Identify gaps in AI evaluation frameworks and create structured evaluation plans.
npx skills add https://github.com/Andy-HNU/AndyClaw --skill ai-evals-andy-hnu
Please help me install this Agent Skill. Skill: ai-evals Source: https://github.com/Andy-HNU/AndyClaw/tree/main/skills/lenny-ai-evals Command: npx skills add https://github.com/Andy-HNU/AndyClaw --skill ai-evals-andy-hnu
Help users create systematic evaluations for AI products using insights from AI practitioners.
Provide a structured evaluation plan, including rubrics and example prompts, for your AI feature.
High-intent search queries and answers about installing and using this skill.
To design an AI evaluation framework, you translate product requirements and user needs into structured plans, using rubrics and test cases to measure output quality, reliability, and usefulness across model iterations.
Creating rubrics for benchmarking AI outputs involves defining structured measurement workflows that align with business metrics, ensuring repeatable test suites quantify model performance accurately.
Yes, you can use structured test suites to validate AI features by creating repeatable evaluation plans that quantify quality and usefulness across different model iterations.
You align AI evaluations with product requirements by identifying gaps in current frameworks and translating them into structured plans that directly measure business metrics and user needs.
To build a repeatable evaluation plan for an AI product, you need to design structured rubrics, example prompts, and measurement workflows that systematically assess model outputs.
yu13130122297Identify uncertainties in research framing, datasets, metrics, and baselines.
cvillamarp-lgtmDesign evaluation rubrics, test cases, and measurement methods for AI features.
ISAQQSAIAutomate LLM evaluation with metrics, human feedback, and benchmarking templates.
ollieb89Evaluate LLM outputs with automated metrics and LLM-as-Judge workflows.
