Google Agent Development Kit (ADK) vs Guizang PPT Skill

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Google Agent Development Kit (ADK) Agents	Guizang PPT Skill Agents
Tagline	Google's open-source framework for building, evaluating, and deploying production AI agents	Claude Code / Codex agent skill that generates single-file HTML slide decks in editorial-magazine or Swiss-design styles.
Category	Agents	Agents
Pricing	Free· Framework itself is free and open-source (Apache 2.0). Costs come from the underlying model provider (e.g. Gemini API / Vertex AI usage) and any hosting infrastructure (Cloud Run, GKE, Agent Engine).	Free· Free, AGPL-3.0; requires a host AI agent (Claude Code, Codex, etc.)
Model	Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM	Multi-model (Claude, Codex, GPT-Image)
Editorial score	—	7.3 / 10
Use cases	Multi-agent research assistantCustomer support triage agentRAG chatbot backed by Vertex AI SearchCode review and refactoring agentBigQuery natural-language analytics agentDocument processing pipelineVoice/streaming conversational agentInternal tool-use agent orchestrating APIsEvaluation and regression testing of LLM workflowsEnterprise workflow automation on Agent Engine	html-slide-deckspresentation-designcover-image-generationclaude-code-skillswiss-design-layouts
Pros	Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly Rich multi-agent primitives out of the box: SequentialAgent, ParallelAgent, LoopAgent, and hierarchical sub-agents Tight Google Cloud integration for deployment (Cloud Run, GKE, Agent Engine) plus native BigQuery/Vertex Search tools Evaluation harness with trajectory-level scoring is included, not a separate paid add-on First-class MCP (Model Context Protocol) client and server support	Two tightly locked visual systems (editorial + Swiss) with 32+ named layouts Single-file HTML output with keyboard, touch, and low-power modes Includes a validator script that blocks off-grid Swiss layouts Plugs directly into Claude Code and Codex via the Skills protocol Active project with 19k+ stars and corporate sponsorship
Cons	Documentation and examples lean heavily on Gemini + Google Cloud; non-Google paths work but feel like second-class citizens API surface is still evolving — breaking changes between minor versions have been common through 2025-2026 Multi-agent orchestration primitives are powerful but the graph/callback model has a real learning curve compared to a plain prompt loop Agent Engine deployment is convenient but locks you into GCP billing and quotas TypeScript/Kotlin support lags the Python SDK in features and community examples	Requires a shell-capable AI agent; will not work in plain chatbots Documentation is primarily in Chinese (English README is partial) Not suited for dense data tables, training decks or collaborative editing AGPL-3.0 license complicates commercial bundling
Website	google.github.io	github.com

Pick Google Agent Development Kit (ADK) if

✅ Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product
✅ Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only
✅ Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously
✅ Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly

Pick Guizang PPT Skill if

✅ Two tightly locked visual systems (editorial + Swiss) with 32+ named layouts
✅ Single-file HTML output with keyboard, touch, and low-power modes
✅ Includes a validator script that blocks off-grid Swiss layouts
✅ Plugs directly into Claude Code and Codex via the Skills protocol

Compare a different pair →