Official Anthropic Agent Skills repo with document and example packs
Agent Evaluation (Context Engineering)
SkillBuild regression suites, rubrics and quality gates for non-deterministic agent pipelines
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Agent Evaluation (Context Engineering)
From Muratcan Koylan's Agent Skills for Context Engineering collection.
Agents don't have a single right answer and behave differently run to run, so normal unit tests only get you part of the way. This skill helps you set up:
- Deterministic checks where they apply
- Multi-dimensional rubrics for the fuzzy parts
- Regression suites and baseline comparisons
- Quality gates before deploy and monitoring after
LLM-judge design itself lives in the collection's advanced-evaluation skill.
No reviews yet
Used it? Write the first review.
Similar skills
Official Browserbase skills for cloud browser automation
Production agent skills from Matt Pocock's .agents directory
Build and review ASP.NET Core apps with current official guidance
Official OpenAI Agent Skills for Codex and ChatGPT workflows
Translate Figma into production code at 1:1 fidelity