Delegate independent tasks to specialized agents working concurrently with isolated context.
AI Evals
ai-evals
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to systematically measure AI output quality.
SKILL.md
Full skill instructions
AI Evals
Help the user create systematic evaluations for AI products using insights from AI practitioners.
How to Help
When the user asks for help with AI evals:
- Understand what they're evaluating - Ask what AI feature or model they're testing and what "good" looks like
- Help design the eval approach - Suggest rubrics, test cases, and measurement methods
- Guide implementation - Help them think through edge cases, scoring criteria, and iteration cycles
- Connect to product requirements - Ensure evals align with actual user needs, not just technical metrics
Core Principles
Evals are the new PRD
Brendan Foody: "If the model is the product, then the eval is the product requirement document." Evals define what success looks like in AI products—they're not optional quality checks, they're core specifications.
Evals are a core product skill
Hamel Husain & Shreya Shankar: "Both the chief product officers of Anthropic and OpenAI shared that evals are becoming the most important new skill for product builders." This isn't just for ML engineers—product people need to master this.
The workflow matters
Building good evals involves error analysis, open coding (writing down what's wrong), clustering failure patterns, and creating rubrics. It's a systematic process, not a one-time test.
Questions to Help Users
- "What does 'good' look like for this AI output?"
- "What are the most common failure modes you've seen?"
- "How will you know if the model got better or worse?"
- "Are you measuring what users actually care about?"
- "Have you manually reviewed enough outputs to understand failure patterns?"
Common Mistakes to Flag
- Skipping manual review - You can't write good evals without first understanding failure patterns through manual trace analysis
- Using vague criteria - "The output should be good" isn't an eval; you need specific, measurable criteria
- LLM-as-judge without validation - If using an LLM to judge, you must validate that judge against human experts
- Likert scales over binary - Force Pass/Fail decisions; 1-5 scales produce meaningless averages
Deep Dive
For all 2 insights from 2 guests, see references/guest-insights.md
Related Skills
- Building with LLMs
- AI Product Strategy
- Evaluating New Technology
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
