← 返回 Skills 市场
351
总下载
0
收藏
2
当前安装
6
版本数
在 OpenClaw 中安装
/install voice-ai-integration
功能描述
Integrate Shengwang products: ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation. Use when the user mentions Shengwa...
安全使用建议
This skill appears to do what it says: route Shengwang/ConvoAI questions to the correct product docs and, when needed, fetch official docs or clone example repos from gitee.com. Before installing or allowing the agent to run it, consider: 1) Review the two helper scripts (fetch-docs.sh, fetch-doc-content.sh) so you know exactly which URLs will be requested and where files will be written. 2) Be prepared that the agent may fetch documentation or clone sample repos into a temporary path — confirm you are comfortable with network access to doc.shengwang.cn, doc-mcp.shengwang.cn, and gitee.com. 3) The skill does not request credentials upfront, but using product APIs later will require your Shengwang/third‑party keys; provide those only when you explicitly choose to perform actions that need them. 4) If you want stricter control, disable autonomous invocation for this skill or require the agent to ask for permission before performing network fetches or cloning repositories.
功能分析
Type: OpenClaw Skill
Name: voice-ai-integration
Version: 0.1.5
The skill bundle is a legitimate integration tool for Shengwang (Agora) Voice AI services, providing structured workflows for an AI agent to assist with product routing and implementation. It includes helper scripts (fetch-docs.sh, fetch-doc-content.sh) that use curl to retrieve documentation from official domains (shengwang.cn) and references official sample repositories on Gitee and GitHub. The instructions in SKILL.md and the documentation modules include explicit safety guidelines regarding credential management and workspace protection, and no evidence of malicious intent, obfuscation, or data exfiltration was found.
能力评估
Purpose & Capability
Name/description match the files and instructions: local reference docs, routing rules, and doc-fetch helper scripts are appropriate for a Shengwang/ConvoAI integration helper. Network targets (doc.shengwang.cn, doc-mcp.shengwang.cn, gitee.com) and git cloning of sample repos are expected for this purpose.
Instruction Scope
Runtime instructions require running scripts to download a docs index and to fetch individual doc pages, and they may git-clone sample repos for inspection. The SKILL.md includes safety rules (state downloads, prefer temp paths, don't modify user projects until asked). It also instructs the agent to route automatically to product modules when intent is clear, which can lead to fetching docs or cloning repos without extra confirmations — not inherently malicious but worth noting for user consent.
Install Mechanism
No install spec; this is instruction-only plus two small shell helper scripts. That is low-risk compared with arbitrary downloads or package installs. The documented network sources are standard (official doc host and gitee).
Credentials
The skill's metadata does not request environment variables or credentials. The reference docs list many provider-specific env var names (LLM/TTS/ASR) but only as informational requirements for using Shengwang services — they are not required by the skill itself at install time.
Persistence & Privilege
The skill is not always-included and does not request elevated privileges. It instructs temporary repo cloning and avoiding writing into the user's main workspace unless explicitly asked. Autonomous invocation by the agent is allowed (platform default) but not combined with other red flags.
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 voice-ai-integration - 安装完成后，直接呼叫该 Skill 的名称或使用
/voice-ai-integration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
v0.1.5
- Clarified that the static doc index is downloaded from doc.shengwang.cn and no user data is sent.
- Added explicit details on network behavior and what is sent during doc downloads and sample repo inspections.
- Simplified language and formatting in the documentation for improved clarity.
- Removed some redundant instructions about project structure and runtime checks.
- No changes to core logic or intended use; documentation and privacy clarifications only.
v0.1.4
- Major update: Reworked product routing and modular flow.
- Removes legacy intake and request-modes logic; all routing is now table-driven and handled at the root.
- Adds clear product recognition aid and combination use-case table.
- Refines scope and responsibilities: product modules handle their own workflows, with no duplication at the entry point.
- Updates and expands local reference docs; new advanced and quickstart guides for ConvoAI.
- Tightens safety, consent, and credential handling rules.
v0.1.3
- Expanded runtime requirements and safety rules in SKILL.md, including explicit environment variables and network hosts.
- Refined intake and routing steps: initial analysis now focuses only on identifying the main Shengwang product, with product-specific logic moved to dedicated modules.
- Added new advanced ConvoAI documentation files, such as advanced-feature-routing.md, generation-rules.md, request-modes.md, and quickstart-intake.md.
- Removed deprecated intake/convoai.md and outdated ConvoAI REST documentation.
- Improved modularity and security: clarified product-specific flows, use of environment variables, and operation boundaries when using external resources.
v0.1.2
- Prefer use of official ConvoAI sample repo, agent-server-sdk (server), and agora-agent-client-toolkit (client) for implementation when supported, rather than building from the REST spec.
- REST API is now a fallback for unsupported operations, debugging, or when the user explicitly requests a REST-first approach.
- Guidance for ConvoAI now prioritizes SDK/sample-first solutions; REST documentation is used only as a fallback reference.
- Reference and research order for ConvoAI updated: check SDK/sample paths before consulting REST docs.
- Minor clarifications to workflows and routing to strengthen best-practice recommendations for implementation.
v0.1.1
- Improved ConvoAI intake workflow: now collects all unresolved kickoff and provider fields in a single consolidated message, with numbered choices and one-line reply.
- Streamlined intake flow: stops asking for details as soon as enough information is provided; no repeated questions.
- Defaults for ConvoAI platform and backend are now accepted via user omission.
- Minor clarifications in workflow steps and routing table to match Shengwang products.
v0.1.0
Initial release of Shengwang (Agora) Voice AI Integration skill.
- Supports integration with ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation.
- Provides a step-by-step workflow for gathering user requirements and routing to the correct documentation or implementation path.
- Ensures mandatory local documentation index is present before proceeding.
- Guides conversational intake, with minimal and focused questions to gather only necessary information.
- Includes clear routing table for documentation lookup and implementation.
- Supports automatic fallback to remote documentation fetching or web links when local references are insufficient.
元数据
常见问题
Voice Ai Integration 是什么？
Integrate Shengwang products: ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation. Use when the user mentions Shengwa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 351 次。
如何安装 Voice Ai Integration？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voice-ai-integration」即可一键安装，无需额外配置。
Voice Ai Integration 是免费的吗？
是的，Voice Ai Integration 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Voice Ai Integration 支持哪些平台？
Voice Ai Integration 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 Voice Ai Integration？
由 Hugo Chan（@hugochaan）开发并维护，当前版本 v0.1.5。
推荐 Skills