ChatGPT aidlc-requirements-analysis-skill for traceable requirements
Turn confirmed intent into numbered requirements, measurable conditions, explicit assumptions, and scope exclusions.
中文Install in ChatGPT
A ChatGPT workspace with skill creation enabled. Use the supplied plain-text material only.
- In a ChatGPT workspace with skill creation enabled, open Plugins → Skills → Create → Create with editor.
- Create a skill in the editor and adapt the text-only `aidlc-requirements-analysis-skill` workflow from the pinned GitHub source into its instructions.
- Save the skill, then type @ in a new chat to select it and try the example.
Example task
Manually select the skill and use the fictional exhibit board notes below to draft `requirements.md`.
project `Exhibit board` | scope=existing notice page | confirmed action `filter by room`
observable behavior selecting the reading room displays `Room A notices` only
assumption `staff can maintain the room list` | excluded `attendance tracking`
nonfunctional metric `load within 2 seconds in the local preview`What to check
Set `FR-1` to verify that `filter by room` shows only `Room A notices`. List `load within 2 seconds in the local preview` separately as a quality condition. Mark room list maintenance as an assumption and put `attendance tracking` out of scope.
Original SKILL.md on GitHub · Updated
Frequently asked question
Where should I put an operational condition that is still unverified?
Record it as an assumption with its source. Number verified functional and quality requirements separately.