[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CV3DM06P255H7T63C1EY4K":3,"skill-same:01M7CV3DM06P255H7T63C1EY4K":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CV3DM06P255H7T63C1EY4K","behavioral-evals",null,"Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.","realsudarshan\u002FSD-skill","realsudarshan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128029723?v=4","01M7CTP2JEKQ9KBJ51NRZ2777Z","Sudarshan Dhakal","01M7CTP2JYR2PRY3BWGA30HX7J",0,"MIT","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: behavioral-evals\ndescription: Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.\n---\n\n# Behavioral Evals\n\n## Overview\n\nBehavioral evaluations (evals) are tests that validate the **agent's decision-making** (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.\n\n> [!NOTE]\n> **Single Source of Truth**: For core concepts, policies, running tests, and general best practices, always refer to **[evals\u002FREADME.md](file:\u002F\u002F\u002FUsers\u002Fabhipatel\u002Fcode\u002Fgemini-cli\u002Fdocs\u002Fevals\u002FREADME.md)**.\n\n---\n\n## ðŸ”„ Workflow Decision Tree\n\n1.  **Does a prompt\u002Ftool change need validation?**\n    *   *No* -> Normal integration tests.\n    *   *Yes* -> Continue below.\n2.  **Is it UI\u002FInteraction heavy?**\n    *   *Yes* -> Use `appEvalTest` (`AppRig`). See **[creating.md](references\u002Fcreating.md)**.\n    *   *No* -> Use `evalTest` (`TestRig`). See **[creating.md](references\u002Fcreating.md)**.\n3.  **Is it a new test?**\n    *   *Yes* -> Set policy to `USUALLY_PASSES`.\n    *   *No* -> `ALWAYS_PASSES` (locks in regression).\n4.  **Are you fixing a failure or promoting a test?**\n    *   *Fixing* -> See **[fixing.md](references\u002Ffixing.md)**.\n    *   *Promoting* -> See **[promoting.md](references\u002Fpromoting.md)**.\n\n---\n\n## ðŸ“‹ Quick Checklist\n\n### 1. Setup Workspace\nSeed the workspace with necessary files using the `files` object to simulate a realistic scenario (e.g., NodeJS project with `package.json`).\n*   *Details in **[creating.md](references\u002Fcreating.md)***\n\n### 2. Write Assertions\nAudit agent decisions using `rig.setBreakpoint()` (AppRig only) or index verification on `rig.readToolLogs()`.\n*   *Details in **[creating.md](references\u002Fcreating.md)***\n\n### 3. Verify\nRun single tests locally with Vitest. Confirm stability locally before relying on CI workflows.\n*   *See **[evals\u002FREADME.md](file:\u002F\u002F\u002FUsers\u002Fabhipatel\u002Fcode\u002Fgemini-cli\u002Fdocs\u002Fevals\u002FREADME.md)** for running commands.*\n\n---\n\n## ðŸ“¦ Bundled Resources\n\nDetailed procedural guides:\n*   **[creating.md](references\u002Fcreating.md)**: Assertion strategies, Rig selection, Mock MCPs.\n*   **[fixing.md](references\u002Ffixing.md)**: Step-by-step automated investigation, architecture diagnosis guidelines.\n*   **[promoting.md](references\u002Fpromoting.md)**: Candidate identification criteria and threshold guidelines.\n","# Behavioral Evals\n\n## Overview\n\nBehavioral evaluations (evals) are tests that validate the **agent's decision-making** (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.\n\n> [!NOTE]\n> **Single Source of Truth**: For core concepts, policies, running tests, and general best practices, always refer to **[evals\u002FREADME.md](file:\u002F\u002F\u002FUsers\u002Fabhipatel\u002Fcode\u002Fgemini-cli\u002Fdocs\u002Fevals\u002FREADME.md)**.\n\n---\n\n## ðŸ”„ Workflow Decision Tree\n\n1.  **Does a prompt\u002Ftool change need validation?**\n    *   *No* -> Normal integration tests.\n    *   *Yes* -> Continue below.\n2.  **Is it UI\u002FInteraction heavy?**\n    *   *Yes* -> Use `appEvalTest` (`AppRig`). See **[creating.md](references\u002Fcreating.md)**.\n    *   *No* -> Use `evalTest` (`TestRig`). See **[creating.md](references\u002Fcreating.md)**.\n3.  **Is it a new test?**\n    *   *Yes* -> Set policy to `USUALLY_PASSES`.\n    *   *No* -> `ALWAYS_PASSES` (locks in regression).\n4.  **Are you fixing a failure or promoting a test?**\n    *   *Fixing* -> See **[fixing.md](references\u002Ffixing.md)**.\n    *   *Promoting* -> See **[promoting.md](references\u002Fpromoting.md)**.\n\n---\n\n## ðŸ“‹ Quick Checklist\n\n### 1. Setup Workspace\nSeed the workspace with necessary files using the `files` object to simulate a realistic scenario (e.g., NodeJS project with `package.json`).\n*   *Details in **[creating.md](references\u002Fcreating.md)***\n\n### 2. Write Assertions\nAudit agent decisions using `rig.setBreakpoint()` (AppRig only) or index verification on `rig.readToolLogs()`.\n*   *Details in **[creating.md](references\u002Fcreating.md)***\n\n### 3. Verify\nRun single tests locally with Vitest. Confirm stability locally before relying on CI workflows.\n*   *See **[evals\u002FREADME.md](file:\u002F\u002F\u002FUsers\u002Fabhipatel\u002Fcode\u002Fgemini-cli\u002Fdocs\u002Fevals\u002FREADME.md)** for running commands.*\n\n---\n\n## ðŸ“¦ Bundled Resources\n\nDetailed procedural guides:\n*   **[creating.md](references\u002Fcreating.md)**: Assertion strategies, Rig selection, Mock MCPs.\n*   **[fixing.md](references\u002Ffixing.md)**: Step-by-step automated investigation, architecture diagnosis guidelines.\n*   **[promoting.md](references\u002Fpromoting.md)**: Candidate identification criteria and threshold guidelines.\n",{"name":5,"description":7},"main","92c2f40ebfad0c0aa3cc1faa89ffd6b23f9e8d1b","gemini\u002Fgemini-github-behavioral-evals","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill","https:\u002F\u002Fsd-skill.vercel.app","https:\u002F\u002Fgithub.com\u002Frealsudarshan","sudarshandhakal.com.np","Innvotative","2026-11-12 23:03:50",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add realsudarshan\u002FSD-skill --skill behavioral-evals",{"tool":39,"command":40},"bunx","bunx skills add realsudarshan\u002FSD-skill --skill behavioral-evals",{"tool":42,"command":43},"pnpm","pnpm dlx skills add realsudarshan\u002FSD-skill --skill behavioral-evals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002FSKILL.md",true,[47,53,57,63,67,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"assets\u002Finteractive_eval.ts.txt","ASSET","资产文件",882,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Fassets\u002Finteractive_eval.ts.txt",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Fstandard_eval.ts.txt",996,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Fassets\u002Fstandard_eval.ts.txt",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fcreating.md","REFERENCE","参考文档",4602,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Freferences\u002Fcreating.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ffixing.md",4757,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Freferences\u002Ffixing.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fpromoting.md",1920,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Freferences\u002Fpromoting.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Frunning.md",2571,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fgemini\u002Fgemini-github-behavioral-evals\u002Freferences\u002Frunning.md",[76,85,93,101,109,117],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CW5Y6EPMPMNDWE4EN2GXRX","winui-app","Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CW5RWFX7616ENEG573VFWG","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fvercel-deploy\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7CW5M4VZHQPWG764X1W0S3B","security-best-practices","Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review\u002Freport, or secure-by-default coding help. Trigger only for supported languages (python, javascript\u002Ftypescript, go). Do not trigger for general code review, debugging, or non-security tasks.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fsecurity-best-practices\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fsecurity-best-practices\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7CW5EBTWA7PQ54HYFT1YW39","playwright","Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fplaywright\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fplaywright\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7CW4DA7SZ4D9JMR3P7VJVM0","openai-docs","Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fopenai-docs\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fopenai-docs\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7CW3EHY7X60KB9SYEMRD3YR","netlify-deploy","Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site\u002Frepo on Netlify, including preview and production deploys.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fnetlify-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fnetlify-deploy\u002FSKILL.md",[],[]]