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.
npx -y skills add ar9av/obsidian-wiki --skill pi-history-ingest --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
reactjs/react.dev
reactjs/react.dev