skillfed

llmwiki-sync

llmwiki-sync automates the full pipeline from Claude Code session transcripts to a searchable, LLM-maintained knowledge base. It converts raw session logs to markdown, ingests them into wiki structure (sources, entities, concepts), and optionally builds a static HTML site. Use it to keep your work history organized and queryable across projects.

llmwiki-sync pulls your Claude Code session transcripts into a local wiki knowledge base for searchable reference.

AI-generated summary based on this skill's SKILL.md

351 54 MIT updated by Pratiyush

Install

Pratiyush/llm-wiki/llmwiki-sync · repository language: Python

CLI (skillfed)coming soon
git clone https://github.com/Pratiyush/llm-wiki
cp -r llm-wiki/.claude/skills/llmwiki-sync ~/.claude/skills/llmwiki-sync

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What does llmwiki-sync do?

llmwiki-sync automates the full pipeline from Claude Code session transcripts to a searchable, LLM-maintained knowledge base. It converts raw session logs to markdown, ingests them into wiki structure (sources, entities, concepts), and optionally builds a static HTML site. Use it to keep your work history organized and queryable across projects.

How do I sync my Claude Code transcripts?

llmwiki-sync pulls your Claude Code session transcripts and automatically converts them into structured wiki format. The tool handles the entire ingestion pipeline—parsing session logs, extracting entities and concepts, organizing them into wiki structure, and syncing them into your local knowledge base without manual intervention.

Can llmwiki-sync refresh the knowledge base with latest sessions?

Yes. llmwiki-sync is designed to refresh your personal knowledge base with your latest work history and context. It ingests recent project sessions into structured wiki format and can automate wiki updates from Claude Code session transcripts on demand or on a schedule.

What format does llmwiki-sync convert session transcripts to?

llmwiki-sync converts Claude Code session transcripts to markdown and organizes them into a wiki structure with sources, entities, and concepts. It can also optionally build a static HTML site from your synced session data, making your work history searchable and accessible.

How do I query information from llmwiki-sync?

llmwiki-sync syncs your session data into a local wiki knowledge base that you can query and retrieve from. Once your Claude Code transcripts are ingested and converted to structured wiki format, you can search across your work history, projects, and recent sessions to stay caught up on what you've been working on.

SKILL.md

rendered from the published skill — quoted content, verbatim

llmwiki-sync

What this skill does

The user maintains a Karpathy-style LLM Wiki — a local, file-based knowledge base compiled from their Claude Code (and Codex CLI) session transcripts.

This skill runs the full sync pipeline:

~/.claude/projects/*/*.jsonl         (raw session transcripts)
        │
        ▼   python3 -m llmwiki sync
llmwiki/raw/sessions/<proj>/*.md     (Karpathy layer 1 — immutable markdown)
        │
        ▼   /wiki-ingest              (Claude in the loop)
llmwiki/wiki/sources, entities,      (Karpathy layer 2 — LLM-maintained wiki)
              concepts, syntheses
        │
        ▼   python3 -m llmwiki build
llmwiki/site/                         (Karpathy layer 3 — static HTML)

When to use

Invoke this skill when the

(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-sync/SKILL.md

Related skills

Tags

knowledge-base-sync session-transcript-ingestion local-wiki-automation karpathy-layer-pipeline project-history-tracking markdown-conversion context-refresh work-documentation