skills.rest
spoonbobo
spoonboboCOMMUNITY
Explore all skills by this author →
GitHub

ingest-knowledge

Ingests, indexes, and queries documents in a claw-scoped knowledge workspace via LightRAG.

Updated Feb 27, 2026
Search Tags:#indexing#retrieval#workspace#knowledge#document management#ingest
One-click install
npx skills add https://github.com/spoonbobo/trinity --skill ingest-knowledge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ingest-knowledge
Source: https://github.com/spoonbobo/trinity/tree/main/app/skills/ingest-knowledge
Command: npx skills add https://github.com/spoonbobo/trinity --skill ingest-knowledge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill allows a claw to ingest documents into a knowledge workspace, making them available for retrieval and querying by other downstream workflows without the claw needing to manage the ingestion process itself.

Core Features & Use Cases

  • Document Registration: Register new documents for indexing.
  • Content Extraction & Chunking: Extract normalized text and break it down into manageable chunks with stable identifiers.
  • Indexing: Index the extracted content into a retrieval subsystem.
  • Workspace Scoping: Maintain document metadata, status, and ensure content is scoped to the correct claw's workspace.
  • Querying: Run scoped retrieval queries against the indexed content.
  • Use Case: Pre-indexing a company handbook or product documentation so that other claws can easily query this information.

Quick Start

Register and ingest the document located at '/path/to/your/document.pdf' into the current claw's knowledge workspace.

Frequently Asked Questions about ingest-knowledge

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

FAQPage Schema
How do I ingest and index documents for retrieval in a knowledge workspace?▼

To ingest and index documents for retrieval, you register the document within a claw-scoped knowledge workspace using the LightRAG service, which handles text extraction, content chunking, and indexing for subsequent querying.

What is document indexing and how does it make content available for retrieval?▼

Ingesting a PDF document registers the file path with the knowledge workspace, which then extracts the text, chunks the content into stable identifiers, and indexes it for scoped retrieval queries by other workflows.

Can I ingest a PDF document and make it available for other workflows to query?▼

Yes, you can pre-index company handbooks or product documentation so that other claws can easily query this information within the workspace without managing the ingestion process themselves.

Does document ingestion work for pre-indexing company handbooks for other claws to query?▼

Yes, you can pre-index company handbooks or product documentation so that other claws can easily query this information within the workspace without managing the ingestion process themselves.

What's the best way to scope retrieval queries to only the documents ingested by a specific claw?▼

Workspace scoping maintains document metadata and status, ensuring that content is scoped to the correct claw's workspace so that retrieval queries only return results from that specific claw's indexed documents.

How do I check the indexing status of a document I ingested into the knowledge workspace?▼

You can check the indexing status of an ingested document by running a document status check within the knowledge workspace, which reports the current metadata and processing state of the file.

Related Skills

Explore More Software Engineering Skills→
jykimjykim
31

obsidian-yaml-frontmatter

Standardize YAML frontmatter properties across Markdown files.

Community
Basic
spoonbobospoonbobo

query-knowledge

Query existing LightRAG knowledge for retrieval-backed answers without ingesting documents.

Community
Intermediate
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
sanjay3290sanjay3290
392

google-docs

Create, search, read, and edit Google Docs via OAuth-authenticated requests.

Community
Intermediate