New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Liveapi Service

by GoogleCloudPlatform in GoogleCloudPlatform/vertex-ai-samples

Generates a LiveAPI client service class in the user's chosen programming language.

Apache-2.0Auto-check passedBackend & APIs

Install Liveapi Service

skills CLI
$ npx skills add GoogleCloudPlatform/vertex-ai-samples --skill liveapi-service -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GoogleCloudPlatform/vertex-ai-samples liveapi-service --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/vertex-ai-samples.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/genai-sdk/references/live_api .claude/skills/liveapi-service && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
liveapi-service
GitHub stars
791
Token cost
~1.2k tokens
SKILL.md length
643 words
Files
5 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generates a LiveAPI client service class in the user's chosen programming language.

  • The user wants to build
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise
  • Non-Gemini Enterprise)

What it does

Liveapi Service is an agent skill from GoogleCloudPlatform/vertex-ai-samples. 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/resumption, bearer token refresh, and sending/receiving ClientMessage/ServerMessage protos.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `live_api.md`, `references/client_server_messages.md` and `references/session_manager.md`).

It sits in Backend & APIs, covering Realtime and WebSockets. It works with Vertex AI, Google Cloud and Google Gemini. The repository describes itself as: 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. The licence is Apache-2.0.

When your agent uses it

  • The user wants to build
  • Integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise
  • Non-Gemini Enterprise)
  • Handles session setup/resumption

Example prompts

  • “Use the liveapi-service skill to generate a LiveAPI client service class in the user's chosen programming language”
  • “/liveapi-service”

What it can do on your machine

Read from SKILL.md and the folder at commit d0aed81. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.cloud.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Liveapi Service loads about 1.2k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 643 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GoogleCloudPlatform/vertex-ai-samples at commit d0aed81, republished under its Apache-2.0 licence (© GoogleCloudPlatform). 643 words, ~1,232 tokens.

Download SKILL.mdSave it as .claude/skills/liveapi-service/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
liveapi-service
description
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/resumption, bearer token refresh, and sending/receiving `ClientMessage`/`ServerMessage` protos.

LiveAPI Service Skill

Provided files in references:

  • client_server_messages.md: The public document of protos used for LiveAPI.
  • client_server_messages.proto: The proto generated based on the client_server_messages.md.
  • session_manager.md: Describes how to correctly handle the sessions.

What you should do:

Step 1:

Copy existing reference files to user provided destination folder

Step 2:

Examine the public documents mentioned in client_server_messages.md. Checking if there are any discrepancies between the public documents and the created markdown / proto as client_server_messages. If yes, update these file in the destination folder

Step 3:

Implement a class in the user wanted coding language that work as a LiveAPI service, it should import the existing proto file, build the connection to the LiveAPI endpoint, expose functions to user and let user able to send and receive data to / from the model.

If a language need a specific environment, such as python, you should create the environment in the output folder and provide a bash file, by executing which, the user can recreate the correct environment, do not use or modify the existing system environment.

Wanted behavior:

The user will provide the following information to the class for initialization:

  • project_id
  • location
  • model_id
  • config, should be a ClientMessage with setup field.
  • use_gemini_enterprise, should be a boolean telling if using Gemini Enterprise or not
  • api_key, if not using Gemini Enterprise, an api_key should be provided.

If using Gemini Enterprise, you should get a bearer token, refresh it when needed, and send it with each websocket connection (including session resumption).

The class should expose the following functions to the user:

  • [async] send_realtime_data(data): allow the user to send realtime_data to the model. The data should be a ClientMessage in the proto file.
  • [async] send_client_content(data): allow the user to send non_realtime data to the model, allow the user to add context. The data should be a ClientMessage in the proto file.
  • [async] receive(): Allow the user to receive data from the model. The data received should be a ServerMessage in the proto file.

Step 4:

Once the code implemented, you should implement a test file, initialize the connection and try to send text, audio, video data and receive the response.

Ask the user for necessary information.

Step 5:

You should finally provide a markdown file with name how_to_run.md, describe how to correctly use the class you just created. You should provide full example about how to correctly build clientmessage for all kinds of support modalities and how to send them. Also you should describe how to correctly fetch data from the model.

Show full SKILL.md (228 more words)Show less

Step 6:

You should create scripts to deploy your implementation as a service, it should contains both frontend UI and backend service [You can use whatever coding language you want]. In these service, the user can use the frontend UI to test your implementation, it should allow the user to:

  • Start new connection / close current connection.
  • Select models to use.
  • Select input sources (audio or / and video [camera or screenshot]) and streaming data to model.
  • Send text message to model.
  • Heard the audio sound from model and see the model and user transcription and conversation history.

Attention

The service should reuse the ServerMessage and ClientMessage defined in the proto for sending and receiving messages.

While implementing the audio / transcription playback logic, please follow the instruction in https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/live-api/best-practices.

Make sure you correctly handle the interrupt signal from ServerMessage, which should:

  • You'll receive audio and transcription interleaved. The played audio and corresponding transcription should be time aligned.
  • Immediately stop the playing for audio and transcription.
  • Clear the playback buffer to dump unsent audio / transcription.
  • Start new chat bubbles for model / user.

Make sure you correctly handle the finished signal from input_transcription or output_transcription, which should start a new bubble after concatenating the data.

Step 7: Implement a description file how_to_test_with_ui.md and tell how to start the services, which URL should the user use and how to interactive with the model.

© GoogleCloudPlatform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/genai-sdk/references/live_api of GoogleCloudPlatform/vertex-ai-samples.

  • SKILL.md
  • live_api.md
  • references/client_server_messages.md
  • references/client_server_messages.proto
  • references/session_manager.md

Open the folder on GitHubat commit d0aed81

Compare with similar skills

Liveapi Service next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Liveapi Service compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Liveapi Service this skillGoogleCloudPlatform/vertex-ai-samples791—~1.2kAutomated safety check: PassApache-2.0
Vertex AI API DevJetBrains/skills3631 repos~2.4kAutomated safety check: PassNone
Gemini APIgoogle/skills21k3 repos~2.6kAutomated safety check: PassApache-2.0
Vertex AI Geminimajiayu000/claude-skill-registry6661 repos~2.1kAutomated safety check: PassApache-2.0
Gemini Sttmajiayu000/claude-skill-registry6661 repos~893Automated safety check: NotesMIT
Gemini Live API Devgoogle-gemini/gemini-skills4.3k—~4.6kAutomated safety check: PassApache-2.0

Similar skills

  • Vertex AI API Dev

    JetBrains/skills

    Official

    Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK.

    363 GitHub starsUsed in 1 repo~2.4k tokens
    AI & LLM EngineeringAuto-check passed

  • Gemini API

    google/skills

    Official

    A skill your agent uses when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform.

    21k GitHub starsUsed in 3 repos~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Vertex AI Gemini

    majiayu000/claude-skill-registry

    Google Cloud Vertex AI for enterprise Gemini deployments — production scaling, fine-tuning, and MLOps.

    666 GitHub starsUsed in 1 repo~2.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Gemini Stt

    majiayu000/claude-skill-registry

    Transcribe audio files using Google's Gemini API or Vertex AI

    666 GitHub starsUsed in 1 repo~893 tokens
    Media & CreativeAuto-check: notes

  • Gemini Live API Dev

    google-gemini/gemini-skills

    Official

    A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.

    4.3k GitHub stars~4.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Ak Cloud Deploy

    yaalalabs/agent-kernel

    Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart.

    191 GitHub stars~14k tokensUpdated today
    Backend & APIsAuto-check passed

More from GoogleCloudPlatform/vertex-ai-samples

  • Quality Flywheel

    GoogleCloudPlatform/vertex-ai-samples

    Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK.

    791 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Vertex AI

    GoogleCloudPlatform/vertex-ai-samples

    Primary Router for Vertex AI skills. An agent skill from GoogleCloudPlatform/vertex-ai-samples.

    791 GitHub stars~522 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Liveapi Service

What does Liveapi Service do?

Generates a LiveAPI client service class in the user's chosen programming language. Liveapi Service is an agent skill from GoogleCloudPlatform/vertex-ai-samples. Generates a LiveAPI client service class in the user's chosen programming language.

When should I use Liveapi Service?

Liveapi Service fits situations like: the user wants to build; integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise; non-Gemini Enterprise); handles session setup/resumption.

How do I install Liveapi Service in Claude Code?

Run `npx skills add GoogleCloudPlatform/vertex-ai-samples --skill liveapi-service -a claude-code`. Or copy the skill folder (skills/genai-sdk/references/live_api in GoogleCloudPlatform/vertex-ai-samples) into .claude/skills/liveapi-service in your project. Claude Code loads it when a task matches its description.

How do I install Liveapi Service in Codex?

Run `npx skills add GoogleCloudPlatform/vertex-ai-samples --skill liveapi-service -a codex`. Or copy the skill folder (skills/genai-sdk/references/live_api in GoogleCloudPlatform/vertex-ai-samples) into .agents/skills/liveapi-service in your project. Codex loads it when a task matches its description.

Can I use Liveapi Service in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleCloudPlatform/vertex-ai-samples --skill liveapi-service -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/liveapi-service, .gemini/skills/liveapi-service, .github/skills/liveapi-service and .opencode/skills/liveapi-service in your project.

What does Liveapi Service need to run?

SKILL.md names no scripts, command-line tools or credentials: Liveapi Service is instructions for the agent only.

Does Liveapi Service access the network?

SKILL.md names 1 domain. As links in the text: docs.cloud.google.com. This is read from the text; nothing was executed.

Is Liveapi Service safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Liveapi Service use?

Liveapi Service is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Liveapi Service use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Liveapi Service?

Skills that share tags, products or a category with Liveapi Service: Vertex AI API Dev (JetBrains/skills, 363 stars), Gemini API (google/skills, 21k stars), Vertex AI Gemini (majiayu000/claude-skill-registry, 666 stars) and Gemini Stt (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Liveapi Service?

GoogleCloudPlatform (a GitHub organization) maintains it in GoogleCloudPlatform/vertex-ai-samples, which has 791 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.

Source: GoogleCloudPlatform/vertex-ai-samples on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.