--- title: How Skillgym Helps You Verify Agent Skills Still Work description: Skillgym is an open-source testing framework from Callstack for verifying AI agent skills (SKILL.md files) still behave correctly after edits. It runs real... canonical: https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Skillgym Helps You Verify Agent Skills Still Work | daily.dev og:description: Skillgym is an open-source testing framework from Callstack for verifying AI agent skills (SKILL.md files) still behave correctly after edits. It runs real... og:url: https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz og:image: https://api.daily.dev/og/posts/oVS6Xuefz.png og:image:alt: How Skillgym Helps You Verify Agent Skills Still Work 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. # How Skillgym Helps You Verify Agent Skills Still Work **[Callstack Blog](https://daily.dev/sources/callstack-blog)** · 7 min read · 1 upvotes · 0 comments ## Summary Skillgym is an open-source testing framework from Callstack for verifying AI agent skills (SKILL.md files) still behave correctly after edits. It runs real agent sessions against CLI runners like Claude Code, Codex, OpenCode, and Cursor Agent, then lets you write TypeScript assertions against the results — checking which skills were used, which files were read, command ordering, final output, and token usage. It supports isolated workspaces per test case and cross-runner matrix testing to catch regressions that only appear on specific agents. The tool addresses the problem of silent behavioral regressions when editing agent skill definitions, replacing manual prompt-and-hope workflows with reproducible, comparable test runs. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Skillgym Helps You Verify Agent Skills Still Work After Every Change](https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-after-every-change-uciahav2f) · Callstack Blog · 0 upvotes · 0 comments - [AddyOsmani.com](https://daily.dev/posts/addyosmani-com-uuv0iho2m) · Addy Osmani · 191 upvotes · 6 comments - [Manage agent skills with GitHub CLI](https://daily.dev/posts/manage-agent-skills-with-github-cli-cwqtearpx) · GitHub Changelog · 1 upvotes · 0 comments - [Improving skill-creator: Test, measure, and refine Agent Skills](https://daily.dev/posts/improving-skill-creator-test-measure-and-refine-agent-skills-obmf0r4sa) · Claude · 75 upvotes · 3 comments - [Agent Skills explained: Replacing AGENTS.md with reusable AI knowledge](https://daily.dev/posts/agent-skills-explained-replacing-agents-md-with-reusable-ai-knowledge-4lgrqdva9) · SwiftLee · 1 upvotes · 0 comments --- Tags: [#testing](https://daily.dev/tags/testing), [#typescript](https://daily.dev/tags/typescript), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz) ```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":"How Skillgym Helps You Verify Agent Skills Still Work","url":"https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz"},"datePublished":"2026-04-20T10:59:44.220Z","dateModified":"2026-04-20T11:00:10.375Z","description":"Skillgym is an open-source testing framework from Callstack for verifying AI agent skills (SKILL.md files) still behave correctly after edits. It runs real...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/24c2689cad8fd2694693c43aa339a374?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/24c2689cad8fd2694693c43aa339a374?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Callstack Blog","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":"Callstack Blog","logo":"https://media.daily.dev/image/upload/s--3qItoroi--/f_auto,q_auto/v1774179048/logos/callstack-blog?_a=BAMAMiWQ0","url":"https://daily.dev/sources/callstack-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-skillgym-helps-you-verify-agent-skills-still-work-ovs6xuefz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"testing,typescript,ai-agents","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Callstack Blog","item":"https://daily.dev/sources/callstack-blog"},{"@type":"ListItem","position":3,"name":"How Skillgym Helps You Verify Agent Skills Still Work"}]} ```