google-adk-setup
Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk, adk web.
- License 许可
- Unlicense
- 所属仓库
- saski/arnesto
- 最近更新
- 2026-11-12
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- google-adk-setup
- description
- Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk, adk web.
02 资源文件 1
- 参考文档references/cli-commands.md1.3 KB
03 SKILL.md 正文
Google ADK Setup
When to Use / When Not to Use
Use this skill when:
- Starting a new ADK project from scratch.
- Configuring GCP credentials and environment variables for ADK.
- Scaffolding an agent folder with
adk create agent. - Launching the ADK dev UI or CLI runner.
- Troubleshooting missing
.envor Vertex AI auth errors.
Do not use this skill when:
- Designing agent logic, tools, or multi-agent systems (use
google-adk-agent-patterns). - Deploying to Cloud Run (deployment commands are in the references).
Prerequisites
- GCP project with billing enabled.
gcloudCLI installed and authenticated:gcloud auth application-default login.uvinstalled (seeusing-uvskill).- Vertex AI API enabled in your GCP project.
Enable the API:
gcloud services enable aiplatform.googleapis.com
Workflow
1. Create the project
uv init agent-project
cd agent-project
uv add google-adk
2. Scaffold the agent
uv run adk create agent
Interactive prompts:
- Model:
gemini-2.5-flash(recommended starting point) - Backend:
Vertex AI - GCP Project ID: your project id
- Location:
global
Generated files:
agent/
├── __init__.py # exposes root_agent
├── agent.py # Agent definition
└── .env # Vertex AI credentials (co-located with the package)
3. Verify the .env file
The .env lives inside the agent/ directory (not the project root):
GOOGLE_GENAI_USE_VERTEXAI=1
GOOGLE_CLOUD_PROJECT=your-project-id
GOOGLE_CLOUD_LOCATION=global
4. Run the dev UI
uv run adk web --reload_agents
Opens at http://localhost:8000.
For Cloud Shell or remote environments, add --allow_origins="*".
5. Run in CLI mode
uv run adk run agent
Key Facts
GOOGLE_CLOUD_LOCATION=globalroutes to the global Vertex AI endpoint; use a regional value (e.g.us-central1) only ifglobalis unavailable..adk/session.db(SQLite) stores conversation session state between runs. Delete it to reset sessions.--reload_agentshot-reloads agent code on file changes; omit in production.
Troubleshooting
| Symptom | Fix |
|---|---|
DefaultCredentialsError |
Run gcloud auth application-default login |
Permission denied: aiplatform.googleapis.com |
Enable API: gcloud services enable aiplatform.googleapis.com |
| Agent changes not reflected | Ensure --reload_agents flag is set |
| Sessions persist unexpectedly | Delete agent/.adk/session.db |
See references/cli-commands.md for the full CLI reference.
04 同仓库更多 Skills
visualize
Use /visualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.
update-cursor-settings
Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
update-cli-config
View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.
statusline
Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.
split-to-prs
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
shell
Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.