ChatGPT code-review-checklist skill for repeated scans
Use supplied diff excerpts and observations to check performance and style, and identify what still needs review.
中文Install in ChatGPT
A ChatGPT workspace with skill creation enabled. Supply change excerpts and observations as text.
- 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 `code-review-checklist` 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 code-review-checklist and use these fictional card rendering notes to write performance and style findings.
change `render route cards` | fixture `card-row-19`
before=one scan of the input | proposed=repeat all-row filtering for each card
small observed sample `10 cards` caused `100 reads` | expected one scan
style rule `name repeated category checks`What to check
Flag `100 reads` for `10 cards` and suggest grouping after one scan. Check the style rule `name repeated category checks`.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can I infer live latency from a change in observed reads?
Report the reproducible read counts first. Describe runtime latency only after timing comparable conditions.