gemini-api

Name: gemini-api
Author: jmxt3

32stars3forks

How to install gemini-api?

jmxt3/gitscape.ai/gemini-api

$npx -y skills add jmxt3/gitscape.ai --skill gemini-api

Installs into the current project.

Summary

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities

Files · 1

View on GitHub

SKILL.md

1	IMPORTANT: Agent Platform (full name Gemini Enterprise Agent Platform) was previously named "Vertex AI" and many web resources use the legacy branding.
2
3	# Gemini API in Agent Platform
4
5	Access Google's most advanced AI models built for enterprise use cases using the Gemini API in Agent Platform.
6
7	Provide these key capabilities:
8
9	- Text generation - Chat, completion, summarization
10	- Multimodal understanding - Process images, audio, video, and documents
11	- Function calling - Let the model invoke your functions
12	- Structured output - Generate valid JSON matching your schema
13	- Context caching - Cache large contexts for efficiency
14	- Embeddings - Generate text embeddings for semantic search
15	- Live Realtime API - Bidirectional streaming for low latency Voice and Video interactions
16	- Batch Prediction - Handle massive async dataset prediction workloads
17
18	## Core Directives
19
20	- Unified SDK: ALWAYS use the Gen AI SDK (`google-genai` for Python, `@google/genai` for JS/TS, `google.golang.org/genai` for Go, `com.google.genai:google-genai` for Java, `Google.GenAI` for C#).
21	- Legacy SDKs: DO NOT use `google-cloud-aiplatform`, `@google-cloud/vertexai`, or `google-generativeai`.
22
23	## SDKs
24
25	- Python: Install `google-genai` with `pip install google-genai`
26	- JavaScript/TypeScript: Install `@google/genai` with `npm install @google/genai`
27	- Go: Install `google.golang.org/genai` with `go get google.golang.org/genai`
28	- C#/.NET: Install `Google.GenAI` with `dotnet add package Google.GenAI`
29	- Java:
30	- groupId: `com.google.genai`, artifactId: `google-genai`
31	- Latest version can be found here: https://central.sonatype.com/artifact/com.google.genai/google-genai/versions (let's call it `LAST_VERSION`)
32	- Install in `build.gradle`:
33
34	```
35	implementation("com.google.genai:google-genai:${LAST_VERSION}")
36	```
37
38	- Install Maven dependency in `pom.xml`:
39
40	```xml
41	<dependency>
42	<groupId>com.google.genai</groupId>
43	<artifactId>google-genai</artifactId>
44	<version>${LAST_VERSION}</version>
45	</dependency>
46	```
47
48	> [!WARNING]
49	> Legacy SDKs like `google-cloud-aiplatform`, `@google-cloud/vertexai`, and `google-generativeai` are deprecated. Migrate to the new SDKs above urgently by following the Migration Guide.
50
51	## Authentication & Configuration
52
53	Prefer environment variables over hard-coding parameters when creating the client. Initialize the client without parameters to automatically pick up these values.
54
55	### Application Default Credentials (ADC)
56	Set these variables for standard [Google Cloud authentication](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/start/gcp-auth):
57	```bash
58	export GOOGLE_CLOUD_PROJECT='your-project-id'
59	export GOOGLE_CLOUD_LOCATION='global'
60	export GOOGLE_GENAI_USE_VERTEXAI=true
61	```
62	- By default, use `location="global"` to access the global endpoint, which provides automatic routing to regions with available capacity.
63	- If a user explicitly asks to use a specific region (e.g., `us-central1`, `europe-west4`), specify that region in the `GOOGLE_CLOUD_LOCATION` parameter instead. Reference the [supported regions documentation](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/locations) if needed.
64
65	### Agent Platform in Express Mode
66	Set these variables when using [Express Mode](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/start/api-keys?usertype=expressmode) with an API key:
67	```bash
68	export GOOGLE_API_KEY='your-api-key'
69	export GOOGLE_GENAI_USE_VERTEXAI=true
70	```
71
72	### Initialization
73	Initialize the client without arguments to pick up environment variables:
74	```python
75	from google import genai
76	client = genai.Client()
77	```
78
79	Alternatively, you can hard-code in parameters when creating the client.
80
81	```python
82	from google import genai
83	client = genai.Client(vertexai=True, project="your-project-id", location="global")
84	```
85
86	## Models
87
88	- Use `gemini-3.1-pro-preview` for complex reasoning, coding, research (1M tokens)
89	- IMPORTANT: Do not use `gemini-3-pro-preview`
90	- Use `gemini-3-flash-preview` for fast, balanced performance, multimodal (1M tokens)
91	- Use `gemini-3.1-flash-lite-preview` for high-frequency, lightweight tasks (1M tokens)
92	- Use `gemini-3-pro-image-preview` for Nano Banana Pro image generation and editing
93	- Use `gemini-3.1-flash-image-preview` for Nano Banana 2 image generation and editing
94	- Use `gemini-live-2.5-flash-native-audio` for Live Realtime API including native audio
95
96	Use the following models only if explicitly requested:
97
98	- `g

People who liked this also viewed

6 picks

Type

gemini-api

32stars3forks

View on GitHub

How to install gemini-api?

jmxt3/gitscape.ai/gemini-api

$npx -y skills add jmxt3/gitscape.ai --skill gemini-api

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	IMPORTANT: Agent Platform (full name Gemini Enterprise Agent Platform) was previously named "Vertex AI" and many web resources use the legacy branding.
2
3	# Gemini API in Agent Platform
4
5	Access Google's most advanced AI models built for enterprise use cases using the Gemini API in Agent Platform.
6
7	Provide these key capabilities:
8
9	- Text generation - Chat, completion, summarization
10	- Multimodal understanding - Process images, audio, video, and documents
11	- Function calling - Let the model invoke your functions
12	- Structured output - Generate valid JSON matching your schema
13	- Context caching - Cache large contexts for efficiency
14	- Embeddings - Generate text embeddings for semantic search
15	- Live Realtime API - Bidirectional streaming for low latency Voice and Video interactions
16	- Batch Prediction - Handle massive async dataset prediction workloads
17
18	## Core Directives
19
20	- Unified SDK: ALWAYS use the Gen AI SDK (`google-genai` for Python, `@google/genai` for JS/TS, `google.golang.org/genai` for Go, `com.google.genai:google-genai` for Java, `Google.GenAI` for C#).
21	- Legacy SDKs: DO NOT use `google-cloud-aiplatform`, `@google-cloud/vertexai`, or `google-generativeai`.
22
23	## SDKs
24
25	- Python: Install `google-genai` with `pip install google-genai`
26	- JavaScript/TypeScript: Install `@google/genai` with `npm install @google/genai`
27	- Go: Install `google.golang.org/genai` with `go get google.golang.org/genai`
28	- C#/.NET: Install `Google.GenAI` with `dotnet add package Google.GenAI`
29	- Java:
30	- groupId: `com.google.genai`, artifactId: `google-genai`
31	- Latest version can be found here: https://central.sonatype.com/artifact/com.google.genai/google-genai/versions (let's call it `LAST_VERSION`)
32	- Install in `build.gradle`:
33
34	```
35	implementation("com.google.genai:google-genai:${LAST_VERSION}")
36	```
37
38	- Install Maven dependency in `pom.xml`:
39
40	```xml
41	<dependency>
42	<groupId>com.google.genai</groupId>
43	<artifactId>google-genai</artifactId>
44	<version>${LAST_VERSION}</version>
45	</dependency>
46	```
47
48	> [!WARNING]
49	> Legacy SDKs like `google-cloud-aiplatform`, `@google-cloud/vertexai`, and `google-generativeai` are deprecated. Migrate to the new SDKs above urgently by following the Migration Guide.
50
51	## Authentication & Configuration
52
53	Prefer environment variables over hard-coding parameters when creating the client. Initialize the client without parameters to automatically pick up these values.
54
55	### Application Default Credentials (ADC)
56	Set these variables for standard [Google Cloud authentication](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/start/gcp-auth):
57	```bash
58	export GOOGLE_CLOUD_PROJECT='your-project-id'
59	export GOOGLE_CLOUD_LOCATION='global'
60	export GOOGLE_GENAI_USE_VERTEXAI=true
61	```
62	- By default, use `location="global"` to access the global endpoint, which provides automatic routing to regions with available capacity.
63	- If a user explicitly asks to use a specific region (e.g., `us-central1`, `europe-west4`), specify that region in the `GOOGLE_CLOUD_LOCATION` parameter instead. Reference the [supported regions documentation](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/locations) if needed.
64
65	### Agent Platform in Express Mode
66	Set these variables when using [Express Mode](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/start/api-keys?usertype=expressmode) with an API key:
67	```bash
68	export GOOGLE_API_KEY='your-api-key'
69	export GOOGLE_GENAI_USE_VERTEXAI=true
70	```
71
72	### Initialization
73	Initialize the client without arguments to pick up environment variables:
74	```python
75	from google import genai
76	client = genai.Client()
77	```
78
79	Alternatively, you can hard-code in parameters when creating the client.
80
81	```python
82	from google import genai
83	client = genai.Client(vertexai=True, project="your-project-id", location="global")
84	```
85
86	## Models
87
88	- Use `gemini-3.1-pro-preview` for complex reasoning, coding, research (1M tokens)
89	- IMPORTANT: Do not use `gemini-3-pro-preview`
90	- Use `gemini-3-flash-preview` for fast, balanced performance, multimodal (1M tokens)
91	- Use `gemini-3.1-flash-lite-preview` for high-frequency, lightweight tasks (1M tokens)
92	- Use `gemini-3-pro-image-preview` for Nano Banana Pro image generation and editing
93	- Use `gemini-3.1-flash-image-preview` for Nano Banana 2 image generation and editing
94	- Use `gemini-live-2.5-flash-native-audio` for Live Realtime API including native audio
95
96	Use the following models only if explicitly requested:
97
98	- `g

People who liked this also viewed

6 picks

Type