Clarify Question Loop

Clarify Question Loop

Ask only questions that change the generated package, runtime adapter, safety boundary, or public/private release decision.

For /hep-build creation or behavior-changing packaging, this is not a substitute for the Builder Interview and Research Gate in docs/builder-interview-research-gate.md. Run that gate first: ask an 8-12 question first batch, research similar agent repositories or comparables and academic/professional theory, then use this clarify loop only for the remaining narrow ambiguities.

Procedure

1. Classify the current best mode.
2. If single-agent vs team selection would change the package shape and the

independent ownership boundaries are unclear, ask before generation. The first batch must include this plain-language question: "이 일을 한 명의 전문가가 처음부터 끝까지 맡으면 되나요, 아니면 조사/분석/검토처럼 여러 전문가가 나눠 맡고 마지막에 합쳐야 하나요?"

1. Follow up on role count, role-specific tools/permissions, whether outputs

must be synthesized, and whether artifacts are sequential dependencies or independent parallel packets.

1. Identify missing facts that would change files or safety.
2. Ask one to five short questions, preferably three. If more than five

functional-quality questions remain, return to the Builder Interview and Research Gate instead of pretending the package is ready.

1. Do not ask for secrets. Ask for secret names or setup boundaries instead.
2. After answers arrive, re-run mode classification if needed.
3. Generate or repair the package using the answers and list assumptions.

Budgets and stop rule (briefing interview engine)

This loop shares the briefing interview engine's contract (agentlas_cloud/interview/): a question is only worth asking if the answer would change execution, not just its phrasing. Respect the surface budget (chat 3-5 in one batch, stormbreaker "누가 따로 맡아야 하는 일인지";

• memory/context -> "각자 따로 기억해야 할 자료, 기준, 진행 상황";
• tools/permissions -> "각자 써도 되는 계정, 파일, 웹사이트, 도구";
• synthesis -> "마지막에 결과를 한데 모으는 일";
• sequential dependency -> "앞 사람이 끝낸 결과를 다음 사람이 이어받는 순서".

If a question still sounds technical, split it into two shorter everyday questions and give examples such as 조사, 분석, 검토, 승인.

Reference

See docs/clarify-question-loop.md.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: agentlas-ai
• Source: agentlas-ai/Hephaestus
• License: Apache-2.0
• Homepage: https://agentlas.cloud

Install and usage instructions live in the source repository linked above.