Backlog Refiner Skill for ChatGPT: Write INVEST Stories and Acceptance Tests
Refine vague backlog items into user stories with INVEST checks, Given/When/Then acceptance cases, and dependencies. Use it before design, engineering, and QA align on a sprint.
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/codexkit-backlog-refiner/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for codexkit-backlog-refiner 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 codexkit-backlog-refiner 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 reader needs to reschedule a booking. Changes require 24 hours' notice, a free destination slot, and release of the old booking only after success. Draft stories and normal and boundary acceptance cases.What to check
State role, goal, benefit, and constraints. Keep the original booking if notice is too short or the target is full, and release it only after a successful change. Flag the capacity-service dependency.
Original SKILL.md on GitHub · Updated
Frequently asked question
What if the item is too large to estimate?
Split out one independent behavior with its own acceptance result. Keep the remaining stories separate and record shared prerequisites.