skills.rest
tronghieu
tronghieuCOMMUNITY
Explore all skills by this author →
GitHub

lumi-ingest

Transform raw source files into structured wiki pages with staged gates.

36|16|Updated May 1, 2026
Search Tags:#knowledge management#grounding#deduplication#citation#ingest#pdf processing#wiki graph
One-click install
npx skills add https://github.com/tronghieu/lumina-wiki --skill lumi-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lumi-ingest
Source: https://github.com/tronghieu/lumina-wiki/tree/main/src/skills/core/ingest
Command: npx skills add https://github.com/tronghieu/lumina-wiki --skill lumi-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It converts a raw document (or a fetched paper) into structured, linkable wiki content while keeping the work checkable and resumable across sessions.

Core Features & Use Cases

  • End-to-end wiki compilation: creates a source page plus concept/person stubs, wiki graph edges, citation edges, and a log entry.
  • Four checkpoint gates: draft, lint, verify, and finalize, so you can accept, edit, or quit at each stage without losing progress.
  • Flexible input modes: ingest from a local file path in raw/sources or notes, or ingest by title/arXiv/URL/identifier (including automatic PDF fetching for external IDs).
  • Deduplication and grounding discipline: applies dedup policy and alias resolution to avoid duplicate stubs and to ground concepts where foundations exist.
  • Resumable runs: durable ingest_status on the source entry plus phase checkpointing in _lumina/_state enables safe continuation after interruptions.

Quick Start

Use the lumi-ingest skill to compile a new paper into the wiki by instructing your AI to ingest raw/sources/your-paper.pdf.

Frequently Asked Questions about lumi-ingest

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

FAQPage Schema
How do I turn raw PDF files into a connected wiki with structured graph edges?▼

Yes, you can ingest arXiv papers by providing the arXiv ID or URL. The Skill automatically fetches external identifiers, performs PDF preprocessing, and compiles the paper into structured wiki content with citations.

What is the best way to avoid duplicate concept stubs when building a knowledge wiki?▼

To resume interrupted wiki compilation, the Skill uses durable ingest_status tracking and phase checkpointing in its state directory. You can continue safely from draft, lint, verify, or finalize gates without losing progress.

How do I verify and control wiki page generation step by step from source documents?▼

You control wiki page generation through four checkpoint gates: draft, lint, verify, and finalize. At each stage, you can accept, edit, or quit, ensuring grounding-first verification and source content accuracy before completion.

Does wiki graph ingestion require any external dependencies or API keys?▼

Yes, you can use this Skill for local knowledge management by ingesting files from local paths in your raw sources or notes directories. It transforms them into linkable wiki content with concept stubs and graph edges.

Related Skills

Explore More Education & Research Skills→
tangshunputangshunpu
7

arxiv-downloader

Download and extract LaTeX sources from arXiv papers using curl or wget.

Community
Intermediate
jmeier1963jmeier1963
2

ask

Answer natural-language questions from wiki pages with synthesized citations.

Community
Advanced
ethan-rioethan-rio

synthesize-wiki

Convert source notes and knowledge graph data into grounded wiki notes.

Community
Intermediate
ZpankzZpankz
7

hkgb

Bridge CSV or database domain graphs with LLM-extracted entities from PDFs and text in Neo4j.

Community
Advanced