[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-vertex-ai":3,"mdc-7idqyh-key":52,"related-repo-google-cloud-vertex-ai":197,"related-org-google-cloud-vertex-ai":247},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":47,"sourceUrl":50,"mdContent":51},"vertex-ai","deploy and tune Vertex AI models","Primary Router for Vertex AI skills. Use this skill when the user wants to work with Google Cloud Vertex AI (e.g., deploying models, running inference, or tuning models). This skill routes to vertex-deploy, vertex-inference, or vertex-tuning.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20,22],{"name":14,"slug":15,"type":16},"LLM","llm","tag",{"name":18,"slug":19,"type":16},"Machine Learning","machine-learning",{"name":21,"slug":4,"type":16},"Vertex AI",{"name":9,"slug":8,"type":16},762,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-samples","2026-07-12T07:38:30.746937",null,296,[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,4,45,46],"automl","colab","colab-enterprise","gemini","gemini-api","genai","generative-ai","google-cloud-platform","ml","mlops","model","model-garden","notebook","pipeline","predictions","samples","vertexai","workbench",{"repoUrl":24,"stars":23,"forks":27,"topics":48,"description":49},[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,4,45,46],"Notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-samples\u002Ftree\u002FHEAD\u002Fskills\u002Fvertex-ai","---\nname: vertex-ai\ndescription: >\n  Primary Router for Vertex AI skills. Use this skill when the user wants to work\n  with Google Cloud Vertex AI (e.g., deploying models, running inference, or tuning models).\n  This skill routes to vertex-deploy, vertex-inference, or vertex-tuning.\n---\n\n# Vertex AI Skills (Primary Router)\n\n## Overview\n\nThis skill acts as the primary router for all Vertex AI related tasks. Google Cloud Vertex AI provides capabilities for deploying open models, running inference against Generative AI models (like Gemini and open models), and fine-tuning models.\n\nYour first step is to determine the user's main objective and then read the appropriate sub-skill.\n\n## Workflow Decision Tree\n\n1.  **Objective Category**: What does the user want to do with Vertex AI?\n\n    -   **Use Gemini SDK (Gen AI SDK)**: If the user explicitly asks about using the Gemini API on Vertex AI with the Gen AI SDK, or asks for features like Live API, multimedia generation, caching, or batch prediction, stop reading this file and IMMEDIATELY read the skill instructions located at `..\u002Fgenai-sdk\u002FSKILL.md`.\n    -   **Deploy Models**: If the user wants to deploy an Open Model from Model Garden or deploy custom weights to create a Vertex AI Endpoint, stop reading this file and IMMEDIATELY read the skill instructions located at `..\u002Fvertex-deploy\u002FSKILL.md`.\n    -   **Run Inference (Text Generation, Chat, Embeddings)**: If the user wants to connect to Vertex AI to generate text, chat, or get embeddings using models like Gemini, Llama, DeepSeek, etc., stop reading this file and IMMEDIATELY read the skill instructions located at `..\u002Fvertex-inference\u002FSKILL.md`.\n    -   **Model Tuning \u002F Fine-Tuning**: If the user wants to fine-tune an Open Model or a Gemini Model, stop reading this file and IMMEDIATELY read the skill instructions located at `..\u002Fvertex-tuning\u002FSKILL.md`.\n\n    -   **Unknown \u002F Not Listed**: If the objective is not clearly one of the above, **STOP**. Ask the user to clarify whether they are looking to deploy a model, run inference, or tune a model on Vertex AI.\n",{"data":53,"body":54},{"name":4,"description":6},{"type":55,"children":56},"root",[57,66,73,79,84,90],{"type":58,"tag":59,"props":60,"children":62},"element","h1",{"id":61},"vertex-ai-skills-primary-router",[63],{"type":64,"value":65},"text","Vertex AI Skills (Primary Router)",{"type":58,"tag":67,"props":68,"children":70},"h2",{"id":69},"overview",[71],{"type":64,"value":72},"Overview",{"type":58,"tag":74,"props":75,"children":76},"p",{},[77],{"type":64,"value":78},"This skill acts as the primary router for all Vertex AI related tasks. Google Cloud Vertex AI provides capabilities for deploying open models, running inference against Generative AI models (like Gemini and open models), and fine-tuning models.",{"type":58,"tag":74,"props":80,"children":81},{},[82],{"type":64,"value":83},"Your first step is to determine the user's main objective and then read the appropriate sub-skill.",{"type":58,"tag":67,"props":85,"children":87},{"id":86},"workflow-decision-tree",[88],{"type":64,"value":89},"Workflow Decision Tree",{"type":58,"tag":91,"props":92,"children":93},"ol",{},[94],{"type":58,"tag":95,"props":96,"children":97},"li",{},[98,104,106],{"type":58,"tag":99,"props":100,"children":101},"strong",{},[102],{"type":64,"value":103},"Objective Category",{"type":64,"value":105},": What does the user want to do with Vertex AI?",{"type":58,"tag":107,"props":108,"children":109},"ul",{},[110,129,146,163,180],{"type":58,"tag":95,"props":111,"children":112},{},[113,118,120,127],{"type":58,"tag":99,"props":114,"children":115},{},[116],{"type":64,"value":117},"Use Gemini SDK (Gen AI SDK)",{"type":64,"value":119},": If the user explicitly asks about using the Gemini API on Vertex AI with the Gen AI SDK, or asks for features like Live API, multimedia generation, caching, or batch prediction, stop reading this file and IMMEDIATELY read the skill instructions located at ",{"type":58,"tag":121,"props":122,"children":124},"code",{"className":123},[],[125],{"type":64,"value":126},"..\u002Fgenai-sdk\u002FSKILL.md",{"type":64,"value":128},".",{"type":58,"tag":95,"props":130,"children":131},{},[132,137,139,145],{"type":58,"tag":99,"props":133,"children":134},{},[135],{"type":64,"value":136},"Deploy Models",{"type":64,"value":138},": If the user wants to deploy an Open Model from Model Garden or deploy custom weights to create a Vertex AI Endpoint, stop reading this file and IMMEDIATELY read the skill instructions located at ",{"type":58,"tag":121,"props":140,"children":142},{"className":141},[],[143],{"type":64,"value":144},"..\u002Fvertex-deploy\u002FSKILL.md",{"type":64,"value":128},{"type":58,"tag":95,"props":147,"children":148},{},[149,154,156,162],{"type":58,"tag":99,"props":150,"children":151},{},[152],{"type":64,"value":153},"Run Inference (Text Generation, Chat, Embeddings)",{"type":64,"value":155},": If the user wants to connect to Vertex AI to generate text, chat, or get embeddings using models like Gemini, Llama, DeepSeek, etc., stop reading this file and IMMEDIATELY read the skill instructions located at ",{"type":58,"tag":121,"props":157,"children":159},{"className":158},[],[160],{"type":64,"value":161},"..\u002Fvertex-inference\u002FSKILL.md",{"type":64,"value":128},{"type":58,"tag":95,"props":164,"children":165},{},[166,171,173,179],{"type":58,"tag":99,"props":167,"children":168},{},[169],{"type":64,"value":170},"Model Tuning \u002F Fine-Tuning",{"type":64,"value":172},": If the user wants to fine-tune an Open Model or a Gemini Model, stop reading this file and IMMEDIATELY read the skill instructions located at ",{"type":58,"tag":121,"props":174,"children":176},{"className":175},[],[177],{"type":64,"value":178},"..\u002Fvertex-tuning\u002FSKILL.md",{"type":64,"value":128},{"type":58,"tag":95,"props":181,"children":182},{},[183,188,190,195],{"type":58,"tag":99,"props":184,"children":185},{},[186],{"type":64,"value":187},"Unknown \u002F Not Listed",{"type":64,"value":189},": If the objective is not clearly one of the above, ",{"type":58,"tag":99,"props":191,"children":192},{},[193],{"type":64,"value":194},"STOP",{"type":64,"value":196},". Ask the user to clarify whether they are looking to deploy a model, run inference, or tune a model on Vertex AI.",{"items":198,"total":246},[199,213,226,239],{"slug":200,"name":200,"fn":201,"description":202,"org":203,"tags":204,"stars":23,"repoUrl":24,"updatedAt":212},"genai-sdk","build enterprise applications with Gemini API","Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS\u002FTS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[205,208,210,211],{"name":206,"slug":207,"type":16},"API Development","api-development",{"name":209,"slug":32,"type":16},"Gemini",{"name":9,"slug":8,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:38:31.989308",{"slug":214,"name":214,"fn":215,"description":216,"org":217,"tags":218,"stars":23,"repoUrl":24,"updatedAt":225},"liveapi-service","generate Gemini LiveAPI client services","Generates a LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise or non-Gemini Enterprise), handles session setup\u002Fresumption, bearer token refresh, and sending\u002Freceiving `ClientMessage`\u002F`ServerMessage` protos.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[219,220,221,222],{"name":206,"slug":207,"type":16},{"name":209,"slug":32,"type":16},{"name":9,"slug":8,"type":16},{"name":223,"slug":224,"type":16},"WebSockets","websockets","2026-07-12T07:38:55.792572",{"slug":227,"name":227,"fn":228,"description":229,"org":230,"tags":231,"stars":23,"repoUrl":24,"updatedAt":238},"quality-flywheel","evaluate and improve GenAI models","Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK. Creates eval datasets (from session traces or synthetic generation), selects and configures metrics (RubricMetric, LLMMetric, CodeExecutionMetric), executes evals via client.evals.evaluate(), and analyzes results to suggest concrete fixes. Supports both single-turn model evaluation and multi-turn agent trajectory evaluation. Use when asked to \"evaluate my agent\", \"evaluate my model\", \"create eval dataset\", \"run evals\", \"analyze eval results\", \"which metrics should I use\", \"generate test data\", or \"improve quality\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[232,235,236,237],{"name":233,"slug":234,"type":16},"Evals","evals",{"name":9,"slug":8,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},"2026-07-12T07:38:35.588796",{"slug":4,"name":4,"fn":5,"description":6,"org":240,"tags":241,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[242,243,244,245],{"name":9,"slug":8,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":4,"type":16},4,{"items":248,"total":427},[249,267,283,305,319,330,344,357,372,385,401,411],{"slug":250,"name":250,"fn":251,"description":252,"org":253,"tags":254,"stars":264,"repoUrl":265,"updatedAt":266},"kb-search","search and extract local knowledge base documents","Allows listing, searching and extracting information from local knowledge base documents for information about tables\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[255,258,261],{"name":256,"slug":257,"type":16},"Documentation","documentation",{"name":259,"slug":260,"type":16},"Knowledge Base","knowledge-base",{"name":262,"slug":263,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":268,"name":269,"fn":270,"description":271,"org":272,"tags":273,"stars":264,"repoUrl":265,"updatedAt":282},"knowledgecatalogdiscoveryagent","knowledge_catalog_discovery_agent","search and rank Knowledge Catalog data entries","Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[274,277,278,281],{"name":275,"slug":276,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":279,"slug":280,"type":16},"Knowledge Management","knowledge-management",{"name":262,"slug":263,"type":16},"2026-07-12T07:38:22.196851",{"slug":284,"name":284,"fn":285,"description":286,"org":287,"tags":288,"stars":302,"repoUrl":303,"updatedAt":304},"contributing","contribute to Cloud Foundation Fabric","End-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[289,292,295,298,299],{"name":290,"slug":291,"type":16},"Automation","automation",{"name":293,"slug":294,"type":16},"Engineering","engineering",{"name":296,"slug":297,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":300,"slug":301,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":306,"name":306,"fn":307,"description":308,"org":309,"tags":310,"stars":302,"repoUrl":303,"updatedAt":318},"fabric-builder","generate Terraform code for Google Cloud","Generates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[311,312,315],{"name":9,"slug":8,"type":16},{"name":313,"slug":314,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":316,"slug":317,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":320,"name":320,"fn":321,"description":322,"org":323,"tags":324,"stars":302,"repoUrl":303,"updatedAt":329},"fast-0-org-setup-prereqs","prepare prerequisites for FAST 0-org-setup","Guides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[325,326],{"name":9,"slug":8,"type":16},{"name":327,"slug":328,"type":16},"Operations","operations","2026-07-12T07:38:28.127148",{"slug":331,"name":331,"fn":332,"description":333,"org":334,"tags":335,"stars":341,"repoUrl":342,"updatedAt":343},"agent-aware-cli","design agent-aware command-line interfaces","Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user wants to build a CLI, apply CLI best practices, or use Go with Cobra and Viper.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[336,339,340],{"name":337,"slug":338,"type":16},"CLI","cli",{"name":293,"slug":294,"type":16},{"name":9,"slug":8,"type":16},1150,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":345,"name":345,"fn":346,"description":347,"org":348,"tags":349,"stars":341,"repoUrl":342,"updatedAt":356},"build-mcp-genmedia","build and configure GenAI MCP servers","Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a container restart, or when \u002Ftmp has been wiped. The prebuilt binaries in \u002Fworkspace\u002F.local\u002Fbin\u002F have no exec bit and live on a noexec mount; this skill compiles fresh executables into \u002Ftmp\u002Fbin\u002F where execution is allowed.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[350,351,352,353],{"name":206,"slug":207,"type":16},{"name":9,"slug":8,"type":16},{"name":14,"slug":15,"type":16},{"name":354,"slug":355,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":341,"repoUrl":342,"updatedAt":371},"genmedia-audio-engineer","synthesize and mix audio content","Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[363,366,369,370],{"name":364,"slug":365,"type":16},"Audio","audio",{"name":367,"slug":368,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":21,"slug":4,"type":16},"2026-07-12T07:39:16.623879",{"slug":373,"name":373,"fn":374,"description":375,"org":376,"tags":377,"stars":341,"repoUrl":342,"updatedAt":384},"genmedia-image-artist","generate and edit AI images","Expert in AI image generation and editing. Use when the user needs high-quality textures, character-consistent visuals, or image-to-image editing using mcp-nanobanana-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[378,379,380,383],{"name":367,"slug":368,"type":16},{"name":9,"slug":8,"type":16},{"name":381,"slug":382,"type":16},"Image Generation","image-generation",{"name":21,"slug":4,"type":16},"2026-07-12T07:39:15.372822",{"slug":386,"name":386,"fn":387,"description":388,"org":389,"tags":390,"stars":341,"repoUrl":342,"updatedAt":400},"genmedia-producer","produce multi-step media content","Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[391,392,393,394,397],{"name":364,"slug":365,"type":16},{"name":367,"slug":368,"type":16},{"name":9,"slug":8,"type":16},{"name":395,"slug":396,"type":16},"Media","media",{"name":398,"slug":399,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":402,"name":402,"fn":403,"description":404,"org":405,"tags":406,"stars":341,"repoUrl":342,"updatedAt":410},"genmedia-video-editor","edit and compose video content","Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[407,408,409],{"name":367,"slug":368,"type":16},{"name":9,"slug":8,"type":16},{"name":398,"slug":399,"type":16},"2026-07-12T07:39:13.749081",{"slug":412,"name":412,"fn":413,"description":414,"org":415,"tags":416,"stars":341,"repoUrl":342,"updatedAt":426},"genmedia-voice-director","generate expressive text-to-speech with Gemini","Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS. Use this when the user needs virtual voice actor personas, expressive speech generation, or multiple variations of a voiceover (like \"take 3 on the bounce\").",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[417,418,419,420,423],{"name":364,"slug":365,"type":16},{"name":367,"slug":368,"type":16},{"name":209,"slug":32,"type":16},{"name":421,"slug":422,"type":16},"Speech","speech",{"name":424,"slug":425,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80]