mirror of
https://github.com/openai/codex.git
synced 2026-09-06 15:29:32 +00:00
skills: make code-review more adversarial
This commit is contained in:
@@ -3,7 +3,7 @@ name: code-review
|
||||
description: Run a final code review on a pull request
|
||||
---
|
||||
|
||||
Use subagents to review code using all code-review-* skills other than this orchestrator. One subagent per skill. Pass full skill path to subagents. Use xhigh reasoning.
|
||||
Use subagents to review code using all code-review-* skills other than this orchestrator. One subagent per skill. Pass full skill path to subagents. Use xhigh reasoning. Don't fork any turns -- blank slate for each subagent.
|
||||
|
||||
You must return every single issue from every subagent. You can return an unlimited number of findings.
|
||||
Use raw Markdown to report findings.
|
||||
|
||||
Reference in New Issue
Block a user