--- title: Testing and Refining Claude Code Skills with MLflow description: A methodology for testing and automatically refining Claude Code skills (SKILL.md files) using MLflow tracing and LLM-based judges. The approach traces every... canonical: https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Testing and Refining Claude Code Skills with MLflow | daily.dev og:description: A methodology for testing and automatically refining Claude Code skills (SKILL.md files) using MLflow tracing and LLM-based judges. The approach traces every... og:url: https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns og:image: https://api.daily.dev/og/posts/0iNP55BNS.png og:image:alt: Testing and Refining Claude Code Skills with MLflow og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Testing and Refining Claude Code Skills with MLflow **[mlflow](https://daily.dev/sources/MLflow)** · 10 min read · 1 upvotes · 0 comments ## Summary A methodology for testing and automatically refining Claude Code skills (SKILL.md files) using MLflow tracing and LLM-based judges. The approach traces every tool call Claude makes during skill execution, then runs judges — both LLM-based and rule-based — to verify correct behavior. When judges fail, the failing trace and rationale are fed back to Claude Code, which edits the skill file itself. Two real examples from the agent-evaluation skill illustrate how this loop caught Claude bypassing MLflow APIs entirely and a missing skill dependency in the description field. Key lessons: write judges before polishing the skill, use both judge types, and ensure judge rationale is detailed enough for automated refinement. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [5 Tips to Get More Out of Your Claude Code with MLflow](https://daily.dev/posts/5-tips-to-get-more-out-of-your-claude-code-with-mlflow-grvi9kt0u) · mlflow · 1 upvotes · 0 comments - [Evaluating Skills](https://daily.dev/posts/evaluating-skills-jjmwcqiur) · LangChain · 1 upvotes · 0 comments - [How to Make Claude Code Improve from its Own Mistakes](https://daily.dev/posts/how-to-make-claude-code-improve-from-its-own-mistakes-0k82t0t43) · Towards Data Science · 3 upvotes · 0 comments - [Evaluating and Improving Agent Skills with MLflow](https://daily.dev/posts/evaluating-and-improving-agent-skills-with-mlflow-84rj4kktk) · mlflow · 2 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Testing and Refining Claude Code Skills with MLflow","url":"https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns"},"datePublished":"2026-04-20T13:19:22.302Z","dateModified":"2026-04-20T13:21:27.787Z","description":"A methodology for testing and automatically refining Claude Code skills (SKILL.md files) using MLflow tracing and LLM-based judges. The approach traces every...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a8441b7cf12d5c7b837231a0b3bb8e96?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a8441b7cf12d5c7b837231a0b3bb8e96?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"mlflow","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"mlflow","logo":"https://media.daily.dev/image/upload/s--iGp2NwSt--/f_auto/v1743317958/logos/MLflow","url":"https://daily.dev/sources/MLflow"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/testing-and-refining-claude-code-skills-with-mlflow-0inp55bns","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,ai-agents,claude-code","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"mlflow","item":"https://daily.dev/sources/MLflow"},{"@type":"ListItem","position":3,"name":"Testing and Refining Claude Code Skills with MLflow"}]} ```