potpie-feature
Use Potpie context before feature work. Load `potpie-project-preferences` first, and load…
Record durable Potpie learnings after useful work.
$ npx -y skills add potpie-ai/potpie --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/potpie-recordContext preview
What this command does when you run it.
Record durable Potpie learnings after useful work.
Record durable Potpie learnings after useful work.
Choose the workflow skill first: `potpie-project-preferences`, `potpie-infra-architecture`, `potpie-change-timeline`, `potpie-debug-memory`, or `potpie-source-ingestion`.
First resolve identity so you link to existing nodes, not duplicates:
potpie graph search-entities "<entity name>" --type <Service|BugPattern|...>
Then write through the V2 graph plan workflow:
potpie --json graph propose --file mutation.json potpie --json graph commit <plan_id> --verify potpie --json graph history --plan <plan_id>
Capture:
**Write the `description` for retrieval, not display.** Include the symptoms, synonyms, and scope a future searcher would type — a vague card means the fact never resurfaces. Pick an honest truth class (`agent_claim` when you inferred it), keep the record compact and source-reference-first, and never hard-delete — end validity or retract instead.
Use Potpie context before feature work. Load `potpie-project-preferences` first, and load…