[!TIP] One-Time Setup: To install the CLI and enable all 7 specialized
development skills in your coding agent, run the setup command:
uvx google-agents-cli setup
Alternatively, to install only the expert skills and let the agent handle
execution:
npx skills add google/agents-cli
Overview
This skill serves as the entrypoint for agents-cli — Google's toolkit for
building, evaluating, and deploying AI agents on the Gemini Enterprise Agent
Platform.
Use this skill to perform the initial setup and identify the correct specialized
workflows for your task.
The Agent Development Lifecycle
After running the setup, the following specialized skills become available and
will activate automatically based on your requests. Use this table to identify
which skill to load for your current phase:
| Phase |
Specialized Skill |
Purpose / When to Load |
| 0 — Understand |
google-agents-cli-workflow |
Clarify intent. Define the agent spec in .agents-cli-spec.md before coding. |
| 1 — Study |
google-agents-cli-workflow |
Leverage samples. Study existing agent samples (e.g., ambient-expense) before scaffolding. |
| 2 — Scaffold |
google-agents-cli-scaffold |
Create/Enhance. Initialize the project structure, CI/CD, and infrastructure templates. |
| 3 — Build |
google-agents-cli-adk-code |
Implement. Write agent logic, tools, callbacks, and manage state using ADK APIs. |
| 4 — Evaluate |
google-agents-cli-eval |
Validate Quality. Run systematic evaluations (LLM-as-judge). |
| 5 — Deploy |
google-agents-cli-deploy |
Go Production. Deploy to Agent Runtime (Vertex AI), Cloud Run, or GKE. |
| 6 — Publish |
google-agents-cli-publish |
Register. Make your agent available as a tool in Gemini Enterprise. |
| 7 — Observe |
google-agents-cli-observability |
Monitor. Set up Cloud Trace, prompt-response logging, and BigQuery analytics. |
Key CLI Commands
Below are the primary commands you will use throughout the development
lifecycle:
| Command |
Description |
agents-cli setup |
Install the CLI and configure skills in your coding agent. |
agents-cli scaffold <name> |
Create a new agent project from a template. |
agents-cli eval run |
Run the agent and grade the traces in a single step (generate + grade). |
agents-cli deploy |
Deploy your agent to Google Cloud (Agent Runtime, Cloud Run, GKE). |
agents-cli publish gemini-enterprise |
Register your deployed agent with Gemini Enterprise. |
For the full list of available commands and global options, run agents-cli --help.
Next Steps
Follow this sequence to initiate the development workflow:
- Execute Setup: Run the
uvx or npx command in the [!TIP] box above
to install the CLI and enable the specialized skills in your environment.
- Verify Installation: Run
agents-cli info to confirm the installation
and view the active project configuration.
- Initiate Phase 0: Ask the user for their core requirements (agent
purpose, external tools, deployment target) and document them in
.agents-cli-spec.md before writing any code.
Reporting Issues
Report bugs or improvements at Google Agents CLI Issues.
Supporting Links
1---2name: google-agents-cli-onboarding3description: >-4 Onboarding entrypoint for agents-cli in Agent Platform. It should be used5 when the user wants to "create a new agent", "develop an agent", "build an agent using ADK",6 "run the agent locally", "debug agent code", "test an agent", "evaluate an agent",7 "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit)8 development lifecycle.9metadata:10 source: https://skillmd.com/skills/google/google-agents-cli-onboarding11---1213> [!TIP] **One-Time Setup**: To install the CLI and enable all 7 specialized14> development skills in your coding agent, run the setup command:15>16> ```bash17> uvx google-agents-cli setup18> ```19>20> Alternatively, to install only the expert skills and let the agent handle21> execution:22>23> ```bash24> npx skills add google/agents-cli25> ```2627## Overview2829This skill serves as the entrypoint for **agents-cli** — Google's toolkit for30building, evaluating, and deploying AI agents on the Gemini Enterprise Agent31Platform.3233Use this skill to perform the initial setup and identify the correct specialized34workflows for your task.3536## The Agent Development Lifecycle3738After running the setup, the following specialized skills become available and39will activate automatically based on your requests. Use this table to identify40which skill to load for your current phase:4142| Phase | Specialized Skill | Purpose / When to Load |43| :--- | :--- | :--- |44| **0 — Understand** | `google-agents-cli-workflow` | **Clarify intent.** Define the agent spec in `.agents-cli-spec.md` before coding. |45| **1 — Study** | `google-agents-cli-workflow` | **Leverage samples.** Study existing agent samples (e.g., `ambient-expense`) before scaffolding. |46| **2 — Scaffold** | `google-agents-cli-scaffold` | **Create/Enhance.** Initialize the project structure, CI/CD, and infrastructure templates. |47| **3 — Build** | `google-agents-cli-adk-code` | **Implement.** Write agent logic, tools, callbacks, and manage state using ADK APIs. |48| **4 — Evaluate** | `google-agents-cli-eval` | **Validate Quality.** Run systematic evaluations (LLM-as-judge). |49| **5 — Deploy** | `google-agents-cli-deploy` | **Go Production.** Deploy to Agent Runtime (Vertex AI), Cloud Run, or GKE. |50| **6 — Publish** | `google-agents-cli-publish` | **Register.** Make your agent available as a tool in Gemini Enterprise. |51| **7 — Observe** | `google-agents-cli-observability` | **Monitor.** Set up Cloud Trace, prompt-response logging, and BigQuery analytics. |5253## Key CLI Commands5455Below are the primary commands you will use throughout the development56lifecycle:5758| Command | Description |59| :--- | :--- |60| `agents-cli setup` | Install the CLI and configure skills in your coding agent. |61| `agents-cli scaffold <name>` | Create a new agent project from a template. |62| `agents-cli eval run` | Run the agent and grade the traces in a single step (generate + grade). |63| `agents-cli deploy` | Deploy your agent to Google Cloud (Agent Runtime, Cloud Run, GKE). |64| `agents-cli publish gemini-enterprise` | Register your deployed agent with Gemini Enterprise. |6566*For the full list of available commands and global options, run `agents-cli67--help`.*6869## Next Steps7071Follow this sequence to initiate the development workflow:72731. **Execute Setup:** Run the `uvx` or `npx` command in the `[!TIP]` box above74 to install the CLI and enable the specialized skills in your environment.752. **Verify Installation:** Run `agents-cli info` to confirm the installation76 and view the active project configuration.773. **Initiate Phase 0:** Ask the user for their core requirements (agent78 purpose, external tools, deployment target) and document them in79 `.agents-cli-spec.md` before writing any code.8081## Reporting Issues8283Report bugs or improvements at [Google Agents CLI Issues](https://github.com/google/agents-cli/issues).8485## Supporting Links8687* [Google Agents CLI Documentation](https://github.com/google/agents-cli/tree/main/docs/src)