google-agents-cli-workflow

SKILL.md

Complete workflow for scaffolding, building, evaluating, and deploying agents using Google's Agent Development Kit.

Covers all seven phases: understanding requirements, studying reference samples, scaffolding projects, implementing agent logic, evaluation, deployment, and observability

Includes mandatory Phase 0 clarification questions (problem statement, APIs, safety constraints, deployment preference) and a spec template to document decisions before coding

Provides phase-specific CLI commands (agents-cli scaffold create, agents-cli run, agents-cli eval run, agents-cli deploy) and cross-references to related skills for deep dives into code patterns, evaluation methodology, and infrastructure

Enforces code preservation (modify only targeted segments, never change models or config without explicit request) and systematic debugging (reproduce, localize, fix one thing, verify, guard)

Agent Development Workflow & Guidelines

agents-cli is a CLI and skills toolkit for building, evaluating, and deploying agents on Google Cloud. It works with any coding agent — Antigravity CLI, Claude Code, Codex, or others — and with the agent framework of your choice (the Agent Development Kit (ADK) by default). Install with uvx google-agents-cli setup.

Before writing agent code, make sure a scaffolded project exists (see Phase 2). Skipping scaffolding loses eval boilerplate, CI/CD config, and project conventions.

Requires: google-agents-cli = 1.1.0
If version is behind, run: uv tool install "google-agents-cli=1.1.0"

Check version: agents-cli info
Install uv 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.