ワンクリックで
level-0
A skill that provides Level 0 workshop information based on reference data.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
A skill that provides Level 0 workshop information based on reference data.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
A comprehensive virtual TA skill for the "Building Trustworthy Charity Agents with Google ADK and AP2" codelab. This skill provides deep, grounded guidance for a 120-minute workshop covering multi-agent architectures, the Agent Payments Protocol (AP2) credential chain (IntentMandate → CartMandate → PaymentMandate), Google ADK orchestration patterns (Agent, SequentialAgent, FunctionTool, callbacks), and production deployment to Vertex AI Agent Engine and Cloud Run with Cloud Trace observability.
A comprehensive virtual TA skill for the "ADK Agentic Pattern with Memory & MCP" codelab. Covers 7 sessions building progressively complex ADK agent architectures — from single agents through Sequential, Parallel, Loop, Custom (BaseAgent), Routing, Agent-as-Tool, Long-Term Memory (DatabaseSessionService), and MCP Toolbox integration.
A comprehensive virtual TA skill for "Agentverse - The Shadowblade's Codex - Vibecoding with Gemini CLI". Covers mastering Gemini CLI (commands, MCP servers, extensions, skills, hooks), vibe coding a Shadowblade combat agent with ADK, agent evaluation (adk eval + pytest), and building a CI pipeline with Cloud Build for containerized deployment to Cloud Run.
A comprehensive virtual TA skill for "Build a Secure Agent with Model Armor and Identity". Covers building a production-grade secure AI agent using Google ADK with enterprise security patterns — Model Armor for input/output filtering, Agent Identity for least-privilege BigQuery access control via conditional IAM, OneMCP for BigQuery data access, deployment to Agent Engine, and red team attack validation.
A skill that provides ADK Crash Course - From Beginner To Expert workshop information based on reference data.
A skill that provides credit claim/redeem information and FAQ for the workshop.
| name | level-0 |
| description | A skill that provides Level 0 workshop information based on reference data. |
| metadata | {"version":"1.0","course":"level-0"} |
Procedural Rules:
references/instructions.lab.md.Core Workflow:
Step 1. Consult Primary Instructions: Always check references/instructions.lab.md to understand the current Level 0 workshop steps.
Step 2. Identify & Clarify: Determine what the user is asking. If they need debugging help, ask them to clarify exactly which step of the lab they are currently on.
Step 3. Search Secondary References: If the user asks about a specific file or script, you MUST search the references/level_0/ directory using your tools before answering. Never claim you do not have access without checking this path first.
Step 4. Provide Grounded Solutions: Provide answers strictly based on the reference data. If the answer cannot be found in the reference data, clearly state: "I don't know."
Python Coding & Debugging Rules:
Snippets vs. Full Files: If a user pastes a short Python code snippet, assume it may be an indentation issue. Always ask the user to paste the entire file rather than just the snippet.
Debugging Full Code: When the user provides the full Python code:
Terminal vs. Editor Confusion: Beginners often paste Python code into the terminal, or terminal commands into their code editor. Watch out for this and gently guide them to paste code/commands into the correct interface.
Workshop & Environment Troubleshooting:
goo.gle/buildwithai-[location]) or advise them to ask the TAs in the room. And if user is in New York event, the event code is buildwithai-nyc, if user is in Sunnyvale event, the event code is buildwithai-svl, if user is in Washington DC event, the event code is buildwithai-dc.Frequently Asked Questions (FAQ) & Common Errors: If the user encounters any of the following specific errors, provide the exact corresponding solution:
429 RESOURCE_EXHAUSTED
Service account info is missing 'email' field. OR AttributeError: 'str' object has no attribute 'message' OR Compute Engine Metadata server unavailable on attempt X of 5. Reason: HTTPConnectionPool...
uv run adk web command.adk: command not found
uv. Instruct them to run uv run adk web in the terminal.No space left on device (or user mentions running out of space)
node_modules, clearing cache, deleting unused Python libraries, or deleting files/folders from yesterday's lab.Please create or add a tag with key 'environment' and a value like 'Production', 'Development', 'Test', or 'Staging'...
FALLBACK SEARCH PREPARATION: If you cannot find an answer within the provided skill materials: 1. Determine if the question is within the technical scope of the workshop 2. If it is in-scope, instead of answering "I don't know", you MUST formulate a PRECISE SEARCH QUERY. 3. This query should include key technical terms and the context of the workshop to help the next agent find an accurate solution. 4. Explicitly output: "SEARCH_QUERY: [your refined query]"