Results for “evaluation-results”

Audits Claude skills and commands for quality, offering Quick Scan for changed skills and Full Stocktake modes with sequential subagent batch evaluation.

Diagnose and improve MSBuild project evaluation performance by analyzing phases, glob patterns, import chains, and property functions.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Comprehensive results analysis for empirical research: generate publication-quality descriptive statistics and balance tables, interpret regression coefficients with economic magnitude and effect sizes, assess identification assumption diagnostics, and produce structured results memos. Use when asked to create summary statistics, Table 1, balance tests, interpret results, assess economic significance, or write results narratives.

Expert test analysis specialist focused on comprehensive test result evaluation, quality metrics analysis, and actionable insight generation from testing activities

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking

Design and implement evaluation harnesses for models, agents, and code. Use when creating benchmarks, designing eval metrics, or comparing system outputs.

Two-stage review engine with four-layer quality model for the WinDAGs meta-DAG. Receives completed node outputs and produces ReviewResult containing QualityVector. Stage 1 (Haiku) checks Floor + Wall on every node. Stage 2 (Sonnet) runs Ceiling evaluation conditionally using economic escalation formula. Enforces BC-EVAL-001 through BC-EVAL-006. Activate when operating as the Evaluator role in the meta-DAG, when reviewing node outputs, when computing quality vectors, or when deciding Stage 2 escalation.

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Evaluates execution outcomes against defined success criteria, scoring each criterion and producing a structured verdict with actionable feedback.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Outcome Eval

Analyzes evaluation patterns across completed plans and evolves the superpowers checklists accordingly.

Grades individual test methods and produces a compact markdown table with a letter grade, score band, and one-line note for each test.

Build and run evaluators for AI/LLM applications using Phoenix, covering error analysis, custom evaluators, experiments, and production monitoring.

Design grading plans. TRIGGERS - Use when user needs help with grading-plan related tasks.

Every metric encodes an opinion about which mistake hurts.

Runs regression evaluations comparing agent edits against human-approved golden projects, and registers new goldens after human approval.

Improve existing content and close the learning loop without cannibalizing new-content work.

Design structured evaluation rubrics for scoring LLM and agent outputs — defining quality dimensions, scoring scales, hard gates, score descriptions, and edge cases. Load when the user asks to create an eval rubric, define evaluation criteria, design scoring dimensions, write an eval spec, or says "what should I evaluate", "design a rubric", "create eval criteria", "define quality dimensions", "evaluation rubric for", "how do I measure quality of". Sub-skill of eval-output orchestrator.

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

LLM output evaluation — automated metrics, LLM-as-judge, A/B testing, regression testing. Use when measuring LLM output quality, comparing prompt or model versions, building an automated eval pipeline, setting up regression tests for prompt changes, or evaluating RAG systems and bias/safety.

Verifica la reproducibilidad y consistencia de un análisis de datos antes de presentarlo, validando contra la pregunta original y documentando limitaciones.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations.

Reviews closed trades, partial exits, and monthly trade aggregates for process adherence, risk discipline, execution quality, and evidence-based trading behavior patterns.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

Analyze closed deals and lost opportunities for patterns