Roadmap Implementation Review Skill for ChatGPT: Compare Code Diffs and Deviation Records
Perform a static comparison of supplied roadmap scope, deviation notes, and changes. Identify omissions, scope expansion, and unverified decisions with locations.
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 .codex/skills/roadmap-review/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the roadmap item, diff excerpts, deviation notes, and any observed test results.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional plan requires filtering by project. A diff also adds account filters without mentioning them in the deviation log. Draft a finding and follow-up.What to check
Locate the account-filter expansion and identify UI and data impact. Request the decision, reason, and follow-up. Label the review as static when no run evidence exists.
Original SKILL.md on GitHub · Updated
Frequently asked question
Does passing static review mean tests passed?
Report only the static finding from supplied evidence. Treat runtime tests as pending until their actual results are available.