Pi History Ingest

This pulls knowledge out of your Pi coding agent session logs and turns them into structured notes in your Obsidian vault. It reads the JSONL session files, follows the active conversation branch, and extracts only what actually happened in those sessions, explicitly avoiding generic knowledge from training data or docs. The append mode checks a manifest to avoid reprocessing files you've already ingested. If you're running Pi as a coding agent and want a searchable wiki of what you've actually built and learned across sessions, this is a straightforward way to automate that extraction. The strict no-hallucination rule around session content is the right call here.

skills.sh installs: 1.2K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Pi History Ingest — Session Mining

You are extracting knowledge from the user's Pi coding agent sessions and distilling it into the Obsidian wiki. Pi sessions are stored as structured JSONL with a tree layout — your job is to follow the active branch, extract durable knowledge, and compile it.

Session knowledge closure: Pi session files are the only factual source for this skill. Do not add background knowledge from model training, other tools, package docs, local files, or the current conversation unless that fact appears in the selected session entries. If outside context seems useful, mark it as an open question or skip it — never present it as extracted session knowledge.

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