage when querying unstructured documents?▼

The best way to reduce token usage is to index unstructured documents into searchable collections first. By using vector embeddings and targeted retrieval, agents query pre-processed content instead of parsing raw files.

Do I need to run connection checks before setting up document indexing?▼

Yes, connection checks and client setup are required prerequisites. Ensuring the Ariadne Core client is properly connected satisfies the requirements needed to execute document ingestion and collection management.

Related Skills

Explore More Data & Analytics Skills→
densondenson

ariadne-core-install

Automate Ariadne Core deployment, connection, and onboarding via setup.py.

Community
Advanced
saskinosiesaskinosie
39

weaviate-query-agent

Query local Weaviate collections with semantic, hybrid, and RAG searches.

Community
Intermediate
ivanshamaevivanshamaev
14

rag-data-pipeline

Build RAG ingestion and query pipelines with hybrid retrieval and reranking.

Community
Advanced
Maheen-ZubairMaheen-Zubair

rag-ingestion-pipeline

Automate document ingestion and indexing for RAG systems.

Community
Advanced