Writing Verification Plans Skill for ChatGPT: Draft End-to-End Acceptance Scenarios
Create a manual acceptance plan with environment, fixtures, actions, observable results, and a result log. Reserve outcome fields for the eventual real run.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download skills/writing-verification-plans/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for writing-verification-plans together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that writing-verification-plans appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
A fictional course booking feature must let a test user select a class, confirm, and see a booking number. Draft a scenario with synthetic course data and add a cancellation scenario.What to check
Both scenarios name their starting state, required fixtures, and pass criteria. The log leaves execution time, actual output, and result blank until someone runs the tests.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can a simulated outcome count as a pass?
Label walkthrough output as rehearsal. Record the observed outcome and decision after the acceptance environment is exercised.