alt Hacker NewsThis looks useful. With AI generated code the hardest part is reviewing it.
A normal git diff gets messy once the agent changes several files for different reasons. Grouping the change into “chapters” seems like the right idea.
Do you infer those chapters only from the diff, or can you also use the agent’s original plan/task history?
the cool part is that you can run the skill from the same agent session so it has the context on the plan and implementation process
but if you run the skill in a fresh session, it naturally wouldn't have the plan