[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-google-google-agents-cli-eval-de":3,"guides-for-google-google-agents-cli-eval":230,"similar-k17dsn9qz29ezffmm5p52x70js867wsh":231},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":20,"identity":187,"isFallback":192,"parentExtension":193,"providers":194,"relations":199,"repo":201,"workflow":227},1778053359436.7268,"k17dsn9qz29ezffmm5p52x70js867wsh",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"This skill should be used when the user wants to \"run an evaluation\", \"evaluate my ADK agent\", \"write an evalset\", \"debug eval scores\", \"compare eval results\", or needs guidance on ADK (Agent Development Kit) evaluation methodology and the eval-fix loop. Covers eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Part of the Google ADK (Agent Development Kit) skills suite. Do NOT use for API code patterns (use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).",{},"ADK Evaluation Guide","https://github.com/google/agents-cli/tree/HEAD/skills/google-agents-cli-eval",[15,16,17,18,19],"adk","evaluation","testing","documentation","gemini",{"_creationTime":21,"_id":22,"extensionId":5,"locale":23,"result":24,"trustSignals":176,"workflow":185},1778053387143.3616,"kn7fm3xfyemtee8xxhqp24fets86701v","en",{"checks":25,"evaluatedAt":166,"extensionSummary":167,"promptVersionExtension":168,"promptVersionScoring":169,"rationale":170,"score":171,"summary":172,"tags":173,"targetMarket":174,"tier":175},[26,31,34,37,41,44,49,53,56,59,63,67,70,74,77,80,83,86,89,92,96,100,104,108,112,115,118,121,125,128,131,134,137,140,144,147,150,153,156,159,163],{"category":27,"check":28,"severity":29,"summary":30},"Practical Utility","Problem relevance","pass","The description clearly states the problem and the user intent for using the skill, focusing on ADK evaluation methodology and the eval-fix loop.",{"category":27,"check":32,"severity":29,"summary":33},"Unique selling proposition","The skill offers a comprehensive guide to ADK evaluation, covering metrics, evalsets, and the eval-fix loop, which is a specific and valuable capability beyond a simple prompt.",{"category":27,"check":35,"severity":29,"summary":36},"Production readiness","The skill provides detailed guidance on the entire ADK evaluation lifecycle, including running evaluations, interpreting scores, debugging, and iterating, making it production-ready for agent development.",{"category":38,"check":39,"severity":29,"summary":40},"Scope","Single responsibility principle","The skill focuses exclusively on ADK evaluation methodology, including metrics, evalsets, and the eval-fix loop, with clear non-goals stated in the description.",{"category":38,"check":42,"severity":29,"summary":43},"Description quality","The description is concise, readable, and accurately reflects the skill's focus on ADK evaluation, including specific use cases and explicit non-goals.",{"category":45,"check":46,"severity":47,"summary":48},"Invocation","Scoped tools","not_applicable","This skill does not expose specific tools; it provides guidance and methodology.",{"category":50,"check":51,"severity":29,"summary":52},"Documentation","Configuration & parameter reference","The SKILL.md file provides a detailed reference for configuration schemas and common evaluation scenarios, including examples.",{"category":38,"check":54,"severity":47,"summary":55},"Tool naming","This skill does not expose specific tools with names.",{"category":38,"check":57,"severity":47,"summary":58},"Minimal I/O surface","This skill does not have explicit tools with input/output schemas.",{"category":60,"check":61,"severity":29,"summary":62},"License","License usability","The skill is licensed under Apache-2.0, a permissive open-source license, as indicated in the SKILL.md frontmatter and confirmed by the LICENSE file.",{"category":64,"check":65,"severity":47,"summary":66},"Maintenance","Commit recency","Commit recency data is not available for this specific skill file.",{"category":64,"check":68,"severity":47,"summary":69},"Dependency Management","No third-party dependencies are directly managed by this skill; it relies on the agents-cli tool itself.",{"category":71,"check":72,"severity":47,"summary":73},"Security","Secret Management","The skill provides guidance and does not handle secrets directly.",{"category":71,"check":75,"severity":29,"summary":76},"Injection","The skill provides guidance and does not load external data or execute arbitrary code.",{"category":71,"check":78,"severity":29,"summary":79},"Transitive Supply-Chain Grenades","The skill is self-contained and does not fetch remote content or execute external scripts.",{"category":71,"check":81,"severity":29,"summary":82},"Sandbox Isolation","The skill provides guidance and does not modify files or interact with the file system.",{"category":71,"check":84,"severity":29,"summary":85},"Sandbox escape primitives","The skill does not contain any scripts or instructions that could lead to sandbox escape.",{"category":71,"check":87,"severity":29,"summary":88},"Data Exfiltration","The skill does not make outbound calls or handle confidential data.",{"category":71,"check":90,"severity":29,"summary":91},"Hidden Text Tricks","The bundled files do not contain any hidden-steering tricks, invisible characters, or obfuscated content.",{"category":93,"check":94,"severity":29,"summary":95},"Hooks","Opaque code execution","The skill does not contain any obfuscated code or runtime script fetching.",{"category":97,"check":98,"severity":47,"summary":99},"Portability","Structural Assumption","The skill provides guidance and does not make assumptions about user project structure.",{"category":101,"check":102,"severity":47,"summary":103},"Trust","Issues Attention","Issue data is not available for this skill.",{"category":105,"check":106,"severity":29,"summary":107},"Versioning","Release Management","The skill has a version defined (0.1.2) in its frontmatter.",{"category":109,"check":110,"severity":47,"summary":111},"Code Execution","Validation","This skill does not execute code or process structured input/output.",{"category":71,"check":113,"severity":29,"summary":114},"Unguarded Destructive Operations","The skill is purely informational and contains no destructive operations.",{"category":109,"check":116,"severity":47,"summary":117},"Error Handling","This skill does not execute code and therefore does not require error handling in that context.",{"category":109,"check":119,"severity":47,"summary":120},"Logging","This skill does not execute code and therefore does not require logging.",{"category":122,"check":123,"severity":29,"summary":124},"Compliance","GDPR","The skill provides guidance and does not process personal data.",{"category":122,"check":126,"severity":29,"summary":127},"Target market","The skill's content is general to ADK evaluation and has no specific regional dependencies, making it global.",{"category":97,"check":129,"severity":47,"summary":130},"Runtime stability","The skill does not execute code and thus has no runtime stability assumptions.",{"category":45,"check":132,"severity":29,"summary":133},"Precise Purpose","The description clearly states the skill's purpose (ADK evaluation) and its non-goals (API code patterns, deployment, scaffolding).",{"category":45,"check":135,"severity":29,"summary":136},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and use cases.",{"category":50,"check":138,"severity":29,"summary":139},"Concise Body","The SKILL.md body is well-structured and under 500 lines, with references to separate files for deeper material.",{"category":141,"check":142,"severity":29,"summary":143},"Context","Progressive Disclosure","The SKILL.md outlines the evaluation flow and links to detailed reference files for specific aspects like metrics and evalset schemas.",{"category":141,"check":145,"severity":47,"summary":146},"Forked exploration","This skill is instructional and does not involve deep exploration that would require forking.",{"category":27,"check":148,"severity":29,"summary":149},"Usage examples","The skill provides numerous concrete examples for running evaluations, debugging, and configuration, covering key functionalities.",{"category":27,"check":151,"severity":29,"summary":152},"Edge cases","The skill addresses common pitfalls and provides advice on how to handle them, such as avoiding shortcuts and understanding failure modes.",{"category":109,"check":154,"severity":47,"summary":155},"Tool Fallback","This skill does not rely on external tools and has no fallback requirements.",{"category":97,"check":157,"severity":29,"summary":158},"Stack assumptions","The skill clearly states its prerequisites, including Python version and the agents-cli tool, upfront.",{"category":160,"check":161,"severity":29,"summary":162},"Safety","Halt on unexpected state","While not code-based, the skill implicitly guides users to halt and reassess if evaluation results are unexpected or scores are low.",{"category":97,"check":164,"severity":29,"summary":165},"Cross-skill coupling","The skill is self-contained and clearly lists related skills for adjacent tasks without implicit dependencies.",1778053370809,"This skill provides detailed instructions and best practices for evaluating ADK agents, covering various metrics, evalset schemas, and common failure scenarios. It guides users through the iterative eval-fix loop and offers advice on configuration and debugging.","2.0.0","3.4.0","This skill is exceptionally well-documented and focused, providing clear, actionable guidance on ADK evaluation. It excels in problem relevance, production readiness, and scope. All checks passed or were not applicable, reflecting a high-quality, focused documentation skill.",98,"A comprehensive guide to ADK agent evaluation methodology and the eval-fix loop.",[15,16,17,18,19],"global","verified",{"codeQuality":177,"collectedAt":178,"documentation":179,"maintenance":181,"security":182,"testCoverage":184},{},1778053361088,{"descriptionLength":180,"readmeSize":8},585,{},{"hasNpmPackage":183,"smitheryVerified":183},false,{"hasCi":183,"hasTests":183},{"updatedAt":186},1778053387143,{"githubOwner":188,"githubRepo":189,"locale":23,"slug":190,"type":191},"google","agents-cli","google-agents-cli-eval","skill",true,null,{"extract":195,"llm":198},{"commitSha":196,"license":197},"9e2966f509ae8ee8a866cf7ecc6e227209f347ff","Apache-2.0",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":200},"kd74jrvbwp33xw6azpzkw7r7vs8644t0",{"_creationTime":202,"_id":200,"identity":203,"providers":205,"workflow":224},1777995558409.8618,{"githubOwner":188,"githubRepo":189,"sourceUrl":204},"https://github.com/google/agents-cli",{"discover":206,"github":209},{"sources":207},[208],"skills-sh",{"closedIssues90d":210,"forks":211,"homepage":212,"license":197,"openIssues90d":213,"pushedAt":214,"readmeSize":215,"stars":216,"topics":217},3,246,"https://google.github.io/agents-cli/",7,1777501706000,8553,2086,[15,218,219,220,19,221,222,223],"agent-development-kit","agents","coding-agent","generative-ai","gemini-enterprise-agent-platform","google-cloud",{"discoverAt":225,"extractAt":226,"githubAt":226,"updatedAt":226},1777995558409,1778053360399,{"anyEnrichmentAt":228,"extractAt":229,"githubAt":228,"llmAt":186,"updatedAt":186},1778053359868,1778053359436,[],[232,262,283,303,332,361],{"_creationTime":233,"_id":234,"community":235,"display":236,"identity":246,"providers":250,"relations":256,"workflow":258},1778053622473.6594,"k171jc4epkmqq2y76n42e3eg0s866rf8",{"reviewCount":8},{"description":237,"installMethods":238,"name":239,"sourceUrl":240,"tags":241},"Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations) and blank spots (gaps that could be addressed). Use before finalizing non-fiction or when feedback feels incomplete.",{},"Blind Spot Detective","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/writing/analysis/blind-spot-detective",[242,243,244,245,18],"writing","analysis","non-fiction","diagnostic",{"githubOwner":247,"githubRepo":248,"locale":23,"slug":249,"type":191},"jwynia","agent-skills","blind-spot-detective",{"extract":251,"llm":254},{"commitSha":252,"license":253},"e02ec7e226a6e4f8419fd3b88a1d8e472d421b32","MIT",{"promptVersionExtension":168,"promptVersionScoring":169,"score":255,"targetMarket":174,"tier":175},99,{"repoId":257},"kd7efn3mprpa8rd8vm5hw5ebzx864fph",{"anyEnrichmentAt":259,"extractAt":260,"githubAt":259,"llmAt":261,"updatedAt":261},1778053625386,1778053622473,1778054012696,{"_creationTime":263,"_id":264,"community":265,"display":266,"identity":276,"providers":278,"relations":281,"workflow":282},1778053359436.7288,"k1780yft5sxt8fewxcc5bm1941866rzt",{"reviewCount":8},{"description":267,"installMethods":268,"name":269,"sourceUrl":270,"tags":271},"This skill should be used when the user wants to \"develop an agent\", \"build an agent using ADK\", \"run the agent locally\", \"debug agent code\", \"test an agent\", \"deploy an agent\", \"publish an agent\", \"monitor an agent\", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.",{},"ADK Development Workflow & Guidelines","https://github.com/google/agents-cli/tree/HEAD/skills/google-agents-cli-workflow",[15,272,273,274,275],"agent-development","workflow","guidelines","cli",{"githubOwner":188,"githubRepo":189,"locale":23,"slug":277,"type":191},"google-agents-cli-workflow",{"extract":279,"llm":280},{"commitSha":196,"license":197},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":200},{"anyEnrichmentAt":228,"extractAt":229,"githubAt":228,"llmAt":186,"updatedAt":186},{"_creationTime":284,"_id":285,"community":286,"display":287,"identity":296,"providers":298,"relations":301,"workflow":302},1778053359436.7283,"k173ynpdc9ckbq2dqv7r5xwtqh866w6z",{"reviewCount":8},{"description":288,"installMethods":289,"name":290,"sourceUrl":291,"tags":292},"This skill should be used when the user wants to \"create an agent project\", \"start a new ADK project\", \"build me a new agent\", \"add CI/CD to my project\", \"add deployment\", \"enhance my project\", or \"upgrade my project\". Part of the Google ADK (Agent Development Kit) skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).",{},"ADK Project Scaffolding Guide","https://github.com/google/agents-cli/tree/HEAD/skills/google-agents-cli-scaffold",[189,293,15,294,275,295],"scaffolding","python","development-workflow",{"githubOwner":188,"githubRepo":189,"locale":23,"slug":297,"type":191},"google-agents-cli-scaffold",{"extract":299,"llm":300},{"commitSha":196,"license":197},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":200},{"anyEnrichmentAt":228,"extractAt":229,"githubAt":228,"llmAt":186,"updatedAt":186},{"_creationTime":304,"_id":305,"community":306,"display":307,"identity":318,"providers":322,"relations":326,"workflow":328},1778054663200.0623,"k1787qemz1vae1jy4xsx7c2zyn867dwd",{"reviewCount":8},{"description":308,"installMethods":309,"name":310,"sourceUrl":311,"tags":312},"Maps the full customer journey from first touch to advocacy. Generates a comprehensive customer-journey.md with all stages, touchpoints, emotions, pain points, opportunities, Mermaid diagrams, and metrics. Use when mapping customer experience, designing onboarding flows, identifying churn risks, or optimizing conversion funnels.",{},"Customer Journey Mapper","https://github.com/onewave-ai/claude-skills/tree/HEAD/customer-journey-mapper",[313,314,315,316,18,317],"customer-experience","journey-mapping","strategy","marketing","reporting",{"githubOwner":319,"githubRepo":320,"locale":23,"slug":321,"type":191},"onewave-ai","claude-skills","customer-journey-mapper",{"extract":323,"llm":325},{"commitSha":324,"license":253},"eb3d80be32b6cafcf0d5df1c1b8a95df75838271",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":327},"kd71e43dj0b7ak5e55pyshxp4n864t6p",{"anyEnrichmentAt":329,"extractAt":330,"githubAt":329,"llmAt":331,"updatedAt":331},1778054667983,1778054663200,1778055270278,{"_creationTime":333,"_id":334,"community":335,"display":336,"identity":348,"providers":351,"relations":355,"workflow":357},1778054812528.7205,"k179w7m3n2zkvrbhmmwn1stces86799q",{"reviewCount":8},{"description":337,"installMethods":338,"name":339,"sourceUrl":340,"tags":341},"3D web graphics with Three.js (WebGL/WebGPU). Capabilities: scenes, cameras, geometries, materials, lights, animations, model loading (GLTF/FBX), PBR materials, shadows, post-processing (bloom, SSAO, SSR), custom shaders, instancing, LOD, physics, VR/XR. Actions: create, build, animate, render 3D scenes/models. Keywords: Three.js, WebGL, WebGPU, 3D graphics, scene, camera, geometry, material, light, animation, GLTF, FBX, OrbitControls, PBR, shadow mapping, post-processing, bloom, SSAO, shader, instancing, LOD, WebXR, VR, AR, product configurator, data visualization, architectural walkthrough, interactive 3D, canvas. Use when: creating 3D visualizations, building WebGL/WebGPU apps, loading 3D models, adding animations, implementing VR/XR, creating interactive graphics, building product configurators.",{},"3D Graphics with Three.js","https://github.com/samhvw8/dot-claude/tree/HEAD/skills/3d-graphics",[342,343,344,345,18,346,347],"three-js","webgl","webgpu","3d-graphics","learning","examples",{"githubOwner":349,"githubRepo":350,"locale":23,"slug":345,"type":191},"samhvw8","dot-claude",{"extract":352,"llm":354},{"commitSha":353,"license":253},"28c76162116d2eedab131c0e1548fdc76a2999f7",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":356},"kd79ad9dpqazy79y2s6rvajgjn865xek",{"anyEnrichmentAt":358,"extractAt":359,"githubAt":358,"llmAt":360,"updatedAt":360},1778054813688,1778054812528,1778054896678,{"_creationTime":362,"_id":363,"community":364,"display":365,"identity":374,"providers":377,"relations":381,"workflow":383},1778054564989.5369,"k1767w6z2kv4rgf7gryn1saw6x867n0n",{"reviewCount":8},{"description":366,"installMethods":367,"name":368,"sourceUrl":369,"tags":370},"Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.",{},"ReClaude","https://github.com/brianlovin/claude-config/tree/HEAD/skills/reclaude",[18,371,372,373],"refactoring","markdown","claude-config",{"githubOwner":375,"githubRepo":373,"locale":23,"slug":376,"type":191},"brianlovin","reclaude",{"extract":378,"llm":380},{"commitSha":379,"license":47},"1a9819ebf3fee811150fc76cbe177ea4e5f747ff",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":382},"kd7c7ftew8fsa52skn0fm3rfvd864fmn",{"anyEnrichmentAt":384,"extractAt":385,"githubAt":384,"llmAt":386,"updatedAt":386},1778054565711,1778054564989,1778054628464]