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…
Build the spec's must-haves on Firebase: the screens and client logic, working inside the Firestore rules, proven against the emulators.
$ npx -y skills add receptron/mulmoterminal --skill features-firebase --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/features-firebaseContext preview
The summary Claude sees to decide when to auto-load this skill.
Build the spec's must-haves on Firebase: the screens and client logic, working inside the Firestore rules, proven against the emulators.
name: blueprint-from-collection-features description: "Build the spec's must-haves on Firebase: the screens and client logic, working inside the Firestore rules, proven against the emulators."
The skeleton, sign-in and the collections with their rules already exist. This step builds what the product DOES.
1. The screens in the spec, no more: Vue 3, the Firebase Web SDK against the emulators in development. Every error Firestore returns (a rule refusing a write, above all) is shown to the user in words. 2. Writes the client makes must fit the rules the data-rules step wrote. If a feature needs a write the rules do not allow, change the rules deliberately — the smallest opening that makes the feature work — and extend `test/blueprint/rules.spec.ts` in both directions for it. Never widen a rule to `if true` or to any signed-in user when the spec says only the owner. 3. Anything a client must not be trusted to do (counting likes, fan-out to followers' timelines, removing someone else's content as a moderator) is a Cloud Function, not a client write. 4. `test/blueprint/features.spec.ts`: each screen's main action works against the emulators as a signed-in user.
Done when the check passes: `emulator-test.sh features`.
Code's trust prompt. The user adds git themselves after the build if they want it.
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.