voice-ai-integration by shengwang-community/skills
npx skills add https://github.com/shengwang-community/skills --skill voice-ai-integration⚠️ 此步骤不容商量。在任何路由、信息收集或代码生成之前执行。
检查 references/docs.txt 是否存在。如果不存在(或者这是一个新项目),请立即下载:
bash skills/voice-ai-integration/scripts/fetch-docs.sh
此文件是文档索引——所有文档查找都依赖它。在此文件存在或已尝试下载之前,不要继续执行步骤 1。如果下载失败,请使用本地参考文档和备用 URL 继续。
使用 信息收集 来收集启动信息。只询问用户尚未提供的细节。
仅收集消除实施障碍所需的细节:
使用对话流程:
ConvoAI 有一个特殊的信息收集模式:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
agent-server-sdk 和客户端的 agora-agent-client-toolkit,而不是直接基于 REST 规范构建对于 ConvoAI,用户在实施前仍必须明确回答或确认任何未解决的 其他 后续值。
对于有默认值的未解决 ConvoAI 字段,保持它们可见,并将省略视为明确的默认确认。这包括 Platform = Web 和 Backend = Python。如果第一个统一回复不完整,仅针对未解决的强制性障碍提出一个简短的后续问题。
如果用户已经提供了足够的信息,不要重复提问。生成一个轻量级的启动摘要,然后自动继续,除非仍有必需的细节缺失。
使用启动摘要加上下面的路由表来选择正确的本地参考模块。如果可用信息足够,则开始使用 references/ 下的现有本地文档进行实施。
如果步骤 2 提供了足够的信息用于实施,则继续。如果仍有必要信息缺失或本地参考不足,则继续步骤 3。
使用 references/doc-fetching.md 来获取更全面的文档。仅在步骤 2 之后,当本地参考不足以完成请求的实施时,才执行此操作。
研究顺序:
agent-server-sdk 和 agora-agent-client-toolkit 路径一旦步骤 3 提供了足够的信息,就继续实施。
git clone --depth 1 <url> —— GitHub URL 必须仅为仓库根目录(不能是分支/子目录路径)每周安装次数
74
仓库
GitHub 星标数
6
首次出现
13 天前
安全审计
安装于
cursor73
kimi-cli72
gemini-cli72
github-copilot72
amp72
cline72
⚠️ This step is NON-NEGOTIABLE. Execute it BEFORE any routing, intake, or code generation.
Check if references/docs.txt exists. If not (or if this is a fresh project), download it immediately:
bash skills/voice-ai-integration/scripts/fetch-docs.sh
This file is the documentation index — all doc lookups depend on it. Do NOT proceed to Step 1 until this file exists or the download has been attempted. If download fails, proceed with local reference docs and fallback URLs.
Use intake to collect kickoff information. Ask only for details the user has not already provided.
Collect only the details needed to remove implementation blockers:
Use a conversational flow:
ConvoAI has a special intake mode:
agent-server-sdk on the server side, and agora-agent-client-toolkit on the client side when the target stack supports it, over building directly from the REST specFor ConvoAI, the user must still explicitly answer or confirm any unresolved Other follow-up value before implementation.
For unresolved ConvoAI fields with defaults, keep them visible and treat omission as an explicit default confirmation. This includes Platform = Web and Backend = Python. If the first consolidated reply is incomplete, ask only a narrow follow-up for the unresolved mandatory blocker.
If the user already gave enough information, do not repeat questions. Produce a lightweight kickoff recap, then continue automatically unless a required detail is still missing.
Use the kickoff summary plus the route table below to select the correct local reference module. If the available information is sufficient, begin implementation using the existing local docs under references/.
| Purpose | Route to |
|---|---|
| New request, vague, or missing details | intake |
| Credentials, AppID, REST auth | general |
| Download SDK, sample project, Token Builder, GitHub repo | Route to the relevant product module |
| Generate Token, token server, AccessToken2, RTC/RTM auth | token-server |
| ConvoAI operation (with details already known) | conversational-ai for SDK/sample-first guidance; use REST docs only as fallback reference |
| RTC SDK integration | rtc |
| RTM messaging / signaling | rtm |
If Step 2 provides enough information for implementation, proceed. If essential information is still missing or the local references are not enough, continue to Step 3.
Use references/doc-fetching.md to fetch more comprehensive documentation. Do this only after Step 2, when the local references are insufficient for the requested implementation.
Research order:
agent-server-sdk, and agora-agent-client-toolkit path before using REST docs as a design sourceOnce Step 3 provides enough information, proceed with implementation.
git clone --depth 1 <url> — GitHub URLs must be repo root only (no branch/subdirectory paths)Weekly Installs
74
Repository
GitHub Stars
6
First Seen
13 days ago
Security Audits
Gen Agent Trust HubPassSocketWarnSnykWarn
Installed on
cursor73
kimi-cli72
gemini-cli72
github-copilot72
amp72
cline72
超能力技能使用指南:AI助手技能调用优先级与工作流程详解
52,100 周安装
| Cloud Recording | cloud-recording |