Agents CLI: Development Workflow
Part of Google's agents-cli skills suite for building agents on the Agent Development Kit (ADK) and Gemini Enterprise Agent Platform. This is the always-active entrypoint skill: it defines the phased development lifecycle (understand the requirements, study reference recipes, scaffold a project, write agent code, evaluate, deploy, publish, and observe), tells the coding agent which of the other six google-agents-cli skills to load at each phase, and carries code-preservation rules, model-selection guidance, and a design-dialogue playbook for clarifying what to build before any code gets written. Requires the agents-cli Python CLI (installed via uv).
This skill hasn't been reviewed yet.
What it does
The entrypoint skill for Google's agents-cli toolkit — walks a coding agent through the full ADK development lifecycle: understand, scaffold, build, evaluate, deploy, publish, observe.
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: Development Workflow
Part of Google's agents-cli skills suite for building agents on the Agent Development Kit (ADK) and Gemini Enterprise Agent Platform. This is the always-active entrypoint skill: it defines the phased development lifecycle (understand the requirements, study reference recipes, scaffold a project, write agent code, evaluate, deploy, publish, and observe), tells the coding agent which of the other six google-agents-cli skills to load at each phase, and carries code-preservation rules, model-selection guidance, and a design-dialogue playbook for clarifying what to build before any code gets written. Requires the agents-cli Python CLI (installed via uv).
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-workflow). 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 (adk-code, scaffold, eval, deploy, publish, observability) from google/agents-cli's skills/ folder.
npx skills add google/agents-cli - 2
Install the CLI itself (optional but recommended)
The skills reference the agents-cli command throughout. Without it installed, the guidance is read-only reference material.
uv tool install google-agents-cli - 3
Activate in Claude
Ask to build, scaffold, evaluate, deploy, or publish an ADK agent — this skill loads first and routes you to the right phase-specific skill.
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
agents-cli is a CLI and skills toolkit for building, evaluating, and deploying agents on Google Cloud, built primarily around the Agent Development Kit (ADK) but usable with other frameworks. This workflow skill is the entrypoint: it does not itself teach ADK APIs or CLI flags, it orchestrates when to load the six other skills in this suite.
The lifecycle it defines
| Phase | Skill to load | Purpose |
|---|---|---|
| 0 — Understand | (none — design dialogue) | Clarify what the agent should do, one question at a time, before any code |
| 1 — Study recipes | google-agents-cli-adk-code |
Look up a capability (retrieval, sandboxing, memory, guardrails) against a catalog of reference implementations |
| 2 — Scaffold | google-agents-cli-scaffold |
Create or enhance a project with agents-cli scaffold create / enhance |
| 3 — Build | google-agents-cli-adk-code |
Write agent code against ADK’s Python API |
| 4 — Evaluate | google-agents-cli-eval |
Run eval datasets, grade traces, iterate on failures |
| 5 — Deploy | google-agents-cli-deploy |
Deploy to Agent Runtime, Cloud Run, or GKE |
| 6 — Publish | google-agents-cli-publish |
Optionally register the agent with Gemini Enterprise |
| 7 — Observe | google-agents-cli-observability |
Set up tracing, logging, and analytics |
Design-first discipline
Before scaffolding or writing any code, the skill insists on a design dialogue: what problem the agent solves, what external APIs/tools it needs, safety constraints, and deployment preference. For non-trivial agents it proposes 2-3 architecture approaches and writes an approved spec to .agents-cli-spec.md before moving on — it explicitly refuses to assume or fill in blanks on the user’s behalf.
Requirements
Needs agents-cli ~1.5.0 installed (uv tool install google-agents-cli), which in turn needs uv and Python 3.11+.