google/agents-cli — Prompts
Verbatim Excerpt 1: Workflow Skill — STOP Guardrail
File: skills/google-agents-cli-workflow/SKILL.md
Technique: Hard-stop directive + prerequisite enforcement
---
name: google-agents-cli-workflow
description: >
This skill should be used when the user wants to "develop an agent",
"build an agent using ADK", "run the agent locally", "debug agent code",
"test an agent", "deploy an agent", "publish an agent", "monitor an agent",
or needs the ADK (Agent Development Kit) development lifecycle and coding
guidelines. Entrypoint for building ADK agents.
Always active — provides the full workflow (scaffold, build, evaluate,
deploy, publish, observe), code preservation rules, model selection
guidance, and troubleshooting steps for ADK or any agent development.
metadata:
author: Google
license: Apache-2.0
version: 0.2.0
requires:
bins:
- agents-cli
install: "uv tool install google-agents-cli"
---
# 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.
Prompting technique: Hard-stop command at the top of the skill with explicit consequence ("Skipping this leads to missing..."). The description field is designed as an activation trigger — listing all phrases that should activate this skill (very broad, catches any agent-related intent).
Verbatim Excerpt 2: Eval Skill — Eval-Fix Loop Instructions
File: skills/google-agents-cli-eval/SKILL.md
Technique: Iterative loop enforcement with explicit counter
## The Eval-Fix Loop
Evaluation is iterative. When a score is below threshold, diagnose the cause,
fix it, rerun — don't just report the failure.
### How to iterate
1. **Start small**: Begin with 1-2 eval cases, not the full suite
2. **Run eval**: `agents-cli eval run`
3. **Read the scores** — identify what failed and why
4. **Fix the code** — adjust prompts, tool logic, instructions, or the evalset
5. **Rerun eval** — verify the fix worked
6. **Repeat steps 3-5** until the case passes
7. **Only then** add more eval cases and expand coverage
**Expect 5-10+ iterations.** This is normal — each iteration makes the agent better.
### Shortcuts That Waste Time
Recognize these rationalizations and push back — they always cost more time
than they save:
Prompting technique: Step-numbered loop with exit condition ("until the case passes"). Counter injection ("Expect 5-10+ iterations") normalizes iteration and prevents premature stopping. Anti-pattern list ("Shortcuts That Waste Time") preemptively blocks agent rationalization behavior.
Verbatim Excerpt 3: Deploy Skill — Deployment Target Decision Matrix
File: skills/google-agents-cli-deploy/SKILL.md
## Deployment Target Decision Matrix
Choose the right deployment target based on your requirements:
| Criteria | Agent Runtime | Cloud Run | GKE |
|----------|-------------|-----------|-----|
| **Languages** | Python | Python | Python (+ others via custom containers) |
| **Scaling** | Managed auto-scaling | Fully configurable | Full Kubernetes scaling |
| **Session state** | Native VertexAiSessionService | In-memory (dev) / Cloud SQL | In-memory / Cloud SQL |
| **Setup complexity** | Lower (managed, purpose-built) | Medium | Higher (Kubernetes expertise) |
**Ask the user** which deployment target fits their needs. Each is a valid
production choice with different trade-offs.
Prompting technique: Decision matrix forces explicit user choice — the agent cannot pick a default. "Ask the user" instruction prevents autonomous decisions on infrastructure choices.