Claude History Ingest for Obsidian Wiki

Mines your past Claude Code sessions, memory files and audit logs, then distills them into topic-based Obsidian wiki pages.

AutomationAdvanced★ 3,520⑂ 350AI score 9/10Last updated: Oct 3, 2026

What it does

Scans both data sources: ~/.claude/projects/ (conversation JSONL, memory/*.md, session metadata) and the macOS Claude desktop local-agent-mode-sessions tree including audit.jsonl.
Runs extract-jsonl.py first to strip thinking/tool_use/progress noise, shrinking files 50–200× so far more sessions fit in one token budget.
Clusters knowledge by topic instead of per conversation, routing it to concepts/, skills/, entities/, synthesis/ or projects/<name>/.
Defaults to incremental append mode driven by .manifest.json (only new or modified sources), with a full re-ingest mode when needed.
Stamps every page with summary, base_confidence, lifecycle and a provenance block (extracted / inferred / ambiguous), then updates index, log and journal through one locked obsidian-wiki memory sync call.
Privacy rules: never copy raw transcripts verbatim, skip secrets and tokens, ask before importing personal content.

Who it's for

Heavy Claude Code users with hundreds of accumulated sessions across projects.
Obsidian note-takers who want their AI work history turned into a searchable knowledge base.
Teams that keep re-debugging the same classes of problems and want the patterns written down.

Example uses

"Process my Claude history" → only changed sessions are ingested and per-project overview pages are refreshed.
"What have I discussed about React performance?" → three separate sessions merge into one concepts/react-performance.md.
Recurring Bash commands in an audit log become projects/my-app/skills/build-and-test.md documenting the build/test workflow.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Ar9av/obsidian-wiki/HEAD/.skills/claude-history-ingest/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .skills/claude-history-ingest folder from the GitHub repo Ar9av/obsidian-wiki into my ~/.claude/skills/claude-history-ingest/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Ar9av/obsidian-wiki.git /tmp/obsidian-wiki && mkdir -p ~/.claude/skills && cp -r /tmp/obsidian-wiki/.skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Clone the repository: git clone https://github.com/Ar9av/obsidian-wiki.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy all skills over: cp -r obsidian-wiki/.skills/* ~/.claude/skills/ — this skill depends on the sibling llm-wiki skill, so copy the whole set.
Export the repo path so helper scripts resolve: export OBSIDIAN_WIKI_REPO=$(pwd)/obsidian-wiki (add it to your shell rc file).
Configure your vault: set OBSIDIAN_VAULT_PATH=/path/to/vault in a .env or the global config; optionally CLAUDE_HISTORY_PATH=~/.claude and WIKI_SKIP_PROJECTS=proj1,proj2.
(Recommended) Pre-extract sessions: python3 $OBSIDIAN_WIKI_REPO/scripts/extract-jsonl.py
Restart Claude Code and ask: "add my Claude conversations to the wiki".

View source on GitHub ↗License: MIT