← 返回 Skills 市场
Cx Agent Studio
作者
Yash Kavaiya
· GitHub ↗
· v1.0.0
409
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cx-agent-studio
功能描述
Guide and instructions for using Google Customer Experience Agent Studio (CX Agent Studio). Use when creating conversational agents, writing or structuring i...
使用说明 (SKILL.md)
CX Agent Studio
Customer Experience Agent Studio (CX Agent Studio) is a minimal code conversational agent builder built on the Agent Development Kit (ADK), representing the evolution of Dialogflow CX.
Core Capabilities
- AI-Augmented Building: Generate agents using Gemini with a 1-2 sentence goal.
- Bi-directional Streaming: Ultra-low latency voice interactions.
- Asynchronous Tool Calling: Maintains natural conversation flow during backend calls.
Quick Actions
1. Generating an Agent with AI
To generate an agent automatically:
- Provide a clear 1-2 sentence goal.
- Optionally provide up to 5 knowledge documents (under 8MB total) like FAQs or tool catalogs. Note: Only works for the root agent and empty agents.
2. Architecture & Design
- Agents: Root (steering) agents orchestrate tasks and delegate to sub-agents. Read
references/agents.md. - Flows: Integrate legacy Dialogflow CX flows for deterministic business logic (auth, sequential validation). Read
references/flows.md. - Variables: Store and retrieve runtime conversation data. Read
references/variables.md.
3. Writing Agent Instructions
Agent instructions guide the model's behavior, persona, and tool/agent usage.
- Syntax References:
- Variables:
{variable_name} - Tools:
{@TOOL: tool_name} - Sub-Agents:
{@AGENT: Agent Name}
- Variables:
- For complex instructions or recommended XML formatting, read:
references/instructions.md - Best Practices: Start simple, use specific/structured instructions, flat parameter structures. Read
references/best-practices.md.
4. Tools & Callbacks
- Tools: Connect your agent to external systems. Wrap complex APIs in Python tools to reduce context overhead. Read
references/tools.md. - Callbacks: Advanced Python hooks (
before_agent_callback,after_model_callback, etc.) to control execution, validate states, or inject custom JSON payloads. Readreferences/callbacks.md.
5. Guardrails & Safety
- Guardrails: Protect against prompt attacks and enforce Responsible AI policies. Read
references/guardrails.md.
6. Agent Evaluation
Evaluation ensures agent performance via automated test cases.
- Scenario Test Cases: AI-generated simulated user conversations based on a user goal.
- Golden Test Cases: Specific, ideal conversation paths for regression testing.
- For detailed evaluation metrics, personas, and test case creation, read:
references/evaluation.md
安全使用建议
This skill is a documentation-only guide for building CX Agent Studio agents and appears internally consistent. It does not ask for credentials or install code. However, the guide encourages adding Python tools and callbacks — any Python tool or connector you attach to agents can execute arbitrary code and call external services, so: (1) review and vet any Python code or third-party connectors before enabling them, (2) avoid uploading sensitive documents to RAG/data stores you don't control, (3) enable guardrails, logging, and data-redaction settings if you use third-party integrations, and (4) audit permissions for any connectors (e.g., Salesforce, Google APIs) you configure. If you want a higher assurance, ask the publisher for provenance (homepage, owner identity) or request an explicit list of required connectors and example tool code to review before installation.
功能分析
Type: OpenClaw Skill
Name: cx-agent-studio
Version: 1.0.0
The skill bundle, primarily documentation, describes a platform (CX Agent Studio) that allows for the execution of arbitrary Python code as 'tools' and 'callbacks' (`references/tools.md`, `references/callbacks.md`). These Python hooks can inspect and modify model requests/responses, tool arguments/results, and the agent's internal state (`context.state`), offering extensive control over the agent's behavior. While presented as legitimate development features, these capabilities represent a significant attack surface (e.g., potential for RCE, data manipulation, or exfiltration) if not properly secured or if malicious code is introduced by a developer or via prompt injection. The documentation itself does not contain malicious code or instructions for the OpenClaw agent to perform harmful actions, but it highlights inherently risky capabilities within the described platform.
能力评估
Purpose & Capability
The name/description (CX Agent Studio guidance) matches the content: design notes, instruction syntax, callbacks, tools, and evaluation guidance. There are no unrelated requirements (no env vars, binaries, or installs) that would be inconsistent with the stated purpose.
Instruction Scope
SKILL.md and referenced docs stay within builder guidance. They explicitly recommend creating Python tools and callbacks to wrap external APIs and manipulate state — this is expected for an agent-builder but means any code you or your team add (Python tools/callbacks) can run arbitrary logic and access data. The skill itself contains no executable code.
Install Mechanism
No install spec and no code files that would be written to disk. Instruction-only skills are lowest-risk from an installation perspective.
Credentials
No required environment variables, credentials, or config paths are declared. The guide discusses integrating connectors and tools in general terms but does not request secrets itself.
Persistence & Privilege
Skill flags are default (always:false, agent-invocable allowed). It does not request permanent presence or modify other skills or system settings. Autonomous invocation is allowed by platform default and not itself a reason to distrust this instruction-only skill.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install cx-agent-studio - 安装完成后，直接呼叫该 Skill 的名称或使用
/cx-agent-studio触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of cx-agent-studio.
- Provides guides and instructions for using Google Customer Experience Agent Studio.
- Covers AI-augmented agent building, bi-directional voice streaming, and asynchronous tool integration.
- Includes syntax and best practices for agent instructions and XML formatting.
- Explains connecting tools, using callbacks, and establishing guardrails for safety.
- Details methods for agent evaluation using scenario and golden test cases.
元数据
常见问题
Cx Agent Studio 是什么？
Guide and instructions for using Google Customer Experience Agent Studio (CX Agent Studio). Use when creating conversational agents, writing or structuring i... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 409 次。
如何安装 Cx Agent Studio？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cx-agent-studio」即可一键安装，无需额外配置。
Cx Agent Studio 是免费的吗？
是的，Cx Agent Studio 完全免费（开源免费），可自由下载、安装和使用。
Cx Agent Studio 支持哪些平台？
Cx Agent Studio 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Cx Agent Studio？
由 Yash Kavaiya（@yash-kavaiya）开发并维护，当前版本 v1.0.0。
推荐 Skills