1.5K skills · sorted by relevance
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
採用・人材戦略の専門スキル。職務記述書（JD）作成、採用計画策定、コンピテンシーモデル設計、 面接評価基準設計、オンボーディング計画をサポート。採用要件の明確化から内定後のフォローまで 一貫した人材獲得プロセスを支援。日英両言語のテンプレートを提供し、グローバル採用にも対応。 Use when: creating job descriptions, designing competency models, planning recruitment strategies, developing interview evaluation criteria, or creating onboarding plans. Triggers: "JD作成", "採用計画", "面接評価", "オンボーディング", "コンピテンシー", "人材獲得", "job description", "recruitment plan", "interview evaluation", "hiring", "talent acquisition"
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
Evaluate recommender system quality for the CSX4207 Vinyl Record Store. Use whenever you must compute or report recommender metrics (Precision@k, Recall@k, HitRate@k, MRR, MAP@k, NDCG@k, coverage, diversity, novelty, serendipity, personalization), design an evaluation protocol/split, run a baseline comparison, or write the evaluation section of a course deliverable. Covers formulas, JavaScript reference implementations, and the reporting checklist.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
Rigorous benchmarking of multi-agent coordination systems: experiment design, statistical analysis, human evaluation protocols, and reproducible reporting. NOT FOR ML model evaluation (use llm-evaluation-harness), A/B testing for web products, survey design, or general data science.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
The English summary is being prepared. Showing the original description.
Build an Excel workbook comparing similar companies by revenue, margins, and valuation multiples, which relate company value to sales or earnings. Include formulas, medians, quartiles, and documented sources to support investment or acquisition analysis.
Create and run automated tests that score LLM answers against expected outputs or judging criteria. Monitor progress, inspect individual results, compare models on the same tests, and use score thresholds in CI, an automated checking workflow.
Design evaluation tasks that check whether agents actually complete work. Define requests, simulated user behavior, starting conditions, and verifiable success criteria, then plan difficulty levels, training-data leakage checks, and ongoing maintenance.
Plan and review PufferLib reinforcement learning workflows, where agents learn through rewards. Covers version-specific environment checks, parallel execution, training and evaluation plans, plus checkpoint inspection before loading saved models.
Prepare and check research documents for clinical decision-support evaluation, including evidence profiles, cohort tables, survival plans, and model assessments. Work with aggregate or synthetic inputs, record sources and review status, and keep outputs outside patient care.
Implement Java workflows for Azure AI Foundry projects using SDK examples for authentication, connected resources, datasets, search indexes, and model evaluations. The skill also covers client setup, paginated resource lists, and error handling.
Implement .NET workflows for Azure AI Foundry projects, including agent creation, resource connections, dataset uploads, model deployment inspection, search index management, and evaluations. Examples also cover authentication, asynchronous operations, and resource cleanup.
Compare prompt revisions on a fixed set of test cases to identify regressions, meaning behavior that gets worse after a change. Record model settings, case-level evidence, missing results, costs, and evaluation limits for a reviewable decision.
Design criteria for using an LLM to judge AI responses through scoring or comparisons between two answers. Includes checks for order and length bias, plus validation against human judgments to assess evaluation reliability.
Turn graded execution traces and production logs into model training examples and preferred-versus-rejected response pairs. Select useful records, remove sensitive information, exclude evaluation examples, and preserve links to the original runs.
Prepare an evaluation framework before fine-tuning a language model. Build labeled examples, checks for each failure type, and a base-model benchmark, while calibrating model-based judges against human labels to support comparisons after training.
Explains how PluginEval combines structural checks and experimental model assessments into quality scores. Helps interpret low scores, identify improvement areas, set marketplace thresholds, and explain what evaluation badges actually represent.
Prepare for one company's upcoming earnings announcement with a compact HTML report. It combines the latest earnings call, competitor comparisons, valuation measures, and recent news, with links to supporting sources and calculation details.