Skills
.Work. You
Rest

lumi-ingest

Community

Turn raw files into a connected wiki

Education & Research#knowledge management#grounding#deduplication#citation#ingest#pdf processing#wiki graph
Authortronghieu
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: lumi-ingest
Download link: https://github.com/tronghieu/lumina-wiki/archive/main.zip#lumi-ingest

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.