Help us improve
Share bugs, ideas, or general feedback.
From vanguard-frontier-agentic
Build, integrate, and debug Gemini API applications on Google Cloud Agent Platform using the unified google-genai SDK. Covers text, multimodal, function calling, structured output, embeddings, caching, streaming, Live API, and model tuning across Python, TypeScript, Go, Java, and C#.
npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticHow this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:gcp-gemini-api-developerThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
"Agent Platform" (full name: Gemini Enterprise Agent Platform) was previously named "Vertex AI". Many web resources still use "Vertex AI" branding.
Guides developers in using the Gemini API for text generation, multimodal, function calling, structured output, and more. Covers models, SDKs (Python, JS, Go), and API spec.
Guides @google/genai SDK for Google Gemini API: multimodal generation, function calling, thinking mode, streaming; migrates from deprecated @google/generative-ai, fixes context/format errors.
Generates production-ready GCP code examples from official ADK, Genkit, Vertex AI, and Gemini repos. Adapts to Python/TypeScript/Go with security, monitoring, IaC for AI agents and apps.
Share bugs, ideas, or general feedback.
"Agent Platform" (full name: Gemini Enterprise Agent Platform) was previously named "Vertex AI". Many web resources still use "Vertex AI" branding.
The following SDKs are DEPRECATED and must NOT be used:
google-cloud-aiplatform (Python)@google-cloud/vertexai (Node.js)google-generativeai (Python — Gemini Developer API SDK)Use ONLY the unified Gen AI SDK:
google-genai (pip install google-genai)@google/genai (npm install @google/genai)google.golang.org/genai (go get google.golang.org/genai)com.google.genai:google-genaiGoogle.GenAI (dotnet add package Google.GenAI)# Application Default Credentials (ADC) — preferred
export GOOGLE_CLOUD_PROJECT='your-project-id'
export GOOGLE_CLOUD_LOCATION='global' # Use 'global' for automatic region routing
export GOOGLE_GENAI_USE_VERTEXAI=true
gemini-3.1-pro-preview — complex reasoning, coding, research (1M tokens)gemini-3-flash-preview — fast, balanced, multimodal (1M tokens)gemini-3.1-flash-lite-preview — high-frequency lightweight tasksgemini-3-pro-image-preview — image generation and editinggemini-live-2.5-flash-native-audio — Live Realtime API (bidirectional audio/video)from google import genai
client = genai.Client # picks up env vars automatically
response = client.models.generate_content(
model="gemini-3-flash-preview",
contents="Explain transformer architecture"
)
print(response.text)
Load only when needed:
| Scenario | Trigger Keywords | Reference |
|---|---|---|
| Text + multimodal | chat, image, video, audio, streaming | references/text-multimodal.md |
| Function calling + tools | tool use, function call, grounding, code execution | references/tools.md |
| Structured output | JSON, schema, structured, typed response | references/structured-output.md |
| Embeddings | embedding, semantic search, vector | references/embeddings.md |
| Context caching | cache, large context, caching tokens | references/caching.md |
| Batch prediction | batch, async, large dataset | references/batch.md |
| Live API | live, realtime, voice, video streaming, bidirectional | references/live-api.md |
| Model tuning | fine-tune, SFT, preference tuning | references/tuning.md |
| Safety | safety filter, threshold, harm category | references/safety.md |
| SDK migration | migrate, deprecated, upgrade | references/migration.md |
google-genai SDK family. If user code imports google-cloud-aiplatform, @google-cloud/vertexai, or google-generativeai, flag it as deprecated and provide migration guidance.location="global" (global endpoint) by default for automatic capacity routing. Only use a specific region if the user explicitly requests it.gemini-3.1-pro-preview ≠ gemini-3-pro-preview — the latter does NOT exist; use the correct model IDs.CachedContent) reduces cost for repeated large contexts (system prompts, documents) — recommend it proactively for production workloads with stable large contexts.-preview models.BatchJob) is for async large-dataset inference — use it instead of looping generate_content for bulk processing.Read-only advisory. Never embed API keys or service account credentials in code examples. Use ADC and environment variables. Do not call batch jobs or fine-tuning jobs on production data without explicit user approval.