# Clarify Question Loop

Use when a meta-agent request is too ambiguous to safely generate, package, publish, or...

- Repository: https://github.com/agentlas-ai/Agentlas-OS (1593 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agentlas-ai/Agentlas-OS --skill clarify-question-loop -g -a claude-code -y`
Codex: `npx skills add agentlas-ai/Agentlas-OS --skill clarify-question-loop -g -a codex -y`
Cursor: `npx skills add agentlas-ai/Agentlas-OS --skill clarify-question-loop -g -a cursor -y`
Gemini CLI: `npx skills add agentlas-ai/Agentlas-OS --skill clarify-question-loop -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add agentlas-ai/Agentlas-OS`

## Description

Use when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to five targeted questions.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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
`contracts/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?"
3. Follow up on role count, role-specific tools/permissions, whether outputs
   must be synthesized, and whether artifacts are sequential dependencies or
   independent parallel packets.
4. Identify missing facts that would change files or safety.
5. 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.
6. Do not ask for secrets. Ask for secret names or setup boundaries instead.
7. After answers arrive, re-run mode classification if needed.
8. Generate or repair the package using the answers and list assumptions.

## Budgets and stop rule (briefing interview engine)

The rest: https://github.com/agentlas-ai/Agentlas-OS/blob/HEAD/.agents/skills/clarify-question-loop/SKILL.md