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

references/errors.md

View on GitHub
# ADK Agent Builder — Common Errors

## Import & Dependency Errors

| Error | Cause | Fix |
|-------|-------|-----|
| `ModuleNotFoundError: No module named 'google.adk'` | `google-adk` not installed | `pip install google-adk` |
| `ImportError: cannot import name 'Agent'` | Wrong ADK version or stale install | `pip install --upgrade google-adk` |
| `Python 3.9 not supported` | ADK requires 3.10+ | Use `pyenv` or update system Python |
| `Dependency conflict with langchain` | Both packages modify `google.cloud` namespace | Use separate virtual environments |

## GCP Authentication Errors

| Error | Cause | Fix |
|-------|-------|-----|
| `google.auth.exceptions.DefaultCredentialsError` | No application default credentials | `gcloud auth application-default login` |
| `403 Forbidden: Vertex AI API` | Service account lacks `aiplatform.user` role | `gcloud projects add-iam-policy-binding PROJECT --member=serviceAccount:SA --role=roles/aiplatform.user` |
| `403: Vertex AI API has not been used in project` | API not enabled | `gcloud services enable aiplatform.googleapis.com` |
| `Permission denied on bucket` | Agent Engine needs GCS access | Grant `storage.objectViewer` to the Agent Engine service account |

## Agent Engine Deployment Errors

| Error | Cause | Fix |
|-------|-------|-----|
| `adk deploy: command not found` | ADK CLI not in PATH | `pip install google-adk[cli]` or check PATH |
| `Quota exceeded for Agent Engine` | Region quota limit | Try `us-central1` (highest quota) or request increase |
| `Build failed: requirements.txt not found` | Missing dependency file | Ensure `requirements.txt` or `pyproject.toml` in project root |
| `Agent failed health check after deploy` | Agent crashes on startup | Check logs: `gcloud logging read "resource.type=aiplatform.googleapis.com/Agent"` |
| `Timeout during deployment` | Large container image or slow build | Reduce dependencies, use `--timeout=600` flag |

## Tool & Runtime Errors

| Error | Cause | Fix |
|-------|-------|-----|
| `Tool 'search' not registered` | Tool not added to agent's tool list | Add tool to `tools=[]` parameter in Agent constructor |
| `RateLimitError from tool API` | External API rate limit hit | Add `tenacity` retry with exponential backoff |
| `Agent loop exceeded max_turns` | Agent stuck in reasoning loop | Set `max_turns` parameter, add exit conditions to system prompt |
| `JSON decode error in tool response` | Tool returning non-JSON | Wrap tool output in structured response format |

## Multi-Agent Orchestration Errors

| Error | Cause | Fix |
|-------|-------|-----|
| `Circular dependency in agent graph` | Agent A delegates to B, B delegates to A | Review orchestration topology, use DAG pattern |
| `SequentialAgent: step 2 failed` | Upstream agent produced unexpected output | Add output validation between pipeline stages |
| `ParallelAgent: timeout on subtask` | One parallel agent hung | Set per-agent `timeout` parameter |
| `Orchestrator received empty response` | Sub-agent returned nothing | Add fallback response in sub-agent's system prompt |

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