judge

Installation
SKILL.md

Judge

Overview

Evaluate agent task outputs against a three-dimension rubric and produce structured verdict records. The judge operates as a quality gate at the task completion boundary, scoring outputs on Semantic accuracy, Pragmatic usefulness, and Syntactic consistency.

Rubric: Three KLS Dimensions

The rubric reuses three dimensions from the KLS (Krogstie-Lindland-Sindre) quality framework defined in disciplined-quality-evaluation:

Dimension Question Criteria
Semantic Does it accurately represent the domain? Factual correctness, domain terminology, no contradictions
Pragmatic Does it enable the intended decisions/actions? Actionable, useful, addresses the task goal
Syntactic Is it internally consistent and well-structured? Format compliance, structural completeness, no broken references
Installs
16
GitHub Stars
3
First Seen
Feb 17, 2026
judge — terraphim/terraphim-skills