PurposeScores an eval diff against a rubric by reading the diff, rubric, and fixture app, answering P1-P5 detection/fix questions, and appending a row to results.csv. Produces structured eval scoring for change validation.

Domains

Others

Forms

Workflow
Required Tools
None
Languages
No strong dependency
Package Manager
N/A
Skill Composition
  • SKILL.md100.0%

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger

When an eval diff path is passed as $ARGUMENTS and you need to score a change against the eval rubric.

Workflow

  • Read the diff, eval-rubric.md, and original fixture app
  • For problems P1-P5, answer Detected? and Fixed? as yes/no
  • Append a row to results.csv with determinable fields filled, others left empty

Result

A new scored row in results.csv evaluating the diff per rubric criteria.