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…
Fill the base and usecase spec templates from the interview answers, and list what is still undecided.
$ npx -y skills add receptron/mulmoterminal --skill spec --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/specContext preview
The summary Claude sees to decide when to auto-load this skill.
Fill the base and usecase spec templates from the interview answers, and list what is still undecided.
name: blueprint-cloudflare-spec description: "Fill the base and usecase spec templates from the interview answers, and list what is still undecided."
The answers are in `.blueprint/answers.json`; the prompt names both pack directories.
1. Start from the base pack's `spec/overview.md`, then the usecase pack's `spec/requirements.md`, in that order, in one file: `.blueprint/spec.md`. Fill every `{{…}}` from the answers. 2. The tables, API and screens are NOT asked directly — derive them from what the product is for, who uses it, what it handles and what they do. Write them as concrete tables and lists, each marked `(提案)`, small enough to build in one pass: the must-haves, nothing else. 3. The app will be on the public internet. For every API operation write who may call it, and say plainly what a visitor who is not signed in can see. 4. Something the answers do not settle is not guessed: write "未定" and add a line to `.blueprint/open-questions.md` saying what is needed and why it matters. 5. Append both packs' `security/` checklists under a heading "必ず詰める点", unchanged. 6. Write in the language the build's prompt says the user reads (without one, the language the user answered in). Nothing is built in this step; the next step stops for the user to read this spec.
Done when the check passes: `.blueprint/spec.md` exists and no `{{` placeholder is left in it.
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.