Do and judge
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
Save adds this to your Playground favorites. Hearts show appreciation.
How you can use it
- Hand a single coding or writing task to a fresh helper agent and have a separate judge check the result before you accept it.
- Get automatic retries with specific reviewer feedback until the work reaches a quality bar or a retry limit is hit.
- Require a stricter pass rule so the work only counts as done when it scores at a high level.
Who it's for
- Developers who want an independent check on AI-generated changes
- Team leads who want a quality gate on delegated tasks
Written by AI from this item's description. Check the source before relying on it.
See what it would do for your project in Playground →Set it up
Pick the app you use.
do-and-judge
- 1
Get the skill file from GitHub
Open the SKILL.md on GitHub and select the download icon (Download raw file). If the folder has other files, like scripts, download them too.
Open SKILL.md on GitHub ↗ - 2
Open Plugins → Skills
Left sidebar → Plugins, then the Skills tab.
- 3
Add → Upload from your computer
Pick the SKILL.md (or Create with editor and paste the text), then Create.
- 4
Use it with /
In a chat, type / and pick the skill, then write your request.
Read a skill before you install it: it tells the AI what to do. Promptu never installs or runs anything.

