ask-then-build
Clarify a feature, change, or refactor through questions, then write a build prompt for another agent. Use for /ask-then-build or requests to ask questions before producing an implementation prompt.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 4.3k
- Forks
- 626
01 前言 Front Matter
- name
- ask-then-build
- description
- Clarify a feature, change, or refactor through questions, then write a build prompt for another agent. Use for /ask-then-build or requests to ask questions before producing an implementation prompt.
03 SKILL.md 正文
Turn a feature idea into a build prompt for another agent, in two phases.
Phase 1 — Questions
-
Identify the 3-6 most non-obvious open questions about the feature or change: edge cases, where it lives in the UI, failure behavior, scope boundaries, how it interacts with existing rules.
-
Ask them ONE at a time. For each: the question, top options A-D, your preferred pick with a one-line reason. Then stop and wait. Use this exact layout. Put a blank line between EVERY block. Markdown renderers (bb included) collapse single newlines into one paragraph, so options written back-to-back render as one run-on blob.
Question title?
One line of context, if needed.
A. First option.
B. Second option.
C. Third option.
D. Fourth option.
My pick: A. One-line reason.
Never number questions as "1 of N" unless you truly know N. If the count is open, keep it open and keep asking until you have the context you need.
-
When the user answers, record the decision immediately — update the repo's docs (product requirements, ADR, or README) if the project has them.
-
If the user overrides an earlier documented decision, update the docs right away and say what was superseded.
Phase 2 — Prompt
After the last answer, deliver ONE concise paragraph prompt for another agent. It must include, in this order:
- Read-first files: the authoritative docs (AGENTS.md, requirements, ADRs).
- What to build: numbered implementation steps, concrete file-level where useful.
- How to validate: build, lint, and a manual check with real data.
- Rules: don't commit, report back with files changed.
Style
- Very concise, plain English, short sentences.
- Never bundle questions. Never write the prompt before all answers are in.
- Never put two options on one line. Always a blank line between A, B, C, D and before "My pick".
- Keep the prompt to a single paragraph — if it needs two, the scope is too big; say so.
04 同仓库更多 Skills
varied-search
Research a topic across the web, GitHub, and X/Twitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.
total-review
Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for /total-review, or when the user or another agent asks for a total review.
stop-overthinking
Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.
state
Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says "state", "where are we", or "what % are we done".
setup-help
Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.
self-archive
Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.