Google Agents Cli Scaffold
Create or enhance ADK agent projects with `agents-cli scaffold` commands, templates, deployment targets, and prototype-first structure after requirements are clarified.
Overview
Google Agents CLI Scaffold is an agent skill for the Build phase that runs agents-cli scaffold create, enhance, and upgrade to generate ADK project structure after workflow Phase 0 requirements are clear.
Install
npx skills add https://github.com/google/agents-cli --skill google-agents-cli-scaffoldWhat is this skill?
- MANDATORY: load `google-agents-cli-workflow` and complete Phase 0 before `scaffold create` on new projects
- Commands: `scaffold create`, `scaffold enhance`, `scaffold upgrade` with template and deployment target options
- Prototype-first workflow before full deployment scaffolding
- Explicitly not for writing agent logic—pair with ADK code skill after structure exists
- Requires `agents-cli` via `uv tool install google-agents-cli`
- Skill metadata version 0.2.0
- Three scaffold commands: create, enhance, upgrade
Adoption & trust: 12.4k installs on skills.sh; 2.7k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a new ADK project or deployment-ready layout but lack eval boilerplate, CI/CD, and agents-cli conventions in the repo.
Who is it for?
Creating a new ADK agent repo or enhancing an existing codebase with agents-cli deployment and CI/CD scaffolding after requirements are defined.
Skip if: Writing ADK agent tools and logic, or executing production deploy steps—use the dedicated code and deploy skills instead.
When should I use this skill?
User wants to create an agent project, start a new ADK project, add CI/CD or deployment scaffolding, enhance, or upgrade an existing agents-cli project.
What do I get? / Deliverables
You get a scaffolded or enhanced ADK project with the chosen template and deployment targets, ready to implement agent code in a follow-on skill.
- New or enhanced ADK repository with agents-cli layout
- CI/CD and deployment target scaffolding per chosen template
Recommended Skills
Journey fit
Build is the primary phase because scaffolding is the first concrete project artifact before agent implementation or CI/CD wiring. Agent-tooling reflects ADK project templates, `scaffold create`, `enhance`, and `upgrade`—not application UI or generic backend CRUD.
How it compares
Generator for repo skeleton and infra stubs—not the lifecycle parent workflow and not hands-on deploy operations.
Common Questions / FAQ
Who is google-agents-cli-scaffold for?
Solo builders on Google ADK who use agents-cli and need create/enhance/upgrade commands without skipping requirements clarification.
When should I use google-agents-cli-scaffold?
Use it in Build agent-tooling when starting a new agent project, adding CI/CD/deployment scaffolding, or upgrading an existing agents-cli layout.
Is google-agents-cli-scaffold safe to install?
Scaffolding modifies project files and may add Cloud CI templates; review the Security Audits panel on this Prism page and commit before `scaffold enhance` or `upgrade`.
Workflow Chain
Requires first: google agents cli workflow
Then invoke: google agents cli adk code
SKILL.md
READMESKILL.md - Google Agents Cli Scaffold
# ADK Project Scaffolding Guide > **Requires:** `agents-cli` (`uv tool install google-agents-cli`) — [install uv](https://docs.astral.sh/uv/getting-started/installation/index.md) first if needed. Use the `agents-cli` CLI to create new ADK agent projects or enhance existing ones with deployment, CI/CD, and infrastructure scaffolding. --- ## Prerequisite: Clarify Requirements (MANDATORY for new projects) **Before scaffolding a new project, load `/google-agents-cli-workflow` and complete Phase 0** — clarify the user's requirements before running any `scaffold create` command. Ask what the agent should do, what tools/APIs it needs, and whether they want a prototype or full deployment. --- ## Step 1: Choose Architecture **Mapping user choices to CLI flags:** | Choice | CLI flag | |--------|----------| | RAG with vector search | `--agent agentic_rag --datastore agent_platform_vector_search` | | RAG with document search | `--agent agentic_rag --datastore agent_platform_search` | | A2A protocol | `--agent adk_a2a` | | Prototype (no deployment) | `--prototype` | | Deployment target | `--deployment-target <agent_runtime\|cloud_run\|gke>` | | CI/CD runner | `--cicd-runner <github_actions\|cloud_build>` | | Session storage | `--session-type <in_memory\|cloud_sql\|agent_platform_sessions>` | ### Product name mapping The platform formerly known as "Vertex AI" is now **Gemini Enterprise Agent Platform** (short: **Agent Platform**). Users may refer to products by different names. Map them to the correct CLI values: | User may say | CLI value | |-------------|-----------| | Agent Engine, Vertex AI Agent Engine, Agent Runtime | `--deployment-target agent_runtime` | | Vertex AI Search, Agent Search | `--datastore agent_platform_search` | | Vertex AI Vector Search, Vector Search | `--datastore agent_platform_vector_search` | | Agent Engine sessions, Agent Platform Sessions | `--session-type agent_platform_sessions` | The `vertexai` Python SDK package name is unchanged. --- ## Step 2: Create or Enhance the Project ### Create a New Project ```bash agents-cli scaffold create <project-name> \ --agent <template> \ --deployment-target <target> \ --region <region> \ --prototype ``` **Constraints:** - Project name must be **26 characters or less**, lowercase letters, numbers, and hyphens only. - Do NOT `mkdir` the project directory before running `create` — the CLI creates it automatically. If you mkdir first, `create` will fail or behave unexpectedly. - Auto-detect the guidance filename based on the IDE you are running in and pass `--agent-guidance-filename` accordingly (`GEMINI.md` for Gemini CLI, `CLAUDE.md` for Claude Code, `AGENTS.md` for OpenAI Codex/other). - When enhancing an existing project, check where the agent code lives. If it's not in `app/`, pass `--agent-directory <dir>` (e.g. `--agent-directory agent`). Getting this wrong causes enhance to miss or misplace files. ### Reference Files | File | Contents | |------|----------| | `references/flags.md` | Full flag reference for `create` and `enhance` commands | ### Enhance an Existing Project ```bash agents-cli scaffold enhance . --deployment-target <target> agents-cli scaffold enhanc