agent-skills

Build an AI English speaking coach powered by Tencent Cloud TRTC Conversational AI (voice-first). Agent-driven — users never touch a terminal. Two paths: Path A Quick Start — 3-screen SPA (scenario practice + sentence correction + reply suggestions + 4-dimension report) Path B Integrate — backend inbound API + integration code, no UI generated

Build real-time AI interpretation powered by Tencent Cloud TRTC Conversational AI (voice-first). Designed for beginners — no coding experience required. Plain-language guidance throughout. Two paths available: Quick Start —— Ready-to-use Vue3 meeting room with real-time AI interpreter (for first-timers who want to see results fast) Integrate into My System —— Add TRTC-based real-time interpretation backend capabilities to your existing project (no UI generated) The Coding Agent drives the entire process in the chat window. Users never touch a terminal or run scripts manually.

Build AI customer service powered by Tencent Cloud TRTC Conversational AI (voice-first). Designed for beginners — no coding experience required. Plain-language guidance throughout. Two paths available: Quick Start —— Ready-to-use voice agent UI + ticket dashboard (for first-timers who want to see results fast) Integrate into My System —— Add TRTC Conversational AI backend capabilities to your existing project (no UI generated) The Coding Agent drives the entire process in the chat window. Users never touch a terminal or run scripts manually.

Internal Chat IM docs query (Path D) — enter ONLY via skills/trtc/SKILL.md routing. Not a standalone dispatcher entry. IM product/SDK/REST/Webhook/TUIKit/billing/errors.

Internal Chat (IM) integration domain skill — enter ONLY via skills/trtc/SKILL.md after product=chat routing. Not a standalone dispatcher entry. Handles Vue 3 Web full/direct chat integration (Path A/B/C/D).

Use for TIMPush (Tencent Cloud IM Push / 腾讯云即时通信推送) developer assistance — Android and iOS integration and troubleshooting via trtc-push-mcp, plus Flutter, uni-app, HarmonyOS, server API, badge, console, and product-limit routing. Use when the user is integrating or debugging TIMPush itself (e.g. 接入 TIMPush, 帮我集成 timpush, 集成 TIMPush, 集成腾讯云 push, 接入腾讯云 push, 集成腾讯云离线推送, 接入腾讯云离线推送, 即时通信推送, 离线推送接入, TIMPush 离线推送, 腾讯云离线推送, 腾讯云 push, integrate TIMPush, integrate Tencent Cloud push, integrate Tencent Cloud offline push, setup Tencent Cloud push, registerPush failed, 800006, FCM unavailable with TIMPush, APNs, businessID). Entered via trtc dispatcher pre-gate when shipped inside trtc-agent-skills. Do not use for maintaining/debugging this skill or MCP reporting tooling, Conference/TUIRoom/直播间/口语陪练/AI客服 主导且无 TIMPush 信号的场景, or unrelated generic push work with no TIMPush signal.

Routes TRTC questions and integration requests to the right skill. Identifies product (Conference, Chat, Call, Live, RTC Engine, Conversational AI, TIMPush), platform, and intent, then dispatches to the appropriate pipeline. Use when the user wants to integrate TRTC, build a video conference, voice room, live stream, 1v1 call, or IM chat app, or asks about SDK usage, error codes, pricing, or API docs — in any phrasing: "接入TRTC", "如何集成", "build a meeting app", "音视频", "直播间", "IM聊天", "错误码", "怎么用TRTC", "video conference", "RTC SDK". 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. Also triggers for TIMPush / 离线推送 / 帮我集成 timpush / 集成腾讯云 push / 接入腾讯云 push / 集成腾讯云离线推送 / 接入腾讯云离线推送 / integrate Tencent Cloud push / Tencent Cloud offline push /

Guides users through building a TRTC Conference Web application step by step. Handles capability overview, scenario matching, integration mode selection, and dispatches to the appropriate playbook or slice-based topic flow. Use when the user wants to integrate TRTC Conference on Web — "搭建会议", "接入会议室", "多人视频", "语音聊天室", "build a meeting app", "integrate conference", "step-by-step", "帮我接入", "从零开始", "add screen sharing", "给项目加功能". Keywords: Conference, 会议, TUIRoom, RoomKit, UIKit, 视频会议, 语音房间, screen share, participant management, Web, Vue, React.

Answers factual, conceptual, and decision-making questions about TRTC from authoritative sources. Use when the user asks about pricing, quotas, error codes, API usage, product comparisons, migration, or how something works conceptually — in any phrasing (e.g. "how much does X cost", "多少钱", "X vs Y", "对比", "error code 6206", "错误码", "does TRTC support Y", "配额", "the correct way to use X", "X是什么", "how does X work", "migrate from V3 to V4", "迁移"). Retrieves answers from DocsBot knowledge base (fact/decision/path questions) and local knowledge-base slices (error-code / API-pattern lookups) — never training-data synthesis.

Evaluates the quality of the trtc skill and its knowledge base by running AI-generated code against a curated eval set and scoring both static constraint compliance and runtime SDK behavior. Use when the user mentions 跑分, 评测, eval, benchmark, 回归, quality check, or asks to compare skill versions. Internal-only tool for TRTC knowledge maintainers.