claude-workshop-261011/evaluate 0.1.0
Evaluate a change against agreed metric thresholds and the main baseline, commit the eval suite and report, and review them
Install it from the Spex app: open Playbooks, search for claude-workshop-261011/evaluate, Add.
License: Apache-2.0Languages: en
Artifacts
| Artifact | Languages | Generated by |
|---|---|---|
| Playbooks | ||
evaluate | en | — |
Versions
| Version | Published |
|---|---|
| 0.1.0 |