Shengwang Integration
Workflow
Step 0: Ensure doc index exists (MANDATORY)
⚠️ Execute this BEFORE any routing or code generation.
Check if references/docs.txt already exists. If it does, skip this step entirely.
If it does not exist, download it:
bash skills/voice-ai-integration/scripts/fetch-docs.sh
This downloads a static doc index from doc.shengwang.cn — no user data is sent.
If download fails, proceed with local reference docs and fallback URLs.
Step 1: Route to the correct product module
Progressive disclosure rule: Only read the file that the current step points to. Do not scan the references/ directory or pre-read files that have not been linked from the current step. Each product module's README.md will tell you which files to read next and when. If a file is not referenced by the document you are currently reading, do not open it.
Match the user's request to a product module using the route table. If the match
is clear, route directly — do not ask extra questions.
Route Table
| User intent |
Route to |
| Credentials, AppID, REST auth |
general |
| Generate Token, token server, AccessToken2 |
token-server |
| ConvoAI voice agent work |
conversational-ai |
| RTC SDK integration |
rtc |
| RTM messaging / signaling |
rtm |
| Cloud Recording |
cloud-recording |
| Download SDK, sample project, GitHub repo |
Route to the relevant product module above |
Product Recognition Aid
When the user describes a use case without naming a product, use this to infer the match:
| Product |
What it does |
Typical user says |
| ConvoAI |
AI voice agent (ASR→LLM→TTS over RTC) |
"AI语音", "voice bot", "对话式AI", "AI agent", "AI 客服" |
| RTC SDK |
Real-time audio/video between humans |
"视频通话", "直播", "video call", "live streaming" |
| RTM |
Real-time messaging / signaling |
"聊天", "消息", "chat", "signaling" |
| Cloud Recording |
Record RTC sessions server-side |
"录制", "recording", "存档", "回看" |
| Token generation |
Generate RTC / RTM tokens |
"token", "鉴权", "token server" |
Common Combinations
| Use case |
Products needed |
| AI voice assistant |
ConvoAI (primary) + RTC SDK (client) |
| AI voice assistant + chat history |
ConvoAI + RTC SDK + RTM |
| 1v1 / group video call |
RTC SDK |
| Video call + chat |
RTC SDK + RTM |
| Live streaming with recording |
RTC SDK + Cloud Recording |
| Record AI conversations |
ConvoAI + RTC SDK + Cloud Recording |
| Chat / messaging only |
RTM |
Routing Rules
- Infer obvious context — do not ask if the answer is already clear
- Do not ask product-specific configuration questions (providers, SDK versions, project structure) at this level; let the product module handle those
- If the product is clear but the request mode is ambiguous (quickstart vs debugging vs feature), let the product module decide internally
- If multiple products are needed, route to the primary product first, then address supporting products in order
- ConvoAI has the most detailed internal routing (see its README.md); always delegate ConvoAI-specific decisions to its module
When the product is still unclear
If the route table and recognition aid above are not enough to determine the product:
- Ask only for the missing detail that would change the routing decision
- Ask at most one question at a time
- Prefer natural wording over an interview script
- Once the product is clear, produce a short routing recap and continue:
ZH:
已了解的信息
─────────────────────────────
场景: [use case]
主要产品: [primary product]
配套产品: [supporting products / 无]
─────────────────────────────
EN:
What I have so far
─────────────────────────────
Use case: [use case]
Primary: [primary product]
Supporting: [supporting products / none]
─────────────────────────────
Do not stop for a separate confirmation step — continue to the product module automatically.
Step 2: Let the product module drive implementation
Each product module follows its own workflow. Do not duplicate implementation logic here.
Common pattern across modules:
- Use local reference docs in
references/ first
- Fetch remote docs via doc-fetching.md only when local references are insufficient
- Fallback to web search only after doc fetching has been attempted
Runtime Requirements
bash and curl for local doc-fetch helper scripts
git for sample-repo inspection when the sample-aligned path is chosen
- Network access to
doc.shengwang.cn, doc-mcp.shengwang.cn, and gitee.com
Network behavior:
fetch-docs.sh downloads a static file from doc.shengwang.cn/llms.txt — no user data is sent
fetch-doc-content.sh fetches a single doc page by URI from doc-mcp.shengwang.cn — only the doc URI is sent, no user context
git clone is used only for sample repo inspection from gitee.com — only the repo URL is sent
Credential and service-activation requirements vary by product — see each product module and general/credentials-and-auth.md for details. Never hardcode credentials.
Safety & Consent Rules
- Do not clone external repos into the user's main workspace by default — prefer a temporary path
- Do not modify an existing user project until the user explicitly asks for code generation
- Do not write secrets into project files — prefer env vars and example placeholders
- Before performing network fetches or repo clones, state what will be downloaded
- If a required dependency or credential is missing, stop and explain the blocker
Download Rules
- Use
git clone --depth 1 <url> with HTTPS repo root URLs only
- On any download failure: report the error, provide the URL for manual download, never silently skip
Links
1---
2name: voice-ai-integration
3description: |
4 Integrate Shengwang products: ConvoAI voice agents, RTC audio/video,
5 RTM messaging, Cloud Recording, and token generation. Use when the user
6 mentions Shengwang, 声网, ConvoAI, RTC, RTM, voice agent, AI agent,
7 video call, live streaming, recording, token, or any Shengwang product task.
8license: MIT
9metadata:
10 source: https://skillmd.com/skills/shengwang-community/voice-ai-integration
11 author: shengwang
12 version: "1.0.0"
13---
14
15# Shengwang Integration
16
17## Workflow
18
19### Step 0: Ensure doc index exists (MANDATORY)
20
21> **⚠️ Execute this BEFORE any routing or code generation.**
22
23Check if `references/docs.txt` already exists. If it does, skip this step entirely.
24If it does not exist, download it:
25```bash
26bash skills/voice-ai-integration/scripts/fetch-docs.sh
27```
28This downloads a static doc index from `doc.shengwang.cn` — no user data is sent.
29If download fails, proceed with local reference docs and fallback URLs.
30
31### Step 1: Route to the correct product module
32
33> **Progressive disclosure rule:** Only read the file that the current step points to. Do not scan the `references/` directory or pre-read files that have not been linked from the current step. Each product module's README.md will tell you which files to read next and when. If a file is not referenced by the document you are currently reading, do not open it.
34
35Match the user's request to a product module using the route table. If the match
36is clear, route directly — do not ask extra questions.
37
38#### Route Table
39
40| User intent | Route to |
41|-------------|----------|
42| Credentials, AppID, REST auth | [general](references/general/credentials-and-auth.md) |
43| Generate Token, token server, AccessToken2 | [token-server](references/token-server/README.md) |
44| ConvoAI voice agent work | [conversational-ai](references/conversational-ai/README.md) |
45| RTC SDK integration | [rtc](references/rtc/README.md) |
46| RTM messaging / signaling | [rtm](references/rtm/README.md) |
47| Cloud Recording | [cloud-recording](references/cloud-recording/README.md) |
48| Download SDK, sample project, GitHub repo | Route to the relevant product module above |
49
50#### Product Recognition Aid
51
52When the user describes a use case without naming a product, use this to infer the match:
53
54| Product | What it does | Typical user says |
55|---------|-------------|-------------------|
56| ConvoAI | AI voice agent (ASR→LLM→TTS over RTC) | "AI语音", "voice bot", "对话式AI", "AI agent", "AI 客服" |
57| RTC SDK | Real-time audio/video between humans | "视频通话", "直播", "video call", "live streaming" |
58| RTM | Real-time messaging / signaling | "聊天", "消息", "chat", "signaling" |
59| Cloud Recording | Record RTC sessions server-side | "录制", "recording", "存档", "回看" |
60| Token generation | Generate RTC / RTM tokens | "token", "鉴权", "token server" |
61
62#### Common Combinations
63
64| Use case | Products needed |
65|----------|----------------|
66| AI voice assistant | ConvoAI (primary) + RTC SDK (client) |
67| AI voice assistant + chat history | ConvoAI + RTC SDK + RTM |
68| 1v1 / group video call | RTC SDK |
69| Video call + chat | RTC SDK + RTM |
70| Live streaming with recording | RTC SDK + Cloud Recording |
71| Record AI conversations | ConvoAI + RTC SDK + Cloud Recording |
72| Chat / messaging only | RTM |
73
74#### Routing Rules
75
76- Infer obvious context — do not ask if the answer is already clear
77- Do not ask product-specific configuration questions (providers, SDK versions, project structure) at this level; let the product module handle those
78- If the product is clear but the request mode is ambiguous (quickstart vs debugging vs feature), let the product module decide internally
79- If multiple products are needed, route to the primary product first, then address supporting products in order
80- ConvoAI has the most detailed internal routing (see its README.md); always delegate ConvoAI-specific decisions to its module
81
82#### When the product is still unclear
83
84If the route table and recognition aid above are not enough to determine the product:
85
861. Ask only for the missing detail that would change the routing decision
872. Ask at most one question at a time
883. Prefer natural wording over an interview script
894. Once the product is clear, produce a short routing recap and continue:
90
91**ZH:**
92```text
93已了解的信息
94─────────────────────────────
95场景: [use case]
96主要产品: [primary product]
97配套产品: [supporting products / 无]
98─────────────────────────────
99```
100
101**EN:**
102```text
103What I have so far
104─────────────────────────────
105Use case: [use case]
106Primary: [primary product]
107Supporting: [supporting products / none]
108─────────────────────────────
109```
110
111Do not stop for a separate confirmation step — continue to the product module automatically.
112
113### Step 2: Let the product module drive implementation
114
115Each product module follows its own workflow. Do not duplicate implementation logic here.
116
117Common pattern across modules:
1181. Use local reference docs in `references/` first
1192. Fetch remote docs via [doc-fetching.md](references/doc-fetching.md) only when local references are insufficient
1203. Fallback to web search only after doc fetching has been attempted
121
122## Runtime Requirements
123
124- `bash` and `curl` for local doc-fetch helper scripts
125- `git` for sample-repo inspection when the sample-aligned path is chosen
126- Network access to `doc.shengwang.cn`, `doc-mcp.shengwang.cn`, and `gitee.com`
127
128Network behavior:
129- `fetch-docs.sh` downloads a static file from `doc.shengwang.cn/llms.txt` — no user data is sent
130- `fetch-doc-content.sh` fetches a single doc page by URI from `doc-mcp.shengwang.cn` — only the doc URI is sent, no user context
131- `git clone` is used only for sample repo inspection from `gitee.com` — only the repo URL is sent
132
133Credential and service-activation requirements vary by product — see each product module and [general/credentials-and-auth.md](references/general/credentials-and-auth.md) for details. Never hardcode credentials.
134
135## Safety & Consent Rules
136
137- Do not clone external repos into the user's main workspace by default — prefer a temporary path
138- Do not modify an existing user project until the user explicitly asks for code generation
139- Do not write secrets into project files — prefer env vars and example placeholders
140- Before performing network fetches or repo clones, state what will be downloaded
141- If a required dependency or credential is missing, stop and explain the blocker
142
143## Download Rules
144
145- Use `git clone --depth 1 <url>` with HTTPS repo root URLs only
146- On any download failure: report the error, provide the URL for manual download, never silently skip
147
148## Links
149
150- Console: https://console.shengwang.cn/
151- Docs (CN): https://doc.shengwang.cn/
152- GitHub: https://github.com/Shengwang-Community