evaluate-presets - Evaluate hat collection presets
Systematically test hat collection presets using shell scripts
Tags
Updated: 2026-03-23Capabilities
Typical Inputs
Typical Outputs
What this skill does
- evaluate single preset
- evaluate all presets
- test preset configurations
- validate preset configurations
- audit preset library
- capture evaluation metrics
- generate evaluation report
- read evaluation summary
- triage evaluation results
- run evaluation in background
Inputs
- preset name
- backend type
- test task YAML file
- preset configuration file
Outputs
- evaluation log
- session recording
- metrics JSON
- environment JSON
- merged config YAML
- evaluation summary Markdown
Requirements
- yq
- Cargo
- Bash tool with background mode