Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When you need to systematically measure LLM application performance, compare models/prompts, detect regressions before deployment, or establish evaluation baselines.
EvaluationSuite class to run metrics over test cases asynchronouslyreferences/details.md for deeper patterns and worked examplesA structured evaluation framework with scored metrics and raw results, enabling regression detection, model comparison, and confident production releases.
Use Cases
A team updates their RAG prompt and worries about quality drop. They use this skill to build an EvaluationSuite with BLEU, BERTScore, and groundedness checks over a fixed test set. Running before/after yields comparable scores, catching a regression in recall@K and preventing a bad deploy.
A startup compares two LLM providers for their chatbot. Using the skill's human eval dimensions and LLM-as-Judge pairwise mode, they score accuracy, fluency, and safety on 200 queries. The report guides vendor selection and sets a quality baseline for future tracking.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File