apply
Set chaff up in the folder: chaff.yaml for the chosen genre, today's findings shelved in .chaff-baseline.json, and, when asked, a…
After the production publish, move the copied records and their files into production with the import proven on the emulators.
$ npx -y skills add receptron/mulmoterminal --skill import-production --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/import-productionContext preview
The summary Claude sees to decide when to auto-load this skill.
After the production publish, move the copied records and their files into production with the import proven on the emulators.
name: blueprint-from-collection-import-production description: "After the production publish, move the copied records and their files into production with the import proven on the emulators."
This step's gates are **deploy-production** and **credential**: the user has approved writing the copied records into the production project with their own Application Default Credentials. If `.blueprint/source/source.json` says `records` is `false`, there is nothing to do: stop.
1. Check that Application Default Credentials exist (`gcloud auth application-default print-access-token`). If not, ask the person, through the blueprint question tool, to run `gcloud auth application-default login` and tell you when it is done. Do not create or download a service account key. 2. Run `yarn import-source --target prod` — the same import the emulator step proved. Do not change it here; if it fails, say why and stop. 3. If files were uploaded, `.blueprint/storage-bucket` names the production bucket (`<prod-project-id>.appspot.com` or `<prod-project-id>.firebasestorage.app`). 4. Tell the person how many records went into each collection.
Done when the check passes: production Firestore, read back with the person's token, has every record with every stored field equal to the source, and every pointed-at file is in the production bucket.
user approved exactly that.
Run multiple coding-agent sessions in parallel — and see which one needs you. A browser terminal for parallel AI coding agents: several sessions side by side, each in its own cell, with the one that needs you marked in colour.
Set chaff up in the folder: chaff.yaml for the chosen genre, today's findings shelved in .chaff-baseline.json, and, when asked, a…
Measure what chaff reports on the named documents today, as the kind the person chose, and propose the setup — changing nothing…
Answer each question from the named documents only, quoting where the answer is written, or saying plainly that the documents do…
Add the approved answers to FAQ.md when the person chose to keep them, after what it already holds; change nothing otherwise.
Build the spec's operations as the Worker's API, with validation and tests.