Search skills/

google-agents-cli-scaffold skill

Covers agents-cli scaffold create, enhance and upgrade: choosing a template, deployment target, CI/CD runner and session storage for a new agent project.

in google/agents-cli Planning, TDD & debuggingSkill & agent tooling
Our verdict Recommended

Clear flag mapping and guardrails for scaffolding; narrow but accurate for agents-cli users.

3/5 Depth expertise shipped Note Security Review before installing 2d Maintenance Updated 2 days ago 519K Adoption installs OK License Apache-2.0, commercial OK

What the google-agents-cli-scaffold skill does

The scaffold skill tells the agent how to create or extend an agent project with agents-cli. It makes clarifying requirements mandatory for new projects, pointing to the workflow skill's design dialogue first. It then maps user choices to flags: the agent template (ADK Python by default, or ADK Go), prototype mode with no deployment, the deployment target (Agent Runtime, Cloud Run or GKE), a CI/CD runner (GitHub Actions or Google Cloud Build) and session storage (in memory, Cloud SQL or platform sessions).

It includes naming constraints (project names up to 26 characters, lowercase), warns not to create the directory before running create, and says to pass the right guidance filename for the IDE (GEMINI.md, CLAUDE.md or AGENTS.md). For existing code it describes scaffold enhance with an agent-directory flag, and scaffold upgrade for newer CLI versions. It lists removed flags and templates so an agent does not reach for them, and sends retrieval, memory and similar capabilities to recipes in the ADK code skill. The SKILL.md is about 13 KB with one flags reference file.

Good for

  • Starting a new ADK agent project with the right template and flags
  • Adding deployment or CI/CD to an existing agent

Not for

  • Writing agent logic once the project exists
  • Non-ADK frameworks that do not use agents-cli templates

Depth 3/5

A 13 KB SKILL.md with a flags reference file; no scripts or evals.

Dependencies and costs

  • agents-cli (uv tool install google-agents-cli), Python 3.11+, uv and Node.js
  • A Google Cloud project and credentials for deployment and cloud features (an AI Studio API key is enough for local create, run and eval)
  • Telemetry: The agents-cli tool sends one usage signal per command (command name, exit code, error class, duration, CLI and Python versions, OS), written as a log entry to your own Google Cloud project's Cloud Logging, never file contents or arguments. Opt out with AGENTS_CLI_TELEMETRY=0; agents-cli info shows the current state.

Security review

Review before installing

Markdown-only guide to creating, enhancing and upgrading agent projects with agents-cli scaffold. Scaffold commands write project files and can overwrite scaffolding files with --force; the skill says to confirm requirements, CI/CD runner and any Git repo creation with the user. The agents-cli tool was not reviewed and sends usage telemetry unless you opt out.

Worth knowing

  • Relies on a CLI or package we could not reviewRequires the agents-cli binary (install: uv tool install google-agents-cli), whose code is not in the skill folder.SKILL.md:19
  • Installs packages or toolsInstall step is uv tool install google-agents-cli; scaffolding also generates a project with its own dependencies.SKILL.md:24
  • Sends usage data by default (can be turned off)The agents-cli tool this skill drives sends per-command usage telemetry by default; the repo README (outside the skill folder) documents AGENTS_CLI_TELEMETRY=0 and DO_NOT_TRACK=1 to opt out.README.md:195

What we checked

The skill folder (2 files) on Oct 29, 2026. Not a full review: it relies on code outside the repository: agents-cli (PyPI package google-agents-cli, installed with uv tool install).

NVIDIA SkillSpector static scan: 15 pattern hits (Excessive Agency 12, Tool Misuse 2, analysis-evasion 1). Hits are CLI flag names in documentation (--skip-checks, --auto-approve, --force) and phrases like 'without asking' that are in fact rules (the skill says never to create a Git repo or push without asking). Nothing executes from the skill folder.

A review, not a certification. Skills change after we check them — read the files before installing.

License

Apache-2.0 — commercial use allowed.

Can it run unattended?

Not really. Scaffolding is a quick interactive step after requirements are clarified.

Alternatives

Mastra Agent Skills

mastra-ai/skills

Mastra's official skills: a framework guide that routes to current docs and ten references, and a Factory supervisor skill for the mastra api CLI.

With caveats Broad access Depth 3/5

Google Agent Skills

google/skills

Google's official collection of about 180 skills for Google Cloud, Gemini APIs, Analytics, Data Manager, sign-in and other Google products.

Recommended Broad access Depth 3/5

The AI SDK repo's skills: one public ai-sdk skill for building with the SDK plus about a dozen maintainer-only skills for the monorepo.

With caveats Check first Depth 2/5

FAQ

What is google-agents-cli-scaffold?

Covers agents-cli scaffold create, enhance and upgrade: choosing a template, deployment target, CI/CD runner and session storage for a new agent project.

How do I install google-agents-cli-scaffold?

It ships in the google/agents-cli repository. Run uvx google-agents-cli setup or npx skills add google/agents-cli; the skill expects the agents-cli binary (uv tool install google-agents-cli).

What does scaffold enhance do?

It adds deployment, CI/CD or other infrastructure files to an existing project, and the skill says to pass an agent-directory flag if your agent code is not in app/. scaffold upgrade moves a project to a newer agents-cli version.

Sources: GitHub repository; install counts from skills.sh via Best Skills (CC BY 4.0). Review based on the published SKILL.md.