Google Agents Cli Workflow
Follow Google’s ADK end-to-end lifecycle—scaffold gate, build, evaluate, deploy, publish, and observe—before writing agent code with agents-cli.
Overview
Google Agents CLI Workflow is an agent skill most often used in Build (also Ship launch, Operate monitoring) that defines the full ADK development lifecycle and scaffold-first rules before any agent code is written.
Install
npx skills add https://github.com/google/agents-cli --skill google-agents-cli-workflowWhat is this skill?
- HARD-GATE: do not write agent code until `agents-cli scaffold create` or `scaffold enhance` plus `agents-cli info` check
- Covers full lifecycle: scaffold, build, evaluate, deploy, publish, observe with troubleshooting guidance
- Always-active workflow skill for ADK and general agent development on Google Cloud
- Install path via `uvx google-agents-cli setup` with `agents-cli` binary requirement
- Works across Gemini CLI, Claude Code, Codex, and other coding agents
- Skill metadata version 0.2.0
- Lifecycle phases referenced: scaffold, build, evaluate, deploy, publish, observe
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 want to build an ADK agent but jumping straight to code skips eval setup, deployment scaffolding, and project conventions agents-cli expects.
Who is it for?
Indie builders starting or extending Google ADK agents who need one authoritative workflow across local dev, evaluation, and Cloud deployment.
Skip if: Non-ADK agent stacks with no `agents-cli`, or one-off script edits when requirements are already clarified and scaffolding is complete.
When should I use this skill?
User wants to develop, run locally, debug, test, deploy, publish, or monitor an ADK agent—or any agent development needing agents-cli conventions.
What do I get? / Deliverables
You follow a gated ADK lifecycle with scaffold verified via `agents-cli info`, then proceed to build, evaluate, deploy, publish, and observe with consistent Google Cloud patterns.
- Scaffold-verified ADK project ready for implementation
- Lifecycle checklist covering eval, deploy, publish, and observe
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build is the canonical shelf because the skill is the entrypoint for developing ADK agents and enforcing scaffold-first conventions before implementation. Agent-tooling matches ADK project structure, model selection, code preservation rules, and agents-cli commands rather than generic app frontend work.
Where it fits
User asks to build an ADK agent—you run `agents-cli info` and scaffold before any Python agent modules are edited.
You need deploy and publish steps aligned with ADK after local tests pass.
Post-release, you follow observe guidance to monitor agent behavior in Google Cloud.
How it compares
Use as the parent orchestration skill—not a replacement for scaffold-only or deploy-only skills in the same ADK suite.
Common Questions / FAQ
Who is google-agents-cli-workflow for?
Solo builders and small teams using Google ADK and agents-cli with Claude Code, Codex, Gemini CLI, or similar agents who need a single lifecycle playbook.
When should I use google-agents-cli-workflow?
Use it in Build when developing or debugging ADK agents, in Ship when preparing deploy and publish steps, and in Operate when you need observe/monitor guidance after launch.
Is google-agents-cli-workflow safe to install?
It drives CLI installs and Cloud-oriented workflows; review the Security Audits panel on this Prism page and pin `google-agents-cli` versions in your environment.
Workflow Chain
Then invoke: google agents cli scaffold
SKILL.md
READMESKILL.md - Google Agents Cli Workflow
# ADK Development Workflow & Guidelines > **STOP — Do NOT write code yet.** If no project exists, scaffold first with `agents-cli scaffold create <name>`. If the user already has code, use `agents-cli scaffold enhance .` to add the agents-cli structure. Run `agents-cli info` to check if a project already exists. Skipping this leads to missing eval boilerplate, CI/CD config, and project conventions. **agents-cli** is a CLI and skills toolkit for building, evaluating, and deploying agents on Google Cloud using the [Agent Development Kit (ADK)](https://adk.dev/). It works with any coding agent — Gemini CLI, Claude Code, Codex, or others. Install with `uvx google-agents-cli setup`. > Requires: google-agents-cli ~= 0.2.0 > If version is behind, run: uv tool install "google-agents-cli~=0.2.0" > Check version: agents-cli info > [Install uv](https://docs.astral.sh/uv/getting-started/installation/index.md) first if needed. ## Session Continuity & Skill Cross-References Re-read the relevant skill **before** each phase — not after you've already started and hit a problem. Context compaction may have dropped earlier skill content. If skills are not available, run `uvx google-agents-cli setup` to install them. | Phase | Skill | When to load | |-------|-------|--------------| | 0 — Understand | — | No skill needed — read `.agents-cli-spec.md` if present, else clarify goals with the user | | 1 — Study samples | — | Check Notable Samples table below — clone and study matching samples before scaffolding | | 2 — Scaffold | `/google-agents-cli-scaffold` | Before creating or enhancing a project | | 3 — Build | `/google-agents-cli-adk-code` | Before writing agent code — API patterns, tools, callbacks, state | | 4 — Evaluate | `/google-agents-cli-eval` | Before running any eval — evalset schema, metrics, eval-fix loop | | 5 — Deploy | `/google-agents-cli-deploy` | Before deploying — target selection, troubleshooting 403/timeouts | | 6 — Publish | `/google-agents-cli-publish` | After deploying, if registering with Gemini Enterprise (optional) | | 7 — Observe | `/google-agents-cli-observability` | After deploying — traces, logging, monitoring setup | --- ## Setup If `agents-cli` is not installed: ```bash uv tool install google-agents-cli ``` ### `uv` command not found Install `uv` following the [official installation guide](https://docs.astral.sh/uv/getting-started/installation/index.md). ### 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. --- ## Phase 0: Understand Before writing or scaffolding anything, understand what you're building. If `.agents