llmwiki-ingest
llmwiki-ingest transforms source files into interconnected wiki pages by extracting entities, concepts, and relationships. It writes source summaries, creates or updates entity and concept pages, cross-links everything, and flags contradictions—all while maintaining a searchable index and activity log. Perfect for building knowledge bases from session transcripts, markdown files, PDFs, and URLs.
llmwiki-ingest converts documents into structured wiki pages with automatic extraction of entities, concepts, and cross-links.
AI-generated summary based on this skill's SKILL.md
Install
Pratiyush/llm-wiki/llmwiki-ingest · repository language: Python
git clone https://github.com/Pratiyush/llm-wiki
cp -r llm-wiki/.claude/skills/llmwiki-ingest ~/.claude/skills/llmwiki-ingestFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I ingest markdown files into my wiki?
llmwiki-ingest processes markdown files by extracting entities, concepts, and relationships, then automatically creates cross-linked wiki pages. The tool writes source summaries, generates or updates entity and concept pages, and maintains a searchable index—transforming your raw markdown into an interconnected knowledge base.
What file formats can llmwiki-ingest process?
llmwiki-ingest handles markdown files, PDFs, URLs, and session transcripts. It converts each format into structured wiki pages by extracting people, companies, projects, and concepts, then cross-linking them semantically. The tool also processes folders for batch ingestion, making it flexible for diverse source material.
Can llmwiki-ingest batch ingest wiki files?
Yes. llmwiki-ingest supports batch ingestion of multiple files and folders at once. It processes each document to extract entities and concepts, creates interconnected pages, and maintains consistency across your entire import. An activity log tracks all changes while a searchable index keeps your knowledge base organized.
How does llmwiki-ingest handle contradictions?
llmwiki-ingest flags contradictions and inconsistencies during bulk imports to help maintain wiki integrity. When conflicts are detected between new content and existing pages, the tool alerts you so you can review and resolve them before finalizing the ingestion.
What does llmwiki-ingest extract from session transcripts?
llmwiki-ingest processes session transcripts into structured project entities, capturing decisions, tools used, and participants. It extracts people, companies, and concepts, then creates cross-linked pages that organize your session data into a searchable, interconnected knowledge base.
Does llmwiki-ingest create wiki pages automatically?
Yes. llmwiki-ingest automatically creates wiki pages from your source files by extracting entities and concepts, writing summaries, and establishing cross-links between related pages. It updates existing pages when needed and maintains a complete activity log of all ingestion operations.
SKILL.md
rendered from the published skill — quoted content, verbatim
llmwiki-ingest
What this skill does
Takes a source file (or a folder) and turns it into wiki pages following the Karpathy LLM Wiki pattern:
- Writes a
wiki/sources/<slug>.mdsummary - Creates/updates entity pages for people, companies, projects, tools, libraries mentioned
- Creates/updates concept pages for ideas, patterns, decisions discussed
- Cross-links everything with
[[wikilinks]] - Flags contradictions
- Updates
wiki/index.md,wiki/overview.md,wiki/log.md
When to use
- User says "ingest this file", "add this to the wiki", "process this into the wiki"
- User runs the
/wiki-ingestslash command - User says "sync the wiki" — in that case, the
llmwiki-syncskill runs the converter first, then invokes this skill for each new file
Workflow
Follow the Ingest Workflow from the repo's CLAUDE.md
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
.claude/skills/llmwiki-ingest/SKILL.md