By healthcare-ai-consulting-llc
Author and integrate ADK 2.0 tools: function tools, MCP tools, OpenAPI tools, human-in-the-loop tool confirmation, Google Search grounding.
Use this skill to write a custom Python function tool for an ADK 2.0 agent. Triggers on: "ADK function tool", "create a tool for ADK", "custom tool in ADK", "wrap a function as ADK tool", "agent tool that does X", "Python callable as ADK tool", "ADK tool with type hints". Generates a properly type-hinted Python function with docstring (used by ADK as the tool schema) ready to drop into an agent's tools=[] list.
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.
Use this skill to wire an MCP (Model Context Protocol) server's tools into an ADK 2.0 agent. Triggers on: "ADK MCP tools", "use MCP server in ADK", "MCP integration ADK", "connect ADK to MCP", "MCP toolset", "ADK reads MCP", "stdio MCP server in ADK", "HTTP MCP server in ADK". Generates an MCP toolset (stdio or HTTP transport) that exposes the remote MCP server's tools to the agent's LLM.
Use this skill to expose a REST API as ADK 2.0 tools by pointing at its OpenAPI / Swagger spec. Triggers on: "ADK OpenAPI tool", "Swagger to ADK", "REST API as ADK tools", "ADK from OpenAPI spec", "expose REST endpoints to agent", "ADK OpenAPIToolset", "auto-generate ADK tools from spec". Generates an OpenAPIToolset bound to a spec file or URL — every operation becomes a callable tool with auto-derived parameters and types.
Use this skill to add human-in-the-loop tool-call confirmation to an ADK 2.0 agent — the agent must get explicit approval before destructive or sensitive tools fire. Triggers on: "ADK human in the loop", "ADK tool confirmation", "approve tool calls in ADK", "HITL ADK", "guard tool execution", "ADK ask before running tool", "manual approval for ADK tool". Generates a tool wrapped with require_confirmation() so ADK pauses and surfaces a prompt before invoking the tool.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace for Google ADK 2.0 (Agent Development Kit).
8 themed plugins · 37 skills · 8 slash commands. Covers every major ADK 2.0 surface: agent scaffolding, multi-agent graph workflows, tooling (MCP/OpenAPI/HITL), sessions with rewind, Gemini Live streaming, evaluation, deployment, observability/safety.
| Plugin | Skills | Surface |
|---|---|---|
adk-agent-builder | 5 | LlmAgent, Sequential/Loop/Parallel workflow agents, custom agents, agent config (no-code), multi-model router |
adk-multi-agent | 5 | Coordinator+subagent, A2A expose, A2A consume, graph workflows (2.0), dynamic workflows (2.0) |
adk-tools | 5 | Function tools, MCP tools, OpenAPI tools, tool-confirmation HITL, Google Search grounding |
adk-sessions-memory | 4 | Session rewind, session migrate, context cache/compress, artifacts |
adk-streaming | 4 | Gemini Live bootstrap, audio, vision, bidirectional tool streaming |
adk-evaluation | 5 | Eval sets, custom metrics, user sim, env sim, optimization loop |
adk-deployment | 5 | adk web, Cloud Run, GKE, Vertex Agent Engine, runtime config |
adk-observability-safety | 4 | Logging/callbacks, tool monitor, safety policies, auth framework |
/plugin marketplace add /Users/alexwork/Documents/ExternalHarddrive/Claude-Skill-Builder-V2-main/adk-2-toolkit
/plugin install adk-agent-builder@adk-2-toolkit
/plugin marketplace add Healthcare-AI-Consulting-LLC/adk-2-toolkit
/plugin install adk-agent-builder@adk-2-toolkit
pip install google-adk --pre # ADK 2.0 beta
# Or with extensions:
pip install "google-adk[extensions]" --pre
Python 3.10+ required.
Each plugin ships one entry-point command:
/adk-new-agent — scaffold an LlmAgent or workflow agent/adk-multi-agent — design coordinator + subagents/adk-add-tool — add a tool (function/MCP/OpenAPI) to an agent/adk-session — wire sessions, memory, rewind/adk-stream — bootstrap Gemini Live streaming/adk-eval — generate eval set + run adk eval/adk-deploy — deploy to Cloud Run / GKE / Vertex/adk-observe — wire callbacks, safety, authgoogle-adk is on the active Python path.npx claudepluginhub healthcare-ai-consulting-llc/adk-2-toolkit --plugin adk-toolsMulti-agent orchestration in ADK 2.0: coordinator+subagent, A2A protocol, graph workflows, dynamic branching loops.
ADK 2.0 sessions and memory: rewind to checkpoints, migrate sessions, context cache/compression, artifact handling.
Gemini Live API streaming agents in ADK 2.0: bootstrap, audio, vision, bidirectional tool streaming.
Evaluate and optimize ADK 2.0 agents: eval set generation, custom metrics, user simulation, environment simulation, optimization loops.
Observability and safety for ADK 2.0 agents: logging callbacks, tool monitoring, safety policies, auth framework.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows