[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718HCKFSGDVYETKSHMDJSXA":3,"skill-same:01M718HCKFSGDVYETKSHMDJSXA":109},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":6,"ownerHtmlUrl":70,"ownerBlogUrl":71,"ownerDescription":6,"updatedAt":72,"install":73,"resources":86},"01M718HCKFSGDVYETKSHMDJSXA","meeting-sdk\u002Flinux",null,"Zoom Meeting SDK for Linux - C++ headless meeting bots with raw audio\u002Fvideo access, transcription, recording, and AI integration for server-side automation","anthropics\u002Fknowledge-work-plugins","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7188MPC48111TN566QNQE3X",35379,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"meeting sdk linux","linux","sdk","meeting sdk","meeting","c++","for","headless","recording","zoom","false","server-side","bot","bots","access","Audio","Video","data","server","docker","2026-11-10 10:12:30",false,"---\nname: meeting-sdk\u002Flinux\ndescription: \"Zoom Meeting SDK for Linux - C++ headless meeting bots with raw audio\u002Fvideo access, transcription, recording, and AI integration for server-side automation\"\nuser-invocable: false\ntriggers:\n  - \"linux meeting bot\"\n  - \"headless zoom bot\"\n  - \"meeting sdk linux\"\n  - \"zoom raw recording linux\"\n  - \"meeting transcription bot\"\n  - \"zoom docker bot\"\n  - \"pulseaudio zoom\"\n  - \"meeting sdk raw data\"\n---\n\n# Zoom Meeting SDK - Linux Development\n\nExpert guidance for building headless meeting bots with the Zoom Meeting SDK on Linux. This SDK enables server-side meeting participation, raw media capture, transcription, and AI-powered meeting automation.\n\n## How to Build a Meeting Bot That Automatically Joins and Records\n\nUse this skill when the requirement is:\n- visible bot joins a real Zoom meeting\n- the bot records raw media itself\n- or the bot triggers a Zoom-managed cloud-recording workflow after join\n\nSkill chain:\n- primary: `meeting-sdk\u002Flinux`\n- add `zoom-rest-api` for OBF\u002FZAK lookup, scheduling, or cloud-recording settings\n- add `zoom-webhooks` when post-meeting cloud recording retrieval is required\n\nMinimal raw-recording flow:\n\n```cpp\nJoinParam join_param;\njoin_param.userType = SDK_UT_WITHOUT_LOGIN;\nauto& params = join_param.param.withoutloginuserJoin;\nparams.meetingNumber = meeting_number;\nparams.userName = \"Recording Bot\";\nparams.psw = meeting_password.c_str();\nparams.app_privilege_token = obf_token.c_str();\n\nSDKError join_err = meeting_service->Join(join_param);\nif (join_err != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"join_failed\");\n}\n\n\u002F\u002F In MEETING_STATUS_INMEETING callback:\nauto* record_ctrl = meeting_service->GetMeetingRecordingController();\nif (!record_ctrl) {\n    throw std::runtime_error(\"recording_controller_unavailable\");\n}\n\nif (record_ctrl->CanStartRawRecording() != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"raw_recording_not_permitted\");\n}\n\nSDKError record_err = record_ctrl->StartRawRecording();\nif (record_err != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"start_raw_recording_failed\");\n}\n\nGetAudioRawdataHelper()->subscribe(new MyAudioDelegate());\n```\n\nUse **raw recording** when the bot must own PCM\u002FYUV media or feed an AI pipeline directly.  \nUse **cloud recording + webhooks** when the requirement is Zoom-managed MP4\u002FM4A\u002Ftranscript assets after the meeting.\n\n**Official Documentation**: https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Flinux\u002F  \n**API Reference**: https:\u002F\u002Fmarketplacefront.zoom.us\u002Fsdk\u002Fmeeting\u002Flinux\u002F  \n**Sample Repository (Raw Recording)**: https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample  \n**Sample Repository (Headless)**: https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample\n\n## Quick Links\n\n**New to Meeting SDK Linux? Follow this path:**\n\n1. **[linux.md](linux.md)** - Quick start guide with complete workflow\n2. **[concepts\u002Fhigh-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md)** - Production bot architectures\n3. **[meeting-sdk-bot.md](meeting-sdk-bot.md)** - Resilient bot with retry logic\n4. **[references\u002Flinux-reference.md](references\u002Flinux-reference.md)** - Dependencies, Docker, CMake\n\n**Common Use Cases:**\n- **Transcription Bot** → [high-level-scenarios.md#scenario-1-transcription-bot](concepts\u002Fhigh-level-scenarios.md)\n- **Recording Bot** → [high-level-scenarios.md#scenario-2-recording-bot](concepts\u002Fhigh-level-scenarios.md)\n- **AI Meeting Assistant** → [high-level-scenarios.md#scenario-3-ai-meeting-assistant](concepts\u002Fhigh-level-scenarios.md)\n- **Quality Monitoring** → [high-level-scenarios.md#scenario-4-monitoring-quality-bot](concepts\u002Fhigh-level-scenarios.md)\n- **Auto-Join + Recording Bot** → [meeting-sdk-bot.md](meeting-sdk-bot.md) for raw recording orchestration, retry, and cloud-recording handoff\n\n**Having issues?**\n- Docker audio issues → [references\u002Flinux-reference.md#pulseaudio-setup](references\u002Flinux-reference.md)\n- Raw recording permission denied → [meeting-sdk-bot.md#raw-recording-permission-denied](meeting-sdk-bot.md)\n- Build errors → [references\u002Flinux-reference.md#troubleshooting](references\u002Flinux-reference.md)\n\n## Routing Rule for Bots\n\nIf the user asks to build a bot that **automatically joins a Zoom meeting and records it**, start with\n[meeting-sdk-bot.md](meeting-sdk-bot.md).\n\n- Use **Meeting SDK Linux** for the visible participant, join flow, and raw recording control.\n- Chain **zoom-rest-api** when the bot must fetch OBF\u002FZAK tokens, schedule meetings, or enable account-side recording settings.\n- Chain **zoom-webhooks** when the requirement is Zoom cloud recording retrieval after meeting end.\n\n## SDK Overview\n\nThe Zoom Meeting SDK for Linux is a **C++ library optimized for headless server environments**:\n- **Headless Operation**: No GUI required, perfect for Docker\u002Fcloud\n- **Raw Data Access**: YUV420 video, PCM audio at 32kHz\n- **GLib Event Loop**: Async event handling for callbacks\n- **Docker-Ready**: Pre-configured Dockerfiles for CentOS\u002FUbuntu\n- **PulseAudio Integration**: Virtual audio devices for headless environments\n\n### Key Differences from Video SDK\n\n| Feature | Meeting SDK (Linux) | Video SDK |\n|---------|-------------------|-----------|\n| **Primary Use** | Join existing meetings as bot | Host custom video sessions |\n| **Visibility** | Visible participant | Session participant |\n| **UI** | Headless (no UI) | Optional custom UI |\n| **Authentication** | JWT + OBF\u002FZAK for external meetings | JWT only |\n| **Recording Control** | `StartRawRecording()` required | Direct raw data access |\n| **Platform** | Linux only | Windows, macOS, iOS, Android |\n\n## Prerequisites\n\n### System Requirements\n- **OS**: Ubuntu 22+, CentOS 8\u002F9, Oracle Linux 8\n- **Architecture**: x86_64\n- **Compiler**: gcc\u002Fg++ with C++11 support\n- **Build Tools**: cmake 3.16+\n\n### Development Dependencies\n```bash\n# Ubuntu\napt-get install -y build-essential cmake \\\n    libx11-xcb1 libxcb-xfixes0 libxcb-shape0 libxcb-shm0 \\\n    libxcb-randr0 libxcb-image0 libxcb-keysyms1 libxcb-xtest0 \\\n    libglib2.0-dev libcurl4-openssl-dev pulseaudio\n\n# CentOS\nyum install -y cmake gcc gcc-c++ \\\n    libxcb-devel xcb-util-image xcb-util-keysyms \\\n    glib2-devel libcurl-devel pulseaudio\n```\n\n### Required Credentials\n1. **Zoom Meeting SDK App** (Client ID & Secret) → [Create at Marketplace](https:\u002F\u002Fmarketplace.zoom.us\u002F)\n2. **JWT Token** → Generate from Client ID\u002FSecret\n3. **For External Meetings**: OBF token OR ZAK token → [Get via REST API](..\u002Freferences\u002Fbot-authentication.md)\n4. **For Raw Recording**: Meeting Recording Token (optional) → [Get via API](https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Fapis\u002F#operation\u002FmeetingLocalRecordingJoinToken)\n\n## Quick Start\n\n### 1. Download & Extract SDK\n\n```bash\n# Download from https:\u002F\u002Fmarketplace.zoom.us\u002F\ntar xzf zoom-meeting-sdk-linux_x86_64-{version}.tar\n\n# Organize files\nmkdir -p demo\u002Finclude\u002Fh demo\u002Flib\u002Fzoom_meeting_sdk\ncp -r h\u002F* demo\u002Finclude\u002Fh\u002F\ncp lib*.so demo\u002Flib\u002Fzoom_meeting_sdk\u002F\ncp -r qt_libs demo\u002Flib\u002Fzoom_meeting_sdk\u002F\ncp translation.json demo\u002Flib\u002Fzoom_meeting_sdk\u002Fjson\u002F\n\n# Create required symlink\ncd demo\u002Flib\u002Fzoom_meeting_sdk && ln -s libmeetingsdk.so libmeetingsdk.so.1\n```\n\n### 2. Initialize & Auth\n\n```cpp\n#include \"zoom_sdk.h\"\n\nUSING_ZOOM_SDK_NAMESPACE\n\n\u002F\u002F Initialize SDK\nInitParam init_params;\ninit_params.strWebDomain = \"https:\u002F\u002Fzoom.us\";\ninit_params.enableLogByDefault = true;\ninit_params.rawdataOpts.audioRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\nInitSDK(init_params);\n\n\u002F\u002F Authenticate with JWT\nAuthContext auth_ctx;\nauth_ctx.jwt_token = your_jwt_token;\nCreateAuthService(&auth_service);\nauth_service->SDKAuth(auth_ctx);\n```\n\n### 3. Join Meeting\n\n```cpp\n\u002F\u002F In onAuthenticationReturn callback\nvoid onAuthenticationReturn(AuthResult ret) {\n    if (ret == AUTHRET_SUCCESS) {\n        JoinParam join_param;\n        join_param.userType = SDK_UT_WITHOUT_LOGIN;\n        \n        auto& params = join_param.param.withoutloginuserJoin;\n        params.meetingNumber = 1234567890;\n        params.userName = \"Bot\";\n        params.psw = \"password\";\n        params.isVideoOff = true;\n        params.isAudioOff = false;\n        \n        meeting_service->Join(join_param);\n    }\n}\n```\n\n### 4. Access Raw Data\n\n```cpp\n\u002F\u002F In onMeetingStatusChanged callback\nvoid onMeetingStatusChanged(MeetingStatus status, int iResult) {\n    if (status == MEETING_STATUS_INMEETING) {\n        auto* record_ctrl = meeting_service->GetMeetingRecordingController();\n        \n        \u002F\u002F Start raw recording (enables raw data access)\n        if (record_ctrl->CanStartRawRecording() == SDKERR_SUCCESS) {\n            record_ctrl->StartRawRecording();\n            \n            \u002F\u002F Subscribe to audio\n            auto* audio_helper = GetAudioRawdataHelper();\n            audio_helper->subscribe(new MyAudioDelegate());\n            \n            \u002F\u002F Subscribe to video\n            IZoomSDKRenderer* video_renderer;\n            createRenderer(&video_renderer, new MyVideoDelegate());\n            video_renderer->setRawDataResolution(ZoomSDKResolution_720P);\n            video_renderer->subscribe(user_id, RAW_DATA_TYPE_VIDEO);\n        }\n    }\n}\n```\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| **Headless Operation** | No GUI, perfect for Docker\u002Fserver deployments |\n| **Raw Audio (PCM)** | Capture mixed or per-user audio at 32kHz |\n| **Raw Video (YUV420)** | Capture video frames in contiguous planar format |\n| **GLib Event Loop** | Async callback handling |\n| **Docker Support** | Pre-built Dockerfiles for CentOS\u002FUbuntu |\n| **PulseAudio Virtual Devices** | Audio in headless environments |\n| **Breakout Rooms** | Programmatic breakout room management |\n| **Chat** | Send\u002Freceive in-meeting chat |\n| **Recording Control** | Local, cloud, and raw recording |\n\n## Critical Gotchas & Best Practices\n\n### ⚠️ CRITICAL: PulseAudio for Docker\u002FHeadless\n\n**The #1 issue for raw audio in Docker:**\n\nRaw audio requires PulseAudio and a config file, even in headless environments.\n\n**Solution**:\n```bash\n# Install PulseAudio\napt-get install -y pulseaudio pulseaudio-utils\n\n# Create config file\nmkdir -p ~\u002F.config\ncat > ~\u002F.config\u002Fzoomus.conf \u003C\u003C EOF\n[General]\nsystem.audio.type=default\nEOF\n\n# Start PulseAudio with virtual devices\npulseaudio --start --exit-idle-time=-1\npactl load-module module-null-sink sink_name=virtual_speaker\npactl load-module module-null-sink sink_name=virtual_mic\n```\n\nSee: [references\u002Flinux-reference.md#pulseaudio-setup](references\u002Flinux-reference.md)\n\n### Raw Recording Permission Required\n\nUnlike Video SDK, Meeting SDK requires explicit permission to access raw data:\n\n```cpp\n\u002F\u002F MUST call StartRawRecording() first\nauto* record_ctrl = meeting_service->GetMeetingRecordingController();\n\nSDKError can_record = record_ctrl->CanStartRawRecording();\nif (can_record == SDKERR_SUCCESS) {\n    record_ctrl->StartRawRecording();\n    \u002F\u002F NOW you can subscribe to audio\u002Fvideo\n} else {\n    \u002F\u002F Need: host\u002Fco-host status OR recording token\n}\n```\n\n**Ways to get permission**:\n1. Bot is host\u002Fco-host\n2. Host grants recording permission\n3. Use `recording_token` parameter (get via [REST API](https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Fapis\u002F#operation\u002FmeetingLocalRecordingJoinToken))\n4. Use `app_privilege_token` (OBF) when joining\n\n### GLib Main Loop Required\n\nSDK callbacks execute via GLib event loop:\n\n```cpp\n#include \u003Cglib.h>\n\n\u002F\u002F Setup main loop\nGMainLoop* loop = g_main_loop_new(NULL, FALSE);\n\n\u002F\u002F Add timeout for periodic tasks\ng_timeout_add_seconds(10, check_meeting_status, NULL);\n\n\u002F\u002F Run loop (blocks until quit)\ng_main_loop_run(loop);\n```\n\n**Without GLib loop**: Callbacks never fire, join hangs indefinitely.\n\n### Heap Memory Mode Recommended\n\nAlways use heap mode for raw data to avoid stack overflow with large frames:\n\n```cpp\ninit_params.rawdataOpts.videoRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\ninit_params.rawdataOpts.shareRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\ninit_params.rawdataOpts.audioRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\n```\n\n### Thread Safety\n\nSDK callbacks execute on SDK threads:\n- Don't perform heavy operations in callbacks\n- Don't call `CleanUPSDK()` from within callbacks\n- Use thread-safe queues for data passing\n- Use mutexes for shared state\n\n## Production Architectures\n\n### Transcription Bot\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-1](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → StartRawRecording → Subscribe Audio → \nStream to AssemblyAI\u002FWhisper → Generate Real-time Transcript\n```\n\n### Recording Bot\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-2](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → StartRawRecording → Subscribe Audio+Video → \nWrite YUV+PCM → FFmpeg Merge → Upload to Storage\n```\n\n### AI Meeting Assistant\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-3](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → Real-time Transcription → AI Analysis → \nExtract Action Items → Generate Summary\n```\n\n## Sample Applications\n\n**Official Repositories**:\n\n| Sample | Description | Link |\n|--------|-------------|------|\n| **Raw Recording Sample** | Traditional C++ approach with config.txt | [GitHub](https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample) |\n| **Headless Sample** | Modern TOML-based with CLI, Docker Compose | [GitHub](https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample) |\n\n**What Each Demonstrates**:\n\n- **Raw Recording Sample**: Complete raw data workflow, PulseAudio setup, Docker multi-distro support\n- **Headless Sample**: AssemblyAI integration, Anthropic AI, production-ready config management\n\n## Documentation Library\n\n### Core Concepts\n- **[linux.md](linux.md)** - Quick start & core workflow\n- **[concepts\u002Fhigh-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md)** - Production bot architectures\n- **[meeting-sdk-bot.md](meeting-sdk-bot.md)** - Resilient bot with retry logic\n\n### Platform Reference\n- **[references\u002Flinux-reference.md](references\u002Flinux-reference.md)** - Dependencies, CMake, Docker, troubleshooting\n\n### Authentication\n- **[..\u002Freferences\u002Fauthorization.md](..\u002Freferences\u002Fauthorization.md)** - SDK JWT generation\n- **[..\u002Freferences\u002Fbot-authentication.md](..\u002Freferences\u002Fbot-authentication.md)** - Bot token types (ZAK, OBF, JWT)\n\n### Advanced Features\n- **[..\u002Freferences\u002Fbreakout-rooms.md](..\u002Freferences\u002Fbreakout-rooms.md)** - Programmatic breakout rooms\n- **[..\u002Freferences\u002Fai-companion.md](..\u002Freferences\u002Fai-companion.md)** - AI Companion controls\n\n## Common Issues\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| **No audio in Docker** | Missing PulseAudio config | Create `~\u002F.config\u002Fzoomus.conf` |\n| **Raw recording denied** | No permission | Use host\u002Fco-host OR recording token |\n| **Callbacks not firing** | Missing GLib main loop | Add `g_main_loop_run()` |\n| **Build errors (XCB)** | Missing X11 libraries | Install libxcb packages |\n| **Segfault on auth** | OpenSSL version mismatch | Install libssl1.1 |\n\n**Complete troubleshooting**: [references\u002Flinux-reference.md#troubleshooting](references\u002Flinux-reference.md)\n\n## Resources\n\n- **Official Docs**: https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Flinux\u002F\n- **API Reference**: https:\u002F\u002Fmarketplacefront.zoom.us\u002Fsdk\u002Fmeeting\u002Flinux\u002F\n- **Dev Forum**: https:\u002F\u002Fdevforum.zoom.us\u002F\n- **GitHub Samples**: \n  - https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample\n  - https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample\n\n---\n\n**Need help?** Start with [linux.md](linux.md) for quick start, then explore [high-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md) for production patterns.\n\n## Operations\n\n- [RUNBOOK.md](RUNBOOK.md) - 5-minute preflight and debugging checklist.\n","# Zoom Meeting SDK - Linux Development\n\nExpert guidance for building headless meeting bots with the Zoom Meeting SDK on Linux. This SDK enables server-side meeting participation, raw media capture, transcription, and AI-powered meeting automation.\n\n## How to Build a Meeting Bot That Automatically Joins and Records\n\nUse this skill when the requirement is:\n- visible bot joins a real Zoom meeting\n- the bot records raw media itself\n- or the bot triggers a Zoom-managed cloud-recording workflow after join\n\nSkill chain:\n- primary: `meeting-sdk\u002Flinux`\n- add `zoom-rest-api` for OBF\u002FZAK lookup, scheduling, or cloud-recording settings\n- add `zoom-webhooks` when post-meeting cloud recording retrieval is required\n\nMinimal raw-recording flow:\n\n```cpp\nJoinParam join_param;\njoin_param.userType = SDK_UT_WITHOUT_LOGIN;\nauto& params = join_param.param.withoutloginuserJoin;\nparams.meetingNumber = meeting_number;\nparams.userName = \"Recording Bot\";\nparams.psw = meeting_password.c_str();\nparams.app_privilege_token = obf_token.c_str();\n\nSDKError join_err = meeting_service->Join(join_param);\nif (join_err != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"join_failed\");\n}\n\n\u002F\u002F In MEETING_STATUS_INMEETING callback:\nauto* record_ctrl = meeting_service->GetMeetingRecordingController();\nif (!record_ctrl) {\n    throw std::runtime_error(\"recording_controller_unavailable\");\n}\n\nif (record_ctrl->CanStartRawRecording() != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"raw_recording_not_permitted\");\n}\n\nSDKError record_err = record_ctrl->StartRawRecording();\nif (record_err != SDKERR_SUCCESS) {\n    throw std::runtime_error(\"start_raw_recording_failed\");\n}\n\nGetAudioRawdataHelper()->subscribe(new MyAudioDelegate());\n```\n\nUse **raw recording** when the bot must own PCM\u002FYUV media or feed an AI pipeline directly.  \nUse **cloud recording + webhooks** when the requirement is Zoom-managed MP4\u002FM4A\u002Ftranscript assets after the meeting.\n\n**Official Documentation**: https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Flinux\u002F  \n**API Reference**: https:\u002F\u002Fmarketplacefront.zoom.us\u002Fsdk\u002Fmeeting\u002Flinux\u002F  \n**Sample Repository (Raw Recording)**: https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample  \n**Sample Repository (Headless)**: https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample\n\n## Quick Links\n\n**New to Meeting SDK Linux? Follow this path:**\n\n1. **[linux.md](linux.md)** - Quick start guide with complete workflow\n2. **[concepts\u002Fhigh-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md)** - Production bot architectures\n3. **[meeting-sdk-bot.md](meeting-sdk-bot.md)** - Resilient bot with retry logic\n4. **[references\u002Flinux-reference.md](references\u002Flinux-reference.md)** - Dependencies, Docker, CMake\n\n**Common Use Cases:**\n- **Transcription Bot** → [high-level-scenarios.md#scenario-1-transcription-bot](concepts\u002Fhigh-level-scenarios.md)\n- **Recording Bot** → [high-level-scenarios.md#scenario-2-recording-bot](concepts\u002Fhigh-level-scenarios.md)\n- **AI Meeting Assistant** → [high-level-scenarios.md#scenario-3-ai-meeting-assistant](concepts\u002Fhigh-level-scenarios.md)\n- **Quality Monitoring** → [high-level-scenarios.md#scenario-4-monitoring-quality-bot](concepts\u002Fhigh-level-scenarios.md)\n- **Auto-Join + Recording Bot** → [meeting-sdk-bot.md](meeting-sdk-bot.md) for raw recording orchestration, retry, and cloud-recording handoff\n\n**Having issues?**\n- Docker audio issues → [references\u002Flinux-reference.md#pulseaudio-setup](references\u002Flinux-reference.md)\n- Raw recording permission denied → [meeting-sdk-bot.md#raw-recording-permission-denied](meeting-sdk-bot.md)\n- Build errors → [references\u002Flinux-reference.md#troubleshooting](references\u002Flinux-reference.md)\n\n## Routing Rule for Bots\n\nIf the user asks to build a bot that **automatically joins a Zoom meeting and records it**, start with\n[meeting-sdk-bot.md](meeting-sdk-bot.md).\n\n- Use **Meeting SDK Linux** for the visible participant, join flow, and raw recording control.\n- Chain **zoom-rest-api** when the bot must fetch OBF\u002FZAK tokens, schedule meetings, or enable account-side recording settings.\n- Chain **zoom-webhooks** when the requirement is Zoom cloud recording retrieval after meeting end.\n\n## SDK Overview\n\nThe Zoom Meeting SDK for Linux is a **C++ library optimized for headless server environments**:\n- **Headless Operation**: No GUI required, perfect for Docker\u002Fcloud\n- **Raw Data Access**: YUV420 video, PCM audio at 32kHz\n- **GLib Event Loop**: Async event handling for callbacks\n- **Docker-Ready**: Pre-configured Dockerfiles for CentOS\u002FUbuntu\n- **PulseAudio Integration**: Virtual audio devices for headless environments\n\n### Key Differences from Video SDK\n\n| Feature | Meeting SDK (Linux) | Video SDK |\n|---------|-------------------|-----------|\n| **Primary Use** | Join existing meetings as bot | Host custom video sessions |\n| **Visibility** | Visible participant | Session participant |\n| **UI** | Headless (no UI) | Optional custom UI |\n| **Authentication** | JWT + OBF\u002FZAK for external meetings | JWT only |\n| **Recording Control** | `StartRawRecording()` required | Direct raw data access |\n| **Platform** | Linux only | Windows, macOS, iOS, Android |\n\n## Prerequisites\n\n### System Requirements\n- **OS**: Ubuntu 22+, CentOS 8\u002F9, Oracle Linux 8\n- **Architecture**: x86_64\n- **Compiler**: gcc\u002Fg++ with C++11 support\n- **Build Tools**: cmake 3.16+\n\n### Development Dependencies\n```bash\n# Ubuntu\napt-get install -y build-essential cmake \\\n    libx11-xcb1 libxcb-xfixes0 libxcb-shape0 libxcb-shm0 \\\n    libxcb-randr0 libxcb-image0 libxcb-keysyms1 libxcb-xtest0 \\\n    libglib2.0-dev libcurl4-openssl-dev pulseaudio\n\n# CentOS\nyum install -y cmake gcc gcc-c++ \\\n    libxcb-devel xcb-util-image xcb-util-keysyms \\\n    glib2-devel libcurl-devel pulseaudio\n```\n\n### Required Credentials\n1. **Zoom Meeting SDK App** (Client ID & Secret) → [Create at Marketplace](https:\u002F\u002Fmarketplace.zoom.us\u002F)\n2. **JWT Token** → Generate from Client ID\u002FSecret\n3. **For External Meetings**: OBF token OR ZAK token → [Get via REST API](..\u002Freferences\u002Fbot-authentication.md)\n4. **For Raw Recording**: Meeting Recording Token (optional) → [Get via API](https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Fapis\u002F#operation\u002FmeetingLocalRecordingJoinToken)\n\n## Quick Start\n\n### 1. Download & Extract SDK\n\n```bash\n# Download from https:\u002F\u002Fmarketplace.zoom.us\u002F\ntar xzf zoom-meeting-sdk-linux_x86_64-{version}.tar\n\n# Organize files\nmkdir -p demo\u002Finclude\u002Fh demo\u002Flib\u002Fzoom_meeting_sdk\ncp -r h\u002F* demo\u002Finclude\u002Fh\u002F\ncp lib*.so demo\u002Flib\u002Fzoom_meeting_sdk\u002F\ncp -r qt_libs demo\u002Flib\u002Fzoom_meeting_sdk\u002F\ncp translation.json demo\u002Flib\u002Fzoom_meeting_sdk\u002Fjson\u002F\n\n# Create required symlink\ncd demo\u002Flib\u002Fzoom_meeting_sdk && ln -s libmeetingsdk.so libmeetingsdk.so.1\n```\n\n### 2. Initialize & Auth\n\n```cpp\n#include \"zoom_sdk.h\"\n\nUSING_ZOOM_SDK_NAMESPACE\n\n\u002F\u002F Initialize SDK\nInitParam init_params;\ninit_params.strWebDomain = \"https:\u002F\u002Fzoom.us\";\ninit_params.enableLogByDefault = true;\ninit_params.rawdataOpts.audioRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\nInitSDK(init_params);\n\n\u002F\u002F Authenticate with JWT\nAuthContext auth_ctx;\nauth_ctx.jwt_token = your_jwt_token;\nCreateAuthService(&auth_service);\nauth_service->SDKAuth(auth_ctx);\n```\n\n### 3. Join Meeting\n\n```cpp\n\u002F\u002F In onAuthenticationReturn callback\nvoid onAuthenticationReturn(AuthResult ret) {\n    if (ret == AUTHRET_SUCCESS) {\n        JoinParam join_param;\n        join_param.userType = SDK_UT_WITHOUT_LOGIN;\n        \n        auto& params = join_param.param.withoutloginuserJoin;\n        params.meetingNumber = 1234567890;\n        params.userName = \"Bot\";\n        params.psw = \"password\";\n        params.isVideoOff = true;\n        params.isAudioOff = false;\n        \n        meeting_service->Join(join_param);\n    }\n}\n```\n\n### 4. Access Raw Data\n\n```cpp\n\u002F\u002F In onMeetingStatusChanged callback\nvoid onMeetingStatusChanged(MeetingStatus status, int iResult) {\n    if (status == MEETING_STATUS_INMEETING) {\n        auto* record_ctrl = meeting_service->GetMeetingRecordingController();\n        \n        \u002F\u002F Start raw recording (enables raw data access)\n        if (record_ctrl->CanStartRawRecording() == SDKERR_SUCCESS) {\n            record_ctrl->StartRawRecording();\n            \n            \u002F\u002F Subscribe to audio\n            auto* audio_helper = GetAudioRawdataHelper();\n            audio_helper->subscribe(new MyAudioDelegate());\n            \n            \u002F\u002F Subscribe to video\n            IZoomSDKRenderer* video_renderer;\n            createRenderer(&video_renderer, new MyVideoDelegate());\n            video_renderer->setRawDataResolution(ZoomSDKResolution_720P);\n            video_renderer->subscribe(user_id, RAW_DATA_TYPE_VIDEO);\n        }\n    }\n}\n```\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| **Headless Operation** | No GUI, perfect for Docker\u002Fserver deployments |\n| **Raw Audio (PCM)** | Capture mixed or per-user audio at 32kHz |\n| **Raw Video (YUV420)** | Capture video frames in contiguous planar format |\n| **GLib Event Loop** | Async callback handling |\n| **Docker Support** | Pre-built Dockerfiles for CentOS\u002FUbuntu |\n| **PulseAudio Virtual Devices** | Audio in headless environments |\n| **Breakout Rooms** | Programmatic breakout room management |\n| **Chat** | Send\u002Freceive in-meeting chat |\n| **Recording Control** | Local, cloud, and raw recording |\n\n## Critical Gotchas & Best Practices\n\n### ⚠️ CRITICAL: PulseAudio for Docker\u002FHeadless\n\n**The #1 issue for raw audio in Docker:**\n\nRaw audio requires PulseAudio and a config file, even in headless environments.\n\n**Solution**:\n```bash\n# Install PulseAudio\napt-get install -y pulseaudio pulseaudio-utils\n\n# Create config file\nmkdir -p ~\u002F.config\ncat > ~\u002F.config\u002Fzoomus.conf \u003C\u003C EOF\n[General]\nsystem.audio.type=default\nEOF\n\n# Start PulseAudio with virtual devices\npulseaudio --start --exit-idle-time=-1\npactl load-module module-null-sink sink_name=virtual_speaker\npactl load-module module-null-sink sink_name=virtual_mic\n```\n\nSee: [references\u002Flinux-reference.md#pulseaudio-setup](references\u002Flinux-reference.md)\n\n### Raw Recording Permission Required\n\nUnlike Video SDK, Meeting SDK requires explicit permission to access raw data:\n\n```cpp\n\u002F\u002F MUST call StartRawRecording() first\nauto* record_ctrl = meeting_service->GetMeetingRecordingController();\n\nSDKError can_record = record_ctrl->CanStartRawRecording();\nif (can_record == SDKERR_SUCCESS) {\n    record_ctrl->StartRawRecording();\n    \u002F\u002F NOW you can subscribe to audio\u002Fvideo\n} else {\n    \u002F\u002F Need: host\u002Fco-host status OR recording token\n}\n```\n\n**Ways to get permission**:\n1. Bot is host\u002Fco-host\n2. Host grants recording permission\n3. Use `recording_token` parameter (get via [REST API](https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Fapis\u002F#operation\u002FmeetingLocalRecordingJoinToken))\n4. Use `app_privilege_token` (OBF) when joining\n\n### GLib Main Loop Required\n\nSDK callbacks execute via GLib event loop:\n\n```cpp\n#include \u003Cglib.h>\n\n\u002F\u002F Setup main loop\nGMainLoop* loop = g_main_loop_new(NULL, FALSE);\n\n\u002F\u002F Add timeout for periodic tasks\ng_timeout_add_seconds(10, check_meeting_status, NULL);\n\n\u002F\u002F Run loop (blocks until quit)\ng_main_loop_run(loop);\n```\n\n**Without GLib loop**: Callbacks never fire, join hangs indefinitely.\n\n### Heap Memory Mode Recommended\n\nAlways use heap mode for raw data to avoid stack overflow with large frames:\n\n```cpp\ninit_params.rawdataOpts.videoRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\ninit_params.rawdataOpts.shareRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\ninit_params.rawdataOpts.audioRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;\n```\n\n### Thread Safety\n\nSDK callbacks execute on SDK threads:\n- Don't perform heavy operations in callbacks\n- Don't call `CleanUPSDK()` from within callbacks\n- Use thread-safe queues for data passing\n- Use mutexes for shared state\n\n## Production Architectures\n\n### Transcription Bot\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-1](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → StartRawRecording → Subscribe Audio → \nStream to AssemblyAI\u002FWhisper → Generate Real-time Transcript\n```\n\n### Recording Bot\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-2](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → StartRawRecording → Subscribe Audio+Video → \nWrite YUV+PCM → FFmpeg Merge → Upload to Storage\n```\n\n### AI Meeting Assistant\n\n**See**: [concepts\u002Fhigh-level-scenarios.md#scenario-3](concepts\u002Fhigh-level-scenarios.md)\n\n```\nJoin Meeting → Real-time Transcription → AI Analysis → \nExtract Action Items → Generate Summary\n```\n\n## Sample Applications\n\n**Official Repositories**:\n\n| Sample | Description | Link |\n|--------|-------------|------|\n| **Raw Recording Sample** | Traditional C++ approach with config.txt | [GitHub](https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample) |\n| **Headless Sample** | Modern TOML-based with CLI, Docker Compose | [GitHub](https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample) |\n\n**What Each Demonstrates**:\n\n- **Raw Recording Sample**: Complete raw data workflow, PulseAudio setup, Docker multi-distro support\n- **Headless Sample**: AssemblyAI integration, Anthropic AI, production-ready config management\n\n## Documentation Library\n\n### Core Concepts\n- **[linux.md](linux.md)** - Quick start & core workflow\n- **[concepts\u002Fhigh-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md)** - Production bot architectures\n- **[meeting-sdk-bot.md](meeting-sdk-bot.md)** - Resilient bot with retry logic\n\n### Platform Reference\n- **[references\u002Flinux-reference.md](references\u002Flinux-reference.md)** - Dependencies, CMake, Docker, troubleshooting\n\n### Authentication\n- **[..\u002Freferences\u002Fauthorization.md](..\u002Freferences\u002Fauthorization.md)** - SDK JWT generation\n- **[..\u002Freferences\u002Fbot-authentication.md](..\u002Freferences\u002Fbot-authentication.md)** - Bot token types (ZAK, OBF, JWT)\n\n### Advanced Features\n- **[..\u002Freferences\u002Fbreakout-rooms.md](..\u002Freferences\u002Fbreakout-rooms.md)** - Programmatic breakout rooms\n- **[..\u002Freferences\u002Fai-companion.md](..\u002Freferences\u002Fai-companion.md)** - AI Companion controls\n\n## Common Issues\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| **No audio in Docker** | Missing PulseAudio config | Create `~\u002F.config\u002Fzoomus.conf` |\n| **Raw recording denied** | No permission | Use host\u002Fco-host OR recording token |\n| **Callbacks not firing** | Missing GLib main loop | Add `g_main_loop_run()` |\n| **Build errors (XCB)** | Missing X11 libraries | Install libxcb packages |\n| **Segfault on auth** | OpenSSL version mismatch | Install libssl1.1 |\n\n**Complete troubleshooting**: [references\u002Flinux-reference.md#troubleshooting](references\u002Flinux-reference.md)\n\n## Resources\n\n- **Official Docs**: https:\u002F\u002Fdevelopers.zoom.us\u002Fdocs\u002Fmeeting-sdk\u002Flinux\u002F\n- **API Reference**: https:\u002F\u002Fmarketplacefront.zoom.us\u002Fsdk\u002Fmeeting\u002Flinux\u002F\n- **Dev Forum**: https:\u002F\u002Fdevforum.zoom.us\u002F\n- **GitHub Samples**: \n  - https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-linux-raw-recording-sample\n  - https:\u002F\u002Fgithub.com\u002Fzoom\u002Fmeetingsdk-headless-linux-sample\n\n---\n\n**Need help?** Start with [linux.md](linux.md) for quick start, then explore [high-level-scenarios.md](concepts\u002Fhigh-level-scenarios.md) for production patterns.\n\n## Operations\n\n- [RUNBOOK.md](RUNBOOK.md) - 5-minute preflight and debugging checklist.\n",{"name":5,"triggers":57,"description":7,"user-invocable":53},[58,59,32,60,61,62,63,64],"linux meeting bot","headless zoom bot","zoom raw recording linux","meeting transcription bot","zoom docker bot","pulseaudio zoom","meeting sdk raw data","main","e605d8ddbfb688da57dfaaceebd93f12a64ef1d3","partner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux",3918,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-11 11:16:59",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add anthropics\u002Fknowledge-work-plugins --skill meeting-sdk\u002Flinux",{"tool":79,"command":80},"bunx","bunx skills add anthropics\u002Fknowledge-work-plugins --skill meeting-sdk\u002Flinux",{"tool":82,"command":83},"pnpm","pnpm dlx skills add anthropics\u002Fknowledge-work-plugins --skill meeting-sdk\u002Flinux","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002FSKILL.md",true,[87,93,97,101,105],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"concepts\u002Fhigh-level-scenarios.md","REFERENCE","参考文档",15179,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002Fconcepts\u002Fhigh-level-scenarios.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"linux.md",11275,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002Flinux.md",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"meeting-sdk-bot.md",30524,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002Fmeeting-sdk-bot.md",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Flinux-reference.md",21151,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002Freferences\u002Flinux-reference.md",{"path":106,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":107,"sourceHtmlUrl":108},"RUNBOOK.md",2350,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fpartner-built\u002Fzoom-plugin\u002Fskills\u002Fmeeting-sdk\u002Flinux\u002FRUNBOOK.md",[110,137,162,184,209,235],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":52},"01M718Y97HCGW12Q53PSJDY03W","ticket-deflector","Reads a forwarded customer email or ticket, pulls order and refund status from a payments connector (PayPal, Square, or Stripe) or Shopify, account history from the CRM, and open tickets from a support desk (Zoho Desk), drafts a tone-matched reply in the owner's writing voice, and can issue a refund through the payments connector with explicit owner approval. With Shopify connected it also runs a proactive order-triage mode that surfaces orders needing attention — unfulfilled past the promised window, payment problems, pending refunds, stuck shipments — and drafts the next action for each before the customer has to ask. Use when the user says \"draft a response,\" \"answer this customer,\" \"where's my order,\" \"I want a refund,\" \"check my orders,\" or \"anything about to blow up.\"","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fticket-deflector\u002FSKILL.md",[],[117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136],"ticket","ticket deflector","mode","up","payments","open","writing","when","workflow","ask","Connector","text","mail","window","next","customer","support","crm","past","read",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":52},"01M718Y55HFAN5705ME5VEDZ9K","tax-season-organizer","Prepares tax-season materials for the owner's accountant, not tax advice. US federal tax; a non-US business gets its closed-books packet instead. Two modes: (1) quarterly estimated tax from YTD net income in the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books); (2) year-end 1099 prep, scanning the ledger, PayPal, and Stripe for contractors paid over USD 600 into a 1099-NEC list with missing W-9 flags.\nAny tax request routes first to \u002Ftax-prep, which confirms the books are closed and reconciled before running this skill. Use this skill directly only when the owner says the period's books are already closed: \"books are closed, now do the 1099s,\" \"run the quarterly estimate off the closed numbers,\" or \"just the contractor W-9 list.\"","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Ftax-season-organizer\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152,153,124,154,155,156,157,158,136,159,160,161],"tax season organizer","tax","us federal","which","netsuite","paid","end","usd","only","now","books","xero","scanning","run","request","flags","list","stripe",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":52},"01M718Y13VVPHDD9NTDBVFJ2AZ","tax-prep","Prepares tax materials as a two-link chain — month-end-prep confirms the books are closed and reconciled first, then tax-season-organizer calculates the quarterly estimated payment or builds the year-end 1099-NEC list and accountant packet from those closed numbers. Requires a ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books); uses Gusto, PayPal, and Stripe when connected, else CSV upload. US federal tax math; a non-US business gets the closed-books packet. Prep material for a CPA, never tax advice, nothing filed. Trigger on \"quarterly taxes,\" \"estimated tax payment,\" \"how much should I set aside,\" \"1099s,\" \"1099-NEC,\" \"W-9s,\" \"year-end tax prep,\" \"get my books ready for my accountant,\" any phrasing that suggests a tax deadline is coming, or a question about net profit or YTD income that sounds like worry about a tax bill. An owner who says the period's books are already closed routes to tax-season-organizer directly.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Ftax-prep\u002FSKILL.md",[],[169,145,170,171,146,172,173,148,174,175,176,177,178,38,179,150,180,181,182,183],"tax prep","prep","SET","as","ready","never","zoho books","get","chain","profit","trigger","material","question","paypal","business",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":52},"01M718XWTWQZ01GYSG9T8RW8TW","speed-to-lead","Makes sure no inbound lead goes unanswered. Watches web forms, the shared inbox, and the CRM for new inquiries, qualifies each one against the owner's criteria, drafts a reply in the owner's voice with real meeting times for the owner to approve and send, routes anything hot to a human right away, and logs the whole thing to the CRM. Never sends on its own. Built to run on a schedule so overnight inquiries are drafted and sorted by morning, and works from forwarded or pasted inquiries when no connector is available. Use this whenever the owner is worried about inbound leads or response time — including phrasings like \"leads are going cold,\" \"did anyone answer that inquiry,\" \"I keep missing form submissions,\" \"nothing falls through the cracks,\" \"handle my inbound,\" \"respond to this lead,\" or \"we lose people because nobody gets back fast enough.\" Reach for it for a single unanswered inquiry as readily as for a standing setup.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fspeed-to-lead\u002FSKILL.md",[190],{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[192,193,194,195,196,197,174,198,199,200,201,202,203,204,124,205,206,127,207,208],"speed to lead","lead","speed","shared","back","cold","time","inbox","send","respond","new","web forms","people","schedule","logs","sure","human",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":218,"publishedAt":52},"01M718XQYMN1KY3TPS33967FK0","social-content-engine","Runs the owner's content operation as a standing thing rather than a one-off: keeps a rolling posting calendar, learns the owner's voice, generates on-brand Canva graphics, writes captions that sound like them, repurposes one asset into every channel format, and stages posts for approval instead of publishing on its own. Pulls product photos and prices from Shopify when connected; with no connectors, drafts the calendar and asset briefs for manual posting. Use this whenever the owner talks about posting, content, or social — including \"I need to post more,\" \"we've gone quiet on Instagram,\" \"what should we post this month,\" \"make the content,\" \"give me a month of posts,\" \"write this in my voice,\" \"repurpose this,\" or \"set up our content calendar.\" Reach for it for a single post as readily as for a full quarter. One handoff: a finished, approved campaign brief goes to canva-creator; this skill owns the standing operation.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fsocial-content-engine\u002FSKILL.md",[215],{"categoryNo":216,"categoryName":217,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[219,220,221,222,223,224,171,225,226,227,228,120,229,124,230,231,232,136,233,234],"social","social content engine","engine","content engine","social content","content","brief","posts","Captions","prices","campaign","me","product","calendar","write","drafts",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":241,"publishedAt":52},"01M718XMPJVH0EVRVP998BVZPC","smb-router","The front door to the Small Business plugin. Listens to what the owner needs right now — vague or specific — and routes them to the best skill or slash command for the moment. Also serves as a guide: explains what's available, suggests what to try next, and adapts recommendations based on stored business context. Trigger whenever the owner asks \"what can you do,\" \"help me with my business,\" \"what should I focus on,\" \"I don't know where to start,\" or any open-ended business request that doesn't clearly match a single skill.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fsmb-router\u002FSKILL.md",[],[242,243,244,172,245,38,179,246,122,247,153,183,248,249,250,251,252,230,253,131],"router","smb","smb router","do","front","single","you","vague","can","with","plugin","focus"]