From adk-tools
Use this skill to add Google Search grounding to an ADK 2.0 agent for factual, up-to-date answers with citations. Triggers on: "ground ADK agent with search", "Google Search in ADK", "ADK with web search", "grounding agent answers", "real-time search ADK", "cite sources ADK", "ADK google_search tool", "search grounding". Generates an agent bound to the built-in google_search tool with instruction text that forces citation of sources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/adk-tools:google-search-groundingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Bind the `google_search` tool to an ADK 2.0 agent so its answers stay current and cite sources.
Bind the google_search tool to an ADK 2.0 agent so its answers stay current and cite sources.
from google.adk.agents import LlmAgent
from google.adk.tools import google_search
root_agent = LlmAgent(
name="grounded_research",
model="gemini-2.5-flash",
description="Answers research questions with live web grounding and citations.",
instruction=(
"You are a research assistant. ALWAYS use google_search before answering "
"questions about facts, dates, prices, or current events. Quote each claim "
"with a [source: URL] inline citation. If search returns nothing relevant, "
"say so explicitly — do NOT speculate."
),
tools=[google_search],
)
If the LLM ignores the citation rule, tighten the instruction:
instruction=(
"Format every factual statement as: 'Claim. [source: URL]'. "
"Statements without citations are FORBIDDEN. If you cannot find a source, "
"say 'I could not verify this.'"
)
from google.adk.tools import google_search
def my_internal_search(query: str) -> list[dict]:
"""Search internal knowledge base. Returns list of {title, url, snippet}."""
...
root_agent = LlmAgent(
...,
tools=[google_search, my_internal_search],
instruction=(
"Use my_internal_search FIRST for company-specific questions. "
"Use google_search for public information. Cite both."
),
)
google_search requires Vertex AI / AI Studio access to Gemini grounding APInpx claudepluginhub healthcare-ai-consulting-llc/adk-2-toolkit --plugin adk-toolsGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.