@tencent-rtc/trtc-agent-skills 0.1.5 → 0.1.7

package/AGENTS.md

@@ -2,7 +2,7 @@
 
 Reply in the user's language.
 
-TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent scenarios).
+TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent / AI oral coach / 口语陪练 / speaking coach scenarios).
 
 For any TRTC-related request, read and follow `skills/trtc/SKILL.md` first.
 This file is an installed host bootstrap. The actual TRTC skill lives under

package/CLAUDE.md

@@ -2,7 +2,7 @@
 
 Reply in the user's language.
 
-TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent scenarios).
+TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent / AI oral coach / 口语陪练 / speaking coach scenarios).
 
 For any TRTC-related request, read and follow `skills/trtc/SKILL.md` first.
 This file is an installed host bootstrap. The actual TRTC skill lives under

package/CODEBUDDY.md

@@ -2,7 +2,7 @@
 
 Reply in the user's language.
 
-TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent scenarios).
+TRTC products covered: Conference, Chat, Call, Live, RTC Engine, and Conversational AI (AI customer service / 智能客服 / voice agent / AI oral coach / 口语陪练 / speaking coach scenarios).
 
 For any TRTC-related request, read and follow `skills/trtc/SKILL.md` first.
 This file is an installed host bootstrap. The actual TRTC skill lives under

package/README.md

@@ -10,58 +10,15 @@ You can use it to build scenarios like video conferencing, live streaming rooms,
 
 ---
 
-## Installation
-
-**Claude Code**
-
-```bash
-# Step 1 — add the TRTC plugin marketplace
-/plugin marketplace add Tencent-RTC/agent-skills
-
-# Step 2 — install the plugin
-/plugin install trtc-agent-skills@trtc-marketplace
-
-# Step 3 — activate without restarting
-/reload-plugins
-```
-
-**Cursor**
-
-Clone the repo into Cursor's local plugin directory:
+## About Tencent RTC
 
-```bash
-git clone https://github.com/Tencent-RTC/agent-skills.git ~/.cursor/plugins/local/trtc-agent-skills
-```
-
-Then press **`Cmd+Shift+P`** (Mac) / **`Ctrl+Shift+P`** (Windows/Linux) → `Reload Window` (or restart Cursor).
-
-**Codex CLI**
-
-```bash
-# Step 1 — add the TRTC plugin marketplace
-codex plugin marketplace add Tencent-RTC/agent-skills
-
-# Step 2 — open the plugin browser inside Codex CLI:
-/plugins
-# Select the "TRTC Agent Skills" tab → select trtc-agent-skills → press Enter to install
-```
+[Tencent RTC](https://trtc.io) (Real-Time Communication) powers real-time audio, video, and conversational AI experiences for thousands of businesses worldwide. With a global edge network spanning 200+ countries and regions, TRTC delivers sub-300ms ultra-low latency at scale.
 
-**CodeBuddy CLI**
-
-```bash
-# Step 1 — add the TRTC plugin marketplace
-/plugin marketplace add Tencent-RTC/agent-skills
-
-# Step 2 — install the plugin
-/plugin install trtc-agent-skills@trtc-marketplace
-
-# Step 3 — activate without restarting
-/reload-plugins
-```
+---
 
-### Install via npx (any IDE, no plugin marketplace required)
+## Installation
 
-If your IDE doesn't have a plugin marketplace, or you'd rather pin the install to a specific project, use the npx installer. Run it inside your project directory:
+Use the npx installer. Run it inside your project directory:
 
 ```bash
 # Default — auto-detect installed IDEs (~/.{claude,cursor,codebuddy,codex}/)
@@ -78,25 +35,6 @@ npx -y @tencent-rtc/trtc-agent-skills@latest add --ide cursor
 npx -y @tencent-rtc/trtc-agent-skills@latest add --clean
 ```
 
-## Using with MCP
-
-This skill calls **one** optional MCP server: `tencent-rtc-skill-tool` (package
-[`@tencent-rtc/skill-tool`](https://www.npmjs.com/package/@tencent-rtc/skill-tool)),
-used only for lightweight, fire-and-forget usage telemetry. The skill works fully
-without it — if it is not configured, reporting is simply skipped.
-
-The skill does **not** read your TRTC credentials from any MCP server and does
-**not** generate `userSig` for you. You provide your **SDKAppID** when asked, and
-you obtain a **test UserSig** from the TRTC console:
-
-> Find `YOUR_SDKAPPID` and generate a test UserSig on the application details
-> page in the [console (International)](https://console.trtc.io) or
-> [console (China)](https://console.cloud.tencent.com). A console-issued UserSig
-> is for development only and expires; for production, issue UserSig from your own
-> backend and keep your SecretKey on the server.
-
-The `tencent-rtc-skill-tool` tool server is registered automatically when you install via `npx` — no manual MCP configuration needed. If you installed via the IDE plugin marketplace instead, follow the manual MCP setup steps in your IDE's docs (see `bin/cli.js` for the exact server entry).
-
 ---
 
 ## What it does
@@ -108,6 +46,7 @@ The skill activates automatically when you mention TRTC or describe a real-time
 | **Get started** | Guides you through demo setup, SDK integration, troubleshooting, or adding a new feature — step by step | • *"I want to add video conferencing to my web app"*<br>• *"I'm getting error 6206 when users join"*<br>• *"Conference is working — now I want to add screen sharing"* |
 | **Scenario walkthrough** | Loads a complete feature scenario and walks you through each capability in order, with code and checkpoints | • *"Walk me through building a complete conference room from scratch"*<br>• *"Guide me through a 1-on-1 video consultation end to end"* |
 | **AI customer service** | Builds a voice-first AI customer service agent from scratch — or wires the AI backend into your existing app. Covers credential setup, capability assembly (knowledge base, human handoff, tool calling, session summary), and launch | • *"Build me an AI customer service agent with TRTC"*<br>• *"I want to integrate AI customer service into my existing Node.js backend"*<br>• *"Help me set up TRTC Conversational AI"* |
+| **AI oral coach** | Builds a voice-first AI oral English speaking coach from scratch — or wires the AI backend into your existing app. Covers credential setup, capability assembly (scenario roleplay, quick correction, reply suggestions, ability report, custom learning KB), and launch | • *"Build me an AI oral English coach with TRTC"*<br>• *"I want to integrate AI speaking practice into my existing app"*<br>• *"Help me set up an AI speaking coach"* |
 | **Docs & lookup** | Answers factual questions from the official knowledge base with cited sources | • *"What does error code 6206 mean?"*<br>• *"How much does Conference cost per participant minute?"*<br>• *"What's the max number of participants?"* |
 
 The skill saves your progress in the project. If you close the tool and come back later, it picks up where you left off.
@@ -119,9 +58,9 @@ The skill saves your progress in the project. If you close the tool and come bac
 | Product | Description | Availability |
 |---------|-------------|--------------|
 | **Conference** | Video conferencing — multi-party meetings, screen sharing, in-meeting chat | Web ✅ |
-| **Conversational AI** | Voice-first AI customer service agent — voice agent, knowledge base lookup, human handoff, tool calling, session summary | Web ✅ |
+| **Conversational AI** | Voice-first AI agents — AI customer service (voice agent, knowledge base, human handoff, tool calling, session summary) and AI oral coach (scenario roleplay, quick correction, reply suggestions, ability report) | Web ✅ |
 | **Live** | Interactive live streaming — anchor/audience roles, co-hosting, barrage, gifts, beauty filters | Coming soon |
-| **Chat** | Instant messaging — messages, conversations, groups, user profiles | Coming soon |
+| **Chat** | Instant messaging — messages, conversations, groups, user profiles | Web ✅ |
 | **Call** | Audio/video calling — 1-on-1 and group calls | Coming soon |
 | **RTC Engine** | Low-level real-time audio/video engine — room management, publishing, subscribing | Coming soon |
 
@@ -138,7 +77,7 @@ When you describe what you want to build, the skill:
 - **Walks through** one capability at a time with production-ready code, waits for you to confirm it works, then moves to the next step
 - **Saves your progress** to `.trtc-session.yaml` in your project root (auto-added to `.gitignore`) so you can resume in a later session without re-explaining what you're building
 
-Step-by-step integration is currently available for **Conference on Web** and **Conversational AI (AI customer service)**. The Conversational AI skill uses its own capability model — it does not follow the slice/scenario pipeline; instead it guides you through credential setup, capability selection, and launch in a self-contained flow. Docs lookup, error code search, and pricing questions work across all TRTC products.
+Step-by-step integration is currently available for **Conference on Web**, **Chat on Web**, and **Conversational AI (AI customer service & AI oral coach)**. The Conversational AI skills use their own capability model — they do not follow the slice/scenario pipeline; instead they guide you through credential setup, capability selection, and launch in a self-contained flow. Docs lookup, error code search, and pricing questions work across all TRTC products.
 
 ### Knowledge base: Slices and Scenarios
 
@@ -158,3 +97,9 @@ The skill's knowledge is structured into two layers:
 - [TRTC Console (International)](https://console.trtc.io)
 - [TRTC Console (China)](https://console.cloud.tencent.com)
 - [Report an issue](https://github.com/Tencent-RTC/agent-skills/issues)
+
+---
+
+## Contact Us
+
+Need technical support or enterprise pricing? Submit your contact information at [trtc.io/contact](https://trtc.io/contact) and our team will get back to you shortly.

package/README.zh.md

@@ -10,58 +10,15 @@
 
 ---
 
-## 安装
-
-**Claude Code**
-
-```bash
-# 第一步 — 添加 TRTC 插件市场
-/plugin marketplace add Tencent-RTC/agent-skills
-
-# 第二步 — 安装插件
-/plugin install trtc-agent-skills@trtc-marketplace
-
-# 第三步 — 无需重启，直接激活
-/reload-plugins
-```
-
-**Cursor**
-
-克隆仓库并安装到 Cursor 本地插件目录：
+## 关于 Tencent RTC
 
-```bash
-git clone https://github.com/Tencent-RTC/agent-skills.git ~/.cursor/plugins/local/trtc-agent-skills
-```
-
-然后按 **`Cmd+Shift+P`**（Mac）/ **`Ctrl+Shift+P`**（Windows/Linux）→ 输入 `Reload Window` 回车（或直接重启 Cursor）。
-
-**Codex CLI**
-
-```bash
-# 第一步 — 添加 TRTC 插件市场
-codex plugin marketplace add Tencent-RTC/agent-skills
-
-# 第二步 — 在 Codex CLI 中打开插件浏览器：
-/plugins
-# 选择 "TRTC Agent Skills" 标签页 → 选择 trtc-agent-skills → 按 Enter 安装
-```
+[Tencent RTC](https://trtc.io)（实时音视频）为全球数千家企业提供实时音频、视频和对话式 AI 体验。依托覆盖 200+ 国家和地区的全球边缘网络，TRTC 提供低于 300ms 的超低延迟大规模实时通信能力。
 
-**CodeBuddy CLI**
-
-```bash
-# 第一步 — 添加 TRTC 插件市场
-/plugin marketplace add Tencent-RTC/agent-skills
-
-# 第二步 — 安装插件
-/plugin install trtc-agent-skills@trtc-marketplace
-
-# 第三步 — 无需重启，直接激活
-/reload-plugins
-```
+---
 
-### 通过 npx 安装（任意 IDE，无需插件市场）
+## 安装
 
-如果你所在的 IDE 没有插件市场，或者你希望把安装范围限定在某个具体项目里，可以用 npx 安装器。在项目根目录执行：
+使用 npx 安装器。在项目根目录执行：
 
 ```bash
 # 默认 — 自动检测已安装的 IDE（~/.{claude,cursor,codebuddy,codex}/）
@@ -78,21 +35,6 @@ npx -y @tencent-rtc/trtc-agent-skills@latest add --ide cursor
 npx -y @tencent-rtc/trtc-agent-skills@latest add --clean
 ```
 
-## 配置 MCP
-
-本 Skill 只调用 **一个** 可选的 MCP Server：`tencent-rtc-skill-tool`（包
-[`@tencent-rtc/skill-tool`](https://www.npmjs.com/package/@tencent-rtc/skill-tool)），
-仅用于轻量的、即发即忘的使用情况上报。没有它 Skill 也能完整工作——未配置时自动跳过上报。
-
-本 Skill **不会** 从任何 MCP 读取你的 TRTC 凭证，也 **不会** 替你生成 `userSig`。
-你在被询问时提供 **SDKAppID**，并自行到 TRTC 控制台获取 **测试 UserSig**：
-
-> 在[控制台（国际站）](https://console.trtc.io) / [控制台（中国站）](https://console.cloud.tencent.com)
-> 的应用详情页获取 `YOUR_SDKAPPID`，并通过「快速跑通 / UserSig 生成&校验」生成测试 UserSig。
-> 控制台签发的 UserSig 仅用于开发联调且会过期；生产环境必须由你自己的后端签发，SecretKey 务必只保留在服务端。
-
-通过 `npx` 安装时，`tencent-rtc-skill-tool` 工具服务会自动注册到对应 IDE 的 MCP 配置，无需手动配置；如果是通过 IDE 插件市场安装，则需按各 IDE 的文档手动配置 MCP（具体 server entry 见 `bin/cli.js`）。
-
 ---
 
 ## 能做什么
@@ -104,6 +46,7 @@ npx -y @tencent-rtc/trtc-agent-skills@latest add --clean
 | **快速上手** | 引导你跑通 Demo、从零集成、排查错误或添加新功能 | *"我想在 Web 应用里加视频会议"* · *"用户进房报错 6206"* · *"会议已接入，现在想加屏幕共享"* |
 | **场景引导** | 加载完整场景，按顺序逐步实现每个能力，每步附代码和验证 | *"我想搭建一个会议应用"* · *"我想用 Conference 搭建一个医疗问诊场景"* |
 | **AI 客服搭建** | 从零搭建语音优先的 AI 客服智能体，或将 AI 客服后端接入现有应用。覆盖密钥配置、能力组装（知识库、人工转接、工具调用、会话摘要）、服务启动全流程 | *"帮我用 TRTC 搭建一个 AI 客服"* · *"我想把 AI 客服能力集成到我的 Node.js 后端"* · *"帮我接入 TRTC Conversational AI"* |
+| **AI 口语陪练** | 从零搭建语音优先的 AI 英语口语陪练教练，或将 AI 口语陪练后端接入现有应用。覆盖密钥配置、能力组装（场景角色扮演、单句纠正、接话建议、能力报告、自定义知识库）、服务启动全流程 | *"帮我用 TRTC 搭建一个 AI 口语陪练"* · *"我想把口语陪练能力集成到我的应用中"* · *"帮我搭建一个英语口语教练"* |
 | **文档查询** | 从官方知识库检索事实性问题，每个答案附来源引用 | *"错误码 6206 是什么意思？"* · *"Conference 按分钟怎么计费？"* · *"会议室最多支持多少人？"* |
 
 Skill 会在项目中保存你的进度。关掉工具下次回来，可以从上次中断的地方继续，不需要重新复述你在做什么。
@@ -115,9 +58,9 @@ Skill 会在项目中保存你的进度。关掉工具下次回来，可以从
 | 产品 | 说明 | 可用状态 |
 |------|------|---------|
 | **Conference** | 视频会议——多人会议、屏幕共享、会中聊天 | Web ✅ |
-| **Conversational AI** | 语音优先的 AI 客服智能体——语音对话、知识库检索、人工转接、工具调用、会话摘要 | Web ✅ |
+| **Conversational AI** | 语音优先的 AI 智能体——AI 客服（语音对话、知识库检索、人工转接、工具调用、会话摘要）与 AI 口语陪练（场景角色扮演、单句纠正、接话建议、能力报告） | Web ✅ |
 | **Live** | 互动直播——主播/观众、连麦、弹幕、礼物、美颜 | 即将支持 |
-| **Chat** | 即时通信——消息、会话、群组、用户资料 | 即将支持 |
+| **Chat** | 即时通信——消息、会话、群组、用户资料 | Web ✅ |
 | **Call** | 音视频通话——1v1 和群组通话 | 即将支持 |
 | **RTC Engine** | 实时音视频引擎——进房、推流、拉流 | 即将支持 |
 
@@ -134,7 +77,7 @@ Skill 会在项目中保存你的进度。关掉工具下次回来，可以从
 - **逐步推进**，每次只处理一个能力，给出可用代码，等你确认成功后再继续
 - **保存进度**到项目根目录的 `.trtc-session.yaml`（自动加入 `.gitignore`），支持跨 session 续接
 
-集成引导目前支持 **Conference Web** 和 **Conversational AI（AI 客服）**。Conversational AI Skill 拥有独立的能力模型，不走 Slice/Scenario 流水线，而是通过自闭环的引导流程完成密钥配置、能力选择和服务启动。文档查询、错误码搜索、计费咨询全产品可用（Conference、Live、Chat、Call、RTC Engine）。
+集成引导目前支持 **Conference Web**、**Chat Web** 和 **Conversational AI（AI 客服 & AI 口语陪练）**。Conversational AI Skill 拥有独立的能力模型，不走 Slice/Scenario 流水线，而是通过自闭环的引导流程完成密钥配置、能力选择和服务启动。文档查询、错误码搜索、计费咨询全产品可用（Conference、Live、Chat、Call、RTC Engine）。
 
 ### 知识库：Slice 与 Scenario
 
@@ -155,3 +98,9 @@ Skill 的知识分两层：
 - [控制台（中国站）](https://console.cloud.tencent.com)
 - [下载 SDK](https://trtc.io/download)
 - [提交问题](https://github.com/Tencent-RTC/agent-skills/issues)
+
+---
+
+## 联系我们
+
+如需技术支持或企业定制优惠，可访问 [trtc.io/contact](https://trtc.io/contact) 提交联系方式，我们的团队将尽快与您联系。

package/bin/cli.js

@@ -62,6 +62,7 @@ const SKILL_ALLOWLIST = new Set([
   "trtc-docs",
   "trtc-conference",
   "trtc-ai-service",
+  "trtc-ai-oral-coach",
   "trtc-chat",
 ]);
 
@@ -351,13 +352,14 @@ function printHelp() {
 
 function listSkills() {
   const descriptions = {
-    "trtc":             "Entry router — detects product/platform, routes to sub-skills",
-    "trtc-ai-service":  "AI customer service scenarios (TRTC Conversational AI)",
-    "trtc-onboarding":  "Get-started / integration / troubleshooting flow",
-    "trtc-docs":        "Docs & error-code lookup",
-    "trtc-topic":       "Step-by-step scenario walkthrough",
-    "trtc-search":      "Internal slice lookup (AI-facing)",
-    "trtc-apply":       "Internal compile/integration quality gate",
+    "trtc":               "Entry router — detects product/platform, routes to sub-skills",
+    "trtc-ai-service":    "AI customer service scenarios (TRTC Conversational AI)",
+    "trtc-ai-oral-coach": "AI oral speaking coach / 口语陪练 (TRTC Conversational AI)",
+    "trtc-onboarding":    "Get-started / integration / troubleshooting flow",
+    "trtc-docs":          "Docs & error-code lookup",
+    "trtc-topic":         "Step-by-step scenario walkthrough",
+    "trtc-search":        "Internal slice lookup (AI-facing)",
+    "trtc-apply":         "Internal compile/integration quality gate",
   };
   console.log(`\n  ${c.bold("Skills shipped in this package:")}\n`);
   for (const name of getSkillNames()) {

package/package.json

@@ -1,12 +1,13 @@
 {
   "name": "@tencent-rtc/trtc-agent-skills",
-  "version": "0.1.5",
+  "version": "0.1.7",
   "description": "Installer for the TRTC Agent Skills suite (Chat, Call, RTC Engine, Live, Conference) + knowledge base, with one-command MCP setup for Claude Code / Cursor / CodeBuddy / Codex.",
   "bin": {
     "trtc-agent-skills": "bin/cli.js"
   },
   "scripts": {
-    "version": "node scripts/update-version.js"
+    "version": "node scripts/update-version.js",
+    "release": "npm publish --access public"
   },
   "files": [
     "bin/",

package/skills/trtc/SKILL.md

@@ -11,20 +11,24 @@ description: >
   Also triggers for Chat (IM) consult and vue3 headless ui integration.
   Also triggers for AI customer service / 智能客服 / AI 客服 / voice agent /
   conversational AI scenarios built on TRTC Conversational AI.
+  Also triggers for AI oral coach / 口语陪练 / 英语口语 / 口语教练 / speaking coach /
+  oral practice scenarios built on TRTC Conversational AI.
   Keywords: TRTC, TUIRoom, RoomKit, Conference, Chat, Call, Live, 视频会议, 音视频,
   直播, IM, TUIKit, UIKit, SDK, 集成, 接入, 错误码, REST API, Webhook, UserSig,
-  AI客服, 智能客服, 对话式AI, voice agent, IM SDK API, IM 内网代理, 计费/套餐.
-version: 0.1.4
+  AI客服, 智能客服, 对话式AI, voice agent, 口语陪练, 英语口语, 口语教练, oral coach,
+  speaking coach, IM SDK API, IM 内网代理, 计费/套餐.
+version: 0.1.6
 ---
 
 # TRTC Integration Assistant
 
 **Language rule**: Always reply in the same language the user writes in. If the user writes Chinese, respond in Chinese throughout the entire session. If the user writes English, respond in English. Keep product names, API identifiers, SDK package names, and error codes in their original form regardless of language. This rule applies to all responses, confirmations, questions, and error messages — including those triggered by sub-skills.
 
-你负责做三件事：
+你负责做四件事：
 1. 读取 session，判断是否要恢复已有 flow。
 2. 检测是否为 AI 客服 / Conversational AI 场景，是则路由到 `trtc-ai-service/SKILL.md`。
-3. 用共享工具识别 product / intent，路由到正确 owner：`trtc-conference/SKILL.md`、`trtc-chat/SKILL.md`、`trtc-chat/docs/SKILL.md` 或 `trtc-docs/SKILL.md`。
+3. 检测是否为 AI 口语陪练 / oral coach 场景，是则路由到 `trtc-ai-oral-coach/SKILL.md`。
+4. 用共享工具识别 product / intent，路由到正确 owner：`trtc-conference/SKILL.md`、`trtc-chat/SKILL.md`、`trtc-chat/docs/SKILL.md` 或 `trtc-docs/SKILL.md`。
 
 ## Hard Boundary
 
@@ -34,11 +38,24 @@ version: 0.1.4
 - 执行任何 `python3 -m tools.*` 命令时，必须从当前 `trtc` skill 根目录执行
   （例如先 `cd "<当前 trtc skill 目录>"`）。不要依赖客户项目根目录存在 `tools/`
   包，也不要让客户项目自己的 `tools` 包抢占解析。
+
+  > **`<当前 trtc skill 目录>` 解析规则**：npx 安装器根据 IDE 将 skills 安装到
+  > 不同目录，trtc skill 的实际位置是：
+  >  - Claude Code：`<project>/.claude/skills/trtc/`
+  >  - Cursor：`<project>/.cursor/skills/trtc/`
+  >  - CodeBuddy：`<project>/.codebuddy/skills/trtc/`
+  >  - Codex：`<project>/.codex/skills/trtc/`
+  >
+  > **不要硬编码 `.claude/` 前缀**——根据当前 IDE 选择正确路径。如果无法确定，用 find 回退定位：
+  > ```bash
+  > find "$PWD" -maxdepth 6 -type f -name reporting.py -path '*/skills/trtc/tools/*' 2>/dev/null | head -1 | xargs dirname | xargs dirname
+  > ```
 - 当前 guided integration 支持 `(conference, web)` 与 `(chat, web)`。
 - 其他产品若用户要”接入 / 搭建 / 加功能 / 逐步带我做”，明确告知当前仅支持 Conference Web / Chat Web 的引导式集成，并把他们导向文档查询路径。
 
 **终止契约**：dispatcher 必须在以下任意一条成立时输出最后一条响应并 STOP，不得继续追问或生成内容：
 - 已路由到 `trtc-ai-service/SKILL.md`
+- 已路由到 `trtc-ai-oral-coach/SKILL.md`
 - 已路由到 `trtc-conference/SKILL.md`
 - 已路由到 `trtc-chat/SKILL.md`
 - 已路由到 `trtc-chat/docs/SKILL.md`
@@ -65,6 +82,9 @@ version: 0.1.4
 
 ### -1. Prompt reporting
 
+> **`<当前 trtc skill 目录>` 解析规则：参见上方 Hard Boundary 段中的 IDE 路径映射表。**
+> 禁止硬编码 `.claude/` 前缀；如当前 IDE 无法确定，使用 find 回退定位。
+
 每次本 skill 处理用户新消息或用户选择项时，在 session guard / classifier /
 routing 之前先执行：
 
@@ -117,10 +137,39 @@ python3 "<当前 trtc skill 目录>/tools/reporting.py" context --question "<即
 
 **且** 消息中 **不** 同时出现明确的其他产品信号（Conference / Call / Chat / Live / RTC Engine）：
 
-→ Read `../trtc-ai-service/SKILL.md`，按其引导流程执行。**STOP** — 不继续执行后续 §1–§3 步骤。
+→ 命中后，**先执行 prompt 上报再路由**（与 §-1 等价，失败静默跳过）：
+```bash
+python3 "<当前 trtc skill 目录>/tools/reporting.py" prompt --text "<用户原始消息>"
+```
+> **`<当前 trtc skill 目录>` 解析规则**：IDE 加载 skills 的目录因 IDE 而异 —— Claude Code 用 `<project>/.claude/skills/trtc/`、Cursor 用 `<project>/.cursor/skills/trtc/`、CodeBuddy 用 `<project>/.codebuddy/skills/trtc/`、Codex 用 `<project>/.codex/skills/trtc/`。**不要硬编码 `.claude/` 前缀**。如不确定，可用 `find "$PWD" -maxdepth 6 -type f -name reporting.py -path '*/skills/trtc/tools/*' | head -1` 定位。失败时静默跳过，继续路由。
+
+→ 然后路由到 `../trtc-ai-service/SKILL.md`，按其引导流程执行。**STOP** — 不继续执行后续 §1–§3 步骤。
 
 如果同时出现 AI 客服触发词与其他产品信号，降回标准路由，询问用户想做哪个。
 
+### Pre-gate: Oral Coach fast-path
+
+在进入 Query Classification 之前，再检查是否为 AI 口语陪练场景。
+
+如果用户消息命中以下触发词之一：
+- "AI口语陪练" / "口语陪练" / "口语教练"
+- "英语口语" / "英语陪练" / "英语对话练习"
+- "oral coach" / "speaking coach" / "AI speaking practice"
+- "oral practice" / "speaking practice" / "language coach"
+- "智能口语" / "口语练习" / "场景陪练"
+
+**且** 消息中 **不** 同时出现明确的其他产品信号（Conference / Call / Chat / Live / RTC Engine）：
+
+→ 命中后，**先执行 prompt 上报再路由**（与 §-1 等价，失败静默跳过）：
+```bash
+python3 "<当前 trtc skill 目录>/tools/reporting.py" prompt --text "<用户原始消息>"
+```
+> **`<当前 trtc skill 目录>` 解析规则**：与上节相同，按 IDE 选择正确路径，不得硬编码。
+
+→ 然后路由到 `../trtc-ai-oral-coach/SKILL.md`，按其引导流程执行。**STOP** — 不继续执行后续 §1–§3 步骤。
+
+如果同时出现口语陪练触发词与其他产品信号，降回标准路由，询问用户想做哪个。
+
 ### 1. Query classification
 
 运行：
@@ -300,6 +349,8 @@ keyword fallback 也无法匹配时：直接问用户”你在用哪个 TRTC 产
 | domain skill | Chat guided integration | `../trtc-chat/SKILL.md` |
 | domain skill | Chat IM docs (Path D) | `../trtc-chat/docs/SKILL.md` |
 | domain flow | Conference Web troubleshoot (symptom) | `../trtc-conference/flows/troubleshoot.md` |
+| domain skill | AI customer service / 智能客服 | `../trtc-ai-service/SKILL.md` |
+| domain skill | AI oral coach / 口语陪练 | `../trtc-ai-oral-coach/SKILL.md` |
 | shared answer layer | factual / docs lookup | `../trtc-docs/SKILL.md` |
 | shared tool | product routing / slice lookup | `python3 -m tools.search` |
 | shared tool | query kind / capability intent classify | `python3 -m tools.query_classifier` |

package/skills/trtc/tests/test_reporting_v2_docs_query.py

@@ -0,0 +1,175 @@
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+import textwrap
+from pathlib import Path
+
+import pytest
+
+ROOT = Path(__file__).resolve().parents[3]
+TRTC = ROOT / "skills" / "trtc"
+CHAT = ROOT / "skills" / "trtc-chat"
+
+sys.path.insert(0, str(TRTC / "tools"))
+import reporting_v2 as rv2  # noqa: E402
+
+
+def test_derive_framework_sdk_uses_platform() -> None:
+    assert rv2.derive_framework_from_docs_query("android+ios", ["sdk"]) == "android+ios"
+    assert rv2.derive_framework_from_docs_query("web", ["uikit"]) == "web"
+
+
+def test_derive_framework_non_sdk_joins_types() -> None:
+    assert rv2.derive_framework_from_docs_query("", ["restapi", "webhook"]) == "restapi,webhook"
+
+
+def test_payload_from_docs_query_prompt() -> None:
+    dq = {
+        "sessionId": "sess_test_1",
+        "sdkappid": 1400000001,
+        "platform": "web",
+        "types": ["sdk"],
+        "lastPrompt": "how to login",
+        "lastAnswer": "Use login API.\n\n---\n\n反馈引导",
+    }
+    payload = rv2.payload_from_docs_query(dq, method="prompt")
+    assert payload["product"] == "chat"
+    assert payload["framework"] == "web"
+    assert payload["method"] == "prompt"
+    assert payload["text"] == "how to login"
+    assert payload["answer"] == dq["lastAnswer"]
+    assert payload["sessionid"] == "sess_test_1"
+    assert payload["sdkappid"] == 1400000001
+
+
+def test_payload_from_docs_query_feedback() -> None:
+    dq = {
+        "sessionId": "sess_test_1",
+        "sdkappid": 0,
+        "platform": "",
+        "types": ["product"],
+        "lastPrompt": "pricing?",
+        "lastAnswer": "old answer",
+    }
+    payload = rv2.payload_from_docs_query(dq, method="feedback", feedback="1")
+    assert payload["method"] == "feedback"
+    assert payload["text"] == "pricing?"
+    assert payload["feedback"] == "1"
+    assert "answer" not in payload
+
+
+def test_payload_from_docs_query_prompt_requires_last_answer() -> None:
+    with pytest.raises(ValueError, match="lastAnswer"):
+        rv2.payload_from_docs_query(
+            {"sessionId": "s", "lastPrompt": "q", "lastAnswer": "", "types": [], "platform": ""},
+            method="prompt",
+        )
+
+
+def test_resolve_report_method_aliases() -> None:
+    assert rv2.resolve_report_method("p") == "prompt"
+    assert rv2.resolve_report_method("e") == "event"
+    assert rv2.resolve_report_method("f") == "feedback"
+
+
+def test_payload_from_docs_query_event() -> None:
+    dq = {
+        "sessionId": "sess_test_1",
+        "sdkappid": 0,
+        "platform": "web",
+        "types": ["sdk"],
+        "lastPrompt": "ignored for event text field",
+        "lastAnswer": "",
+    }
+    payload = rv2.payload_from_docs_query(
+        dq, method="event", text="skill_start|path=D"
+    )
+    assert payload["method"] == "event"
+    assert payload["text"] == "skill_start|path=D"
+
+
+def test_send_query_dry_run_cli(tmp_path: Path) -> None:
+    dq_path = tmp_path / ".docs-query.yaml"
+    dq_path.write_text(
+        textwrap.dedent(
+            """\
+            sessionId: sess_cli
+            sessionStartedAt: 1
+            platform: web
+            types:
+              - sdk
+            sdkappid: 0
+            lastPrompt: user question
+            lastAnswer: |
+              answer body
+
+              ---
+
+              footer
+            """
+        ),
+        encoding="utf-8",
+    )
+    r = subprocess.run(
+        [
+            sys.executable,
+            str(TRTC / "tools" / "reporting_v2.py"),
+            "send-query",
+            "--m",
+            "p",
+            "--docs-query",
+            str(dq_path),
+            "--dry-run",
+            "--debug",
+        ],
+        cwd=TRTC,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    assert r.returncode == 0, r.stderr
+    data = json.loads(r.stdout.strip())
+    assert data["action"] == "dry-run"
+    inner = json.loads(data["payload"])
+    assert inner["method"] == "prompt"
+    assert inner["text"] == "user question"
+    assert "answer body" in inner["answer"]
+
+
+def test_send_docs_query_legacy_alias(tmp_path: Path) -> None:
+    dq_path = tmp_path / ".docs-query.yaml"
+    dq_path.write_text(
+        "sessionId: s1\nsdkappid: 0\nplatform: \"\"\ntypes: []\n"
+        "lastPrompt: q\nlastAnswer: a\n",
+        encoding="utf-8",
+    )
+    r = subprocess.run(
+        [
+            sys.executable,
+            str(TRTC / "tools" / "reporting_v2.py"),
+            "send-docs-query",
+            "--method",
+            "prompt",
+            "--docs-query",
+            str(dq_path),
+            "--dry-run",
+            "--debug",
+        ],
+        cwd=TRTC,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    assert r.returncode == 0, r.stderr
+
+
+def test_find_docs_query_yaml_from_chat_cwd() -> None:
+    found = rv2.find_docs_query_yaml()
+    assert found == (CHAT / ".docs-query.yaml").resolve()
+
+
+def test_chat_bundle_template_has_last_answer() -> None:
+    text = (CHAT / ".docs-query.yaml").read_text(encoding="utf-8")
+    assert "lastAnswer:" in text