Claude History Ingest

Turns your Claude Code conversation history into structured Obsidian notes. It scans both CLI sessions in ~/.claude and desktop app agent sessions, pulling from conversation transcripts, memory files, and audit logs. Memory files get priority since they're already distilled, then it mines the JSONL transcripts for knowledge worth keeping. The manifest tracking means you can run it repeatedly and only process new or modified sessions. Useful when you've had a productive week of coding sessions and want to capture the insights before they disappear into your scrollback. The audit log parsing is smart, it extracts what the agent actually did, not just what was discussed.

skills.sh installs: 3K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ar9av/obsidian-wiki --skill claude-history-ingest --agent claude-code

Installs into .claude/skills of the current project.

Files

Claude History Ingest — Conversation Mining

You are extracting knowledge from the user's past Claude Code conversations and distilling it into the Obsidian wiki. Conversations are rich but messy — your job is to find the signal and compile it.

This skill can be invoked directly or via the wiki-history-ingest router (/wiki-history-ingest claude).

Before You Start

Writing profile: Before drafting or rewriting natural-language Markdown, read and apply the Writing Profile Resolution section in llm-wiki/SKILL.md. Framework schema, provenance, safety, and operation-specific requirements take precedence. WRITING.md preferences apply only to newly drafted or rewritten natural-language Markdown; preserve source content and structured records.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly