Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-ml/jeremy-google-adk/skills/adk-agent-builder

adk-agent-builder

Verified

Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel/Loop), tool wiring, evaluation, and optional Vertex AI Agent Engine deployment. Use when building, scaffolding, or deploying ADK agents on Google Cloud, or when wiring ADK tools and orchestration patterns. Trigger with "build an ADK agent", "scaffold an agent on ADK", or "deploy to Agent Engine".

FileKindSize
ARD.mdmarkdown3.8 KB
PRD.mdmarkdown6.8 KB
SKILL.mdskill md3.8 KB
references/errors.mdmarkdown3.2 KB
references/examples.mdmarkdown3.7 KB
references/implementation.mdmarkdown4.7 KB
# ARD: ADK Agent Builder

> Part of [Tons of Skills](https://tonsofskills.com) by [Intent Solutions](https://intentsolutions.io) | [jeremylongshore.com](https://jeremylongshore.com)

## System Context

The ADK Agent Builder operates within the Google Cloud AI ecosystem. It generates project scaffolds that target the `google-adk` SDK and optionally deploy to Vertex AI Agent Engine.

```
Developer (Claude Code)
    │
    ▼
ADK Agent Builder Skill
    │
    ├── Reads: project context, existing code, user requirements
    ├── Generates: agent scaffold (src/agents/, src/tools/, tests/)
    └── Optionally deploys: adk deploy → Vertex AI Agent Engine
                                            │
                                            ├── IAM (Service Account, roles)
                                            ├── Cloud Build (container image)
                                            └── Agent Engine Runtime (serving)
```

## Data Flow

1. **Input**: User describes the agent they want (purpose, tools needed, single vs multi-agent)
2. **Architecture selection**: Skill determines ReAct (single) or orchestrated (multi-agent) based on complexity
3. **Scaffold generation**: Creates directory structure, agent entrypoint, tool registry, config, tests
4. **Tool wiring**: Connects requested tools (APIs, databases, search) with credential management
5. **Validation**: Runs smoke test prompt against local agent to verify it works
6. **Deployment** (optional): Generates `adk deploy` command + post-deploy health checks

## Key Design Decisions

| Decision | Choice | Rationale |
|----------|--------|-----------|
| SDK | Google ADK over LangChain/CrewAI | Native GCP integration, Agent Engine deployment, Google-maintained |
| Agent pattern | ReAct (reasoning + acting) | Proven pattern for tool-using agents, ADK's primary paradigm |
| Multi-agent | Sequential/Parallel/Loop | ADK's built-in orchestration patterns, no custom framework needed |
| Tool registry | Centralized `src/tools/` | Single place to add/remove tools, clear dependency graph |
| Credentials | Environment variables + Secret Manager | Never hardcoded, works in local dev and Agent Engine |
| Testing | Unit tests + smoke prompts | Unit tests for tool logic, smoke prompts for end-to-end agent behavior |

## Tool Usage Pattern

| Tool | Purpose |
|------|---------|
| `Read` | Examine existing project files, understand codebase context |
| `Write` | Create scaffold files (agent code, configs, tests) |
| `Edit` | Modify existing files (add tools to registry, update config) |
| `Grep` | Find existing patterns, check for conflicts |
| `Bash(cmd:*)` | Run `adk deploy`, `pip install`, `python -m pytest`, smoke tests |

## Error Handling Strategy

| Error Class | Detection | Recovery |
|------------|-----------|----------|
| Missing `google-adk` | ImportError on scaffold validation | Provide `pip install google-adk` command |
| GCP auth failure | `gcloud auth` check before deploy | Guide through `gcloud auth application-default login` |
| Missing IAM roles | 403 on Agent Engine API | Identify exact role needed, provide `gcloud` command |
| Vertex AI not enabled | API disabled error | Provide `gcloud services enable` command |
| Tool credential missing | Environment variable not set | List required env vars, suggest Secret Manager |
| Deployment quota exceeded | 429 or quota error | Suggest region change or quota increase request |

## Extension Points

- **Custom tools**: Add `.py` files to `src/tools/`, register in tool registry
- **New agent architectures**: ADK supports custom orchestration beyond Sequential/Parallel/Loop
- **Alternative deployment**: Local-only, Cloud Run, or custom infrastructure instead of Agent Engine
- **Testing expansion**: Add evaluation datasets, A/B prompt testing, latency benchmarks
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall