Agents CLI: Project Scaffolding
Part of Google's agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade`: mapping a user's stated requirements (retrieval/RAG, sandboxed execution, cross-session memory, A2A, deployment target, CI/CD runner, session storage) to the correct CLI flags, then walking through creating a new project or adding deployment/CI/CD scaffolding to an existing one. Recommends a prototype-first workflow and defers to google-agents-cli-workflow's Phase 0 design dialogue before scaffolding anything new. Does not cover writing agent code (google-agents-cli-adk-code) or deployment operations (google-agents-cli-deploy).
This skill hasn't been reviewed yet.
What it does
Guide for creating or enhancing agent projects with Google's agents-cli — template selection, deployment target, CI/CD runner, and session storage flags.
How to use this
Once it is installed, this skill picks itself up. You do not need to name it.
- Created by
- Google LLC
- Category
- Engineering
- Source
- View source
Run this on Skills and Agents
You can run the skill on Skills and Agents by creating an account. You don't need to install anything. We provide the model and tokens. Your connected tools and company brain are ready to use.
Skills give you best practices and templates to get the most out of your AI
Add this skill
Pick where you want it. Nothing to configure after.
These install links go live once the signup flow ships. Until then, ask Claude, ChatGPT, or Gemini to fetch this skill's file directly from GitHub.
Not sure which? See the install guide.
Share this skill
Agents CLI: Project Scaffolding
Part of Google's agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade`: mapping a user's stated requirements (retrieval/RAG, sandboxed execution, cross-session memory, A2A, deployment target, CI/CD runner, session storage) to the correct CLI flags, then walking through creating a new project or adding deployment/CI/CD scaffolding to an existing one. Recommends a prototype-first workflow and defers to google-agents-cli-workflow's Phase 0 design dialogue before scaffolding anything new. Does not cover writing agent code (google-agents-cli-adk-code) or deployment operations (google-agents-cli-deploy).
Third-party, by Google LLC
September 13, 2026
Install from google/agents-cli
This skill is one of 7 bundled in Google's agents-cli repo (skills/google-agents-cli-scaffold). Installing pulls all 7 skills in the repo — there's no way to grab just this one.
- 1
Install all 7 agents-cli skills
Installs this skill along with the other 6 (workflow, adk-code, eval, deploy, publish, observability) from google/agents-cli's skills/ folder.
npx skills add google/agents-cli - 2
Install the CLI itself (required to run scaffold commands)
This skill's guidance runs through actual agents-cli scaffold commands.
uv tool install google-agents-cli - 3
Activate in Claude
Ask to create a new ADK project, add CI/CD, or add deployment support to an existing project.
Your skill is downloading.
Create a free account and the platform does the rest:
- Get an email the moment this skill updates
- See every skill and agent you've installed, in one place
- Get your next recommendation based on what you actually use
No credit card. Takes about a minute.
What this skill does
This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the source below.
A skill from Google’s
google/agents-cli. The canonical source — including the CLI, the other 6 skills, and release notes — lives in that repo.
What this skill does
Guides agents-cli scaffold create (new projects) and agents-cli scaffold enhance (adding deployment/CI/CD to an existing project), plus scaffold upgrade. Before running any scaffold command on a new project, it requires loading google-agents-cli-workflow and completing its Phase 0 requirements dialogue — the CLI flags below only get chosen once the user has actually stated what they want.
Mapping requirements to flags
| Choice | CLI flag |
|---|---|
| Retrieval/RAG, sandboxed execution, cross-session memory, OAuth consent, guardrails, scheduled runs | No flag — these come from clone-and-study recipes in google-agents-cli-adk-code |
| A2A protocol | Built in by default when scaffolding an ADK agent |
| Prototype (no deployment) | --prototype |
| Deployment target | --deployment-target <agent_runtime|cloud_run|gke> |
| CI/CD runner | --cicd-runner <github_actions|google_cloud_build> |
| Session storage | --session-type <in_memory|cloud_sql|agent_platform_sessions> |
Older Google Cloud product names map onto these flags — e.g. “Agent Engine” / “Vertex AI Agent Engine” both mean --deployment-target agent_runtime. Some previously-documented flags (--datastore, the agentic_rag template, agents-cli infra datastore) have been removed in favor of the recipe-based approach for retrieval.
Prototype-first
The skill recommends starting with --prototype (no deployment target) and adding deployment scaffolding later via scaffold enhance, rather than committing to Agent Runtime/Cloud Run/GKE up front.
Scope
Does not cover writing agent code (google-agents-cli-adk-code) or deployment operations once scaffolded (google-agents-cli-deploy).