call-uikit
This is the parent skill for Tencent Call TUICallKit integration across all platforms. It should be used when users want to build audio/video CALL features (1-to-1 or small group calls). This skill guides platform selection and provides common knowledge shared across all Call implementations. For platform-specific guidance, use the corresponding sub-skills (call/vue, call/react, etc.).
What this skill does
# Call TUICallKit Integration Skill (Multi-Platform Aggregation)
> π **Parent Skill**: This is a sub-skill of `tencent-rtc-skills` (root skill).
> If user's intent is ambiguous across products (Chat/Call/Live/Room), load the root skill first for product recommendation.
> **π Global Reference**: This sub-skill follows the global standards defined in ROOT SKILL:
> - Skill-First Principle (priority order)
> - Boundary Recognition Pattern
> - MCP Tools Reference (record_prompt, get_usersig, record_result)
> - MCP Tool Call Sequence Pattern
> - Documentation-Driven Integration Rules
> - Silent Execution Rules
> - Zero External Configuration
> - Auto-Fetch Authentication Credentials
> - Agent Execution Checklist Template
>
> Call-specific rules below may EXTEND or OVERRIDE global rules where explicitly noted.
---
## π΅ Boundary Recognition (Call-Specific)
### Keywords That CONFIRM Call Scope
Only proceed with Call integration if user's request contains:
- call, phone call, video call, voice call
- 1-to-1, one-to-one, peer-to-peer
- dial, answer, hang up, incoming call, ringtone
- TUICallKit, CallKit
- WeChat call-like
### OUT OF SCOPE β Redirect
> **π Reference**: See ROOT SKILL for global Boundary Recognition Pattern.
| User Keywords | Redirect To | Reason |
|---------------|-------------|--------|
| "video conference" / "meeting" / "conference" | TUIRoomKit (Room) | Room is designed for meetings with member management and screen sharing |
| "chat" / "IM" / "message" / "instant messaging" | Chat TUIKit | Chat is designed for instant messaging |
| "live streaming" / "host" / "audience" / "gift" | TUILiveKit (Live) | Live is designed for live streaming scenarios |
### β οΈ Special Case: "video conference" Redirection
**CRITICAL**: When user says "video conference", Agent MUST redirect to Room:
```
User: "Use CallKit to implement video conference"
Agent Response:
"Note: TUICallKit is designed for **peer-to-peer calls** (like WeChat calls), not for conferences.
For **video conference** needs, I strongly recommend **TUIRoomKit (Room)**:
- β
Designed specifically for meeting scenarios
- β
Supports member management (mute all, kick, roles)
- β
Supports screen sharing
- β
Suitable for multi-person meetings
If you really need simple 1-to-1 or small group calls (without meeting features), I can continue with TUICallKit.
Please confirm your requirements."
```
---
## Overview
This Skill serves as the **multi-platform aggregation entry point** for Tencent Cloud Call TUICallKit, applicable to the following scenarios:
1. Users need audio/video call features but have not specified a platform/framework
2. Need to understand capability differences and selection recommendations across platforms
3. Need cross-platform common concepts and knowledge
**Platform-Specific Guidance**: Once the platform is determined, please use the corresponding sub-Skill:
- `call/vue` - Vue3 Web Applications
- `call/react` - React Web Applications
- `call/android` - Android Native Applications
- `call/ios` - iOS Native Applications
- `call/flutter` - Flutter Cross-Platform Applications
---
## π― When to Use Call vs Room
### Use Call (TUICallKit) When:
| Scenario | Example | Why Call? |
|----------|---------|-----------|
| **1-to-1 Calls** | Video chat between two friends | Call semantics, ringtone support |
| **Small Group Calls** | Family video call (3-5 people) | Lightweight, call-focused UI |
| **Call with Ringtone** | Incoming call notification needed | Built-in ringtone and call states |
| **Call Status Management** | Show "Ringing...", "Connected", "Ended" | Native call state machine |
| **Quick Integration** | Simple call feature in existing app | Minimal setup, focused API |
### Use Room (TUIRoomKit) Instead When:
| Scenario | Why Room? |
|----------|-----------|
| **Video Conference** | Meeting controls, member management |
| **Screen Sharing Required** | Native screen share support |
| **Large Participant Count** | Optimized for many participants |
| **Meeting Features** | Mute all, roles, agenda |
---
## π Product Selection Guidance
When user's requirement is ambiguous, clarify:
```
User: "Implement audio/video communication feature"
Agent should ask:
"What is your audio/video communication requirement:
1. **1-to-1 or Small Group Calls** (like WeChat calls, with incoming ringtone) β Recommend TUICallKit
2. **Multi-person Video Conference** (like Tencent Meeting, with member management) β Recommend TUIRoomKit
Please select your scenario, and I will load the corresponding integration guide."
```
---
## Core Features
TUICallKit provides:
### 1. Call Types
- **Voice Call** - Audio-only calls
- **Video Call** - Audio + video calls
- **Group Call** - Multi-person calls (up to 9)
### 2. Call Flow
```
βββββββββββ βββββββββββ βββββββββββ βββββββββββ
β Idle β βββΆ β Calling β βββΆ βConnectedβ βββΆ β Ended β
βββββββββββ βββββββββββ βββββββββββ βββββββββββ
β β²
β (Answer) β
βΌ β
βββββββββββ β
β Ringing β βββββββββ
βββββββββββ
```
### 3. UI Components
- **Incoming Call UI** - Shows caller info, accept/reject buttons
- **Calling UI** - Shows callee info, hang up button
- **In-Call UI** - Video view, controls (mute, speaker, camera)
- **Floating Window** - Mini window when app is backgrounded
### 4. Call Features
- Ringtone customization
- Call timeout handling
- Network quality indicators
- Camera/microphone control
- Speaker/earpiece switching
---
## π΄ Mandatory MCP Tool Usage
> **π Reference**: See ROOT SKILL "Global: MCP Tool Call Sequence Pattern" for universal sequence.
### Call-Specific Tools
| Tool | Purpose | When to Use |
|------|---------|-------------|
| `get_native_call_uikit_integration` | Native platform integration guide | For Android/iOS/Flutter |
| `get_web_call_uikit_integration` | Web platform integration guide | For React/Vue |
| `get_web_call_uikit_api` | API documentation | For customization needs |
---
## π Sub-Skill Directory
| Platform | Skill Path | Status |
|----------|------------|--------|
| React Web | `/call/react/SKILL.md` | Planned |
| Vue3 Web | `/call/vue/SKILL.md` | Planned |
| Android | `/call/android/SKILL.md` | Planned |
| iOS | `/call/ios/SKILL.md` | Planned |
| Flutter | `/call/flutter/SKILL.md` | Planned |
---
## Keywords for Intent Matching
When user prompt contains these keywords, this skill (or its sub-skills) should be considered:
**Primary Keywords** (Strong match):
- call, phone call, video call, voice call
- TUICallKit, CallKit
- dial, answer, hang up, incoming call
- 1-to-1, one-to-one, peer-to-peer
**Secondary Keywords** (May also match Room):
- audio/video
- video chat
**Exclusion Keywords** (Prefer other products):
- meeting, conference β Room
- live streaming, host β Live
- chat, IM, message β Chat
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.