wiki-ingest

Fetch, archive, and compile URLs, files, or text into linked wiki pages.

5|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/GYF0311/lorekit --skill wiki-ingest-gyf0311
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-ingest
Source: https://github.com/GYF0311/lorekit/tree/main/skills/wiki-ingest
Command: npx skills add https://github.com/GYF0311/lorekit --skill wiki-ingest-gyf0311

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of turning incoming external content (URLs, files, or pasted text) into a persistently organized local knowledge base without missing links, duplicates, or broken references.

Core Features & Use Cases

  • URL/file ingestion workflow: Fetch content (with URL dedupe and stateful resume) and convert it into corpus-ready wiki entries with proper filing rules.
  • Entity/concept page building with timeline: Identify main subjects, gate for notability, then create new pages or append a ## Timeline entry with 強化 / 修正 / 新增分歧 annotations.
  • Backlink and integrity safeguards: Pre-check dead links (ingest check), align aliases to avoid duplicates, record source hashes (raw_sha256), and finish with a single multi-step closure (ingest record), followed by sync to refresh indexes and vectors.

Quick Start

Trigger ingest by telling your AI: ingest https://example.com/some-article and store it into my knowledge base with backlinks and timeline updates.

Frequently Asked Questions about wiki-ingest

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

FAQPage Schema
How do I archive web URLs into a local knowledge base with backlinks?

You can ingest URLs by triggering a command to fetch content, verify source hashes, and file it into corpus directories while automatically generating structured entity pages with reciprocal backlinks.

How does entity extraction and timeline compilation work for pasted text?

Entity extraction and timeline compilation work by identifying main subjects, gating for notability, and appending structured timeline entries with annotations for additions, modifications, or divergences directly to concept pages.

What is the best way to prevent duplicate wiki entries and dead links during source archiving?

The best way to prevent duplicate wiki entries and dead links during source archiving is to enforce alias de-duplication, run pre-ingest dead-link checks, and verify raw_sha256 hashes before recording the final stateful ingest closure.

Can I ingest local files and GitHub gists into my wiki corpus?

Yes, you can ingest local files and GitHub gists into your wiki corpus, as the ingestion workflow supports fetching content from URLs including gist and GitHub routes, local files, or pasted text, applying filing-rule routing to store them correctly.

How do I refresh indexes and vectors after adding new entries to my knowledge base?

To refresh indexes and vectors after adding new entries to your knowledge base, you run a controlled sync operation following the multi-step ingest record closure, which updates the retrieval indexes to include the newly archived source material.