Deep Interview Skill for ChatGPT: Clarify Scope and Acceptance Criteria One Question at a Time
Use a focused interview for ambiguous requests. Establish intent, outcome, boundaries, and decision ownership before creating a usable requirement brief.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned internal/builtin/skills/deep-interview/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the current request, confirmed facts, decision boundaries, and any existing spec.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional request says 'improve the member page.' The user explains existing members cannot find expiry dates and registration remains out of scope. Ask the next question and capture confirmed scope.What to check
Ask how expiry discoverability should be measured. Keep existing members, the date, and registration scope clear. Record placement and validation decisions still open.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should complete acceptance criteria trigger a new interview?
Check whether the supplied material supports execution. Ask only about unresolved ambiguities that affect the outcome and summarize an already complete brief.