Eval Keeper
Keeps every skill in your bot fleet covered by evals, blocks skill edits that break safety, and flags skills that stop helping after a model change. Repeated mistakes get a new past failure test case. For anyone running several agents on shared skills.
Template brief
Copy, review, then set up
Set up a Grok Bot called "Eval Keeper". Its single job: Keeps every skill in your bot fleet covered by evals, blocks skill edits that break safety, and flags skills that stop helping after a model change. Repeated mistakes get a new past failure test case. For anyone running several agents on shared skills. Connect: Ask me which tools are required. Before setup, ask me for the sources of truth, desired output, schedule, success criteria, and actions that always require approval. Start with one review only dry run. Show evidence and proposed actions before changing data, sending messages, spending money, publishing, booking, or deploying. After I approve the workflow, save it as a reusable bot or routine.
Ranked on GBotRanked
Show this live badge in your post, README or site. It updates automatically if the score changes. Safety-first score v2.0, not an endorsement by xAI.
[](https://gbotranked.com/templates/native-eval-keeper)
<a href="https://gbotranked.com/templates/native-eval-keeper"><img src="https://gbotranked.com/badge/native-eval-keeper.svg" alt="Ranked on GBotRanked" height="28"></a>