AgentHub Result Scoring and Winner Selection
Rank completed AgentHub results using shared metrics or an evidence-based rubric, with a defensible winner and explicit ties.
Before & after
Same prompt, same agent — the only difference is the skill.
Good question. I can help you evaluate the results. To compare them fairly, I'll need to see the outputs from all three versions and know what success looks like for your use case. Are you measuring accuracy, latency, token efficiency, user satisfaction, or something else? If you share the results and your success criteria, I can offer an analysis.
AGENT COMPARISON REPORT VERSION PERFORMANCE TABLE Metric | v1 Baseline | v2 Variant-A | v3 Variant-B | Winner Accuracy | 82.1% | 87.4% | 84.9% | v2 (+5.3pp) Latency (ms) | 1240 | 1520 | 890 | v3 (-350ms) Token Cost/Call | $0.042 | 0.051 | 0.038 | v3 (-9%) User Rating | 3.2/5 | 3.8/5 | 3.5/5 | v2 (+0.6) STATISTICAL SIGNIFICANCE Accuracy lift (v2 vs v1): +5.3pp, 95% CI: 3.1-7.5pp, p=0.002 Effect size: 0.47 (small-to-medium) Sample size: n=412 calls per version RISK ASSESSMENT v2 strength: Best accuracy and user preference v2 weakness: 22% slower (latency tradeoff) v3 strength: Fastest and cheapest per call v3 weakness: Accuracy gap vs v2 (-2.5pp) HEAD-TO-HEAD: v2 vs v3 To break the tie, run 200 calls at peak usage times Metric to watch: Does v3 latency advantage outweigh accuracy cost for production users? RECOMMENDATION Short term: Deploy v2 to 20% of traffic (explore accuracy gains) Long term: Hybrid approach – route high-stakes queries to v2, standard queries to v3 Expected outcome: +4% accuracy, -12% cost vs current baseline NEXT STEPS 1. Load test v2 at production scale (p99 latency target: 1500ms) 2. Collect user feedback on v2 output quality in staging 3. Define rollback criteria if accuracy variance exceeds 1.5pp
About this skill
Several agents finished the same task, but the most convincing summary may hide the weakest implementation. Compare the actual results against shared requirements, separate disqualifications from weak scores, and choose a winner whose advantages can be traced to evidence.
What it does
- Checks that candidates answered the same task under comparable inputs and constraints.
- Applies identical metric definitions, denominators, and measurement conditions to every eligible result.
- Builds an anchored judging rubric when the task has no reliable numeric metric.
- Reduces judge bias by masking candidate identity, scoring independently, and checking close comparisons in reversed order.
- Ranks every evaluable candidate and separately identifies disqualified or unevaluable results.
- Explains the winning tradeoff, unresolved uncertainty, and the smallest check that could change the decision.
What you get
A compact evaluation containing the shared criteria, complete ranking, evidence behind the scores, and a winner, tie, or provisional recommendation. Existing session criteria take precedence; missing information is marked explicitly.
Best for
Developers and technical leads comparing completed AgentHub agent outputs, code patches, research responses, or other competing solutions to the same task.
SKILL.md preview
---
name: agenthub-result-scoring-and-winner-selection
description: Evaluate completed AgentHub results using identical metric definitions or an anchored judging rubric, then rank candidates with evidence, eligibility decisions, and explicit uncertainty. Use when the user says "/hub:eval", "score these agent results", "compare the completed agents", "pick the winning branch", "which result actually meets the requirements?", "these agents all claim they passed", or "the judge keeps picking the longest answer".
---
# AgentHub Result Scoring and Winner Selection
… (sign up to view the full skill)More development skills
View all Development skills →Performance Bottleneck Profiling: Node, Python, Go
Classifies a slowdown, gives exact profiler commands, reads the output, and proves the fix with same-conditions p95/p99 numbers.
Feature Scaffolding with Working Tests
Turn a short feature spec into code, runnable tests, and integration wiring that match your existing project.
Feature Flag Rollouts and Kill Switches
Design staged flag rollouts, verify rollback paths, and audit flag debt with explicit defaults, gates, and retirement plans.
Microcontroller Firmware and RTOS Engineering
Build and debug MCU firmware with bounded ISR/RTOS timing, safe DMA ownership, and measured power budgets.