Agent skill · data analytics · aiskillstore
judge
Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly - called by cookoff/omakase-off.
Why this skill is useful
Provides a structured scoring framework for evaluating implementations that the AI wouldn't reliably generate on its own.
What it needs
About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Test Kitchen Judge Score implementations using the 5-criteria framework. Fill out ALL sections exactly as shown. Terminology: This skill uses "impl" but works for both: Cookoff: impl-1, impl-2, impl-3 (same design, different implementations) Omakase: variant-a, variant-b (different approaches/designs) REQUIRED OUTPUT FORMAT You MUST produce this exact structure. Do not summarize or abbreviate. Scoring Reference Scores Meaning Score Meaning ------- --------- 5 Excellent - exceeds expectations 4 Good - fully meets requirements 3 Adequate - core works, some gaps 2 Poor - significant issues 1 Critical flaw - disqualifying Hard Gates (Automatic) 1. Fitness Gate: If Fitness Δ ≥ 2 between impls → Higher fitness WINS immediately 2. Critical Flaw: If ANY criterion = 1 → That impl is ELIMINATED Fitness Gate Interpretation The Fitness Gate triggers the same way in both contexts, but means different things: Context What Fitness Δ ≥ 2 Means --------- -------------------------- Cookoff One implementation deviated from or misunderstood the design. All impls should have similar Fitness since they're implementing the same spec. A large gap is a red flag. Omakase One approach genuinely solves the problem better. Different approaches can legitimately have different Fitness. A large gap means one approach is clearly superior. In both cases, higher Fitness wins. The interpretation just explains why the gap exists. Feasibility Red Flags Check before scoring: O(n²) or worse on unbounded data Unbounded memory growth Self-DDoS patterns (polling, no backoff) Missing pagination Blocking I/O in hot path No error recovery Process 1. Read all implementation code (should already be in context) 2. Fill out the worksheet for EACH implementation - do not skip sections 3. Check hard gates 4. Announce winner with rationale CRITICAL: Use integer scores only (1-5). Do not use half points like 4.5. CRITICAL: Fill out every checkbox. Do not summarize or abbreviate the worksheet.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/judge