hoang-ai-marketing

Convert a single MP3 voiceover file into a single HeyGen avatar lip-sync MP4 video. Single-purpose — no planning, no SRT, no chunking, no Remotion compositing. Uses HeyGen MCP tools exclusively (no direct REST API calls). Locks avatar look and voice ID to a fixed allowlist. USE WHEN user says "tạo video heygen từ mp3", "mp3 to heygen", "heygen mp4 từ audio", "convert mp3 sang heygen video", "tạo avatar video từ file mp3", "lip sync mp3 heygen", "biến mp3 thành video heygen", or any time the user has exactly one MP3 file and wants exactly one HeyGen avatar MP4 out.

Convert a script (Vietnamese or English text) directly into a single HeyGen avatar video — HeyGen handles TTS using the locked ElevenLabs voice, then lip-syncs the avatar. Single-purpose — no MP3 generation, no SRT, no chunking, no Remotion. Uses HeyGen MCP tools exclusively (no direct REST API calls). Avatar look and voice ID are fixed allowlists. USE WHEN user says "tạo video heygen từ script", "script to heygen", "heygen mp4 từ text", "convert script sang heygen video", "tạo avatar video từ script", "heygen text to video", "biến script thành video heygen", or any time the user has script text (not an MP3) and wants exactly one HeyGen avatar MP4 out.

End-to-end short-video pipeline — từ kịch bản (Việt/Anh) ra MP4 TikTok/Reels 9:16 hoàn chỉnh. Orchestrator 3 phase ghép 3 skill có sẵn — (1) `mkt-elevenlabs-tts-to-mp3` đọc script bằng voice của Hoàng, (2) checkpoint user duyệt MP3, (3) `heygen-mp3-to-mp4` lip-sync avatar HeyGen, (4) delegate Phase 3 packaging cho sub-agent `mkt-full-video-phase3-packager` (transcribe + scene outline + checkpoint + fan-out N scene writers parallel + scaffold + preview Studio). USE WHEN user nói "tạo full video từ script", "script to tiktok video", "pipeline full video heygen + hyperframe", "tạo video từ kịch bản đến mp4", "elevenlabs heygen hyperframe full pipeline", "kịch bản ra video tiktok", hoặc có sẵn 1 script + (optional) ảnh b-roll và muốn ra MP4 9:16 đóng gói có captions, SFX, b-roll.

Tạo single-page landing website (HTML đơn file dùng Tailwind CDN + Lucide icons + Chart.js) trình bày nội dung video chia sẻ kiến thức AI/tech theo design language của Claude AI. Body dark navy theme + accent màu thương hiệu (Claude orange, DeepSeek blue, OpenAI green, etc.); infographic placeholder dùng style cream hand-drawn editorial của Claude AI. Scroll-down dọc, vertical connector lines giữa section, big hero typography với gradient highlight cho keyword thương hiệu, 3-column stats cards, Chart.js benchmarks, image placeholder kèm prompt ẩn (chữ tiếng Việt có dấu, giữ tiếng Anh cho brand/tech) — chỉ hiện nút Copy. Khi user đưa transcript / topic / tài liệu, skill tự outline section, viết Vietnamese copy, viết image prompt Claude-AI-editorial-style, build HTML. Optional bước cuối — gọi mkt-broll-image để generate ảnh thật qua AI33 (Nano Banana Pro). USE WHEN user says 'tạo landing page kiến thức', 'website 1 trang scroll', 'tạo trang trình bày video AI/tech', 'Claude AI style landing', 'transcript thành

Compose final short video from production plan + HeyGen avatar clips + Grok/custom visuals using Remotion. Builds props JSON, opens Remotion Studio preview for user to review, and only renders final MP4 when user approves. Handles interleaving avatar/visual clips, captions with effects, BGM, sound effects, and progress bar. USE WHEN user says 'ghép video remotion', 'compose video', 'editor video ngắn', 'remotion compose', 'ghép clip heygen', 'tạo video cuối cùng', 'preview video remotion', 'mở remotion studio'.

Create HeyGen AI avatar video clips from a production plan. Takes production-plan.json + MP3 voiceover, splits audio into avatar chunks, uploads to HeyGen, generates lip-synced avatar videos, and downloads completed clips. This skill ONLY handles HeyGen avatar production — use plan-short-video-edit for planning and heygen-remotion-short-video-editor for final composition. USE WHEN user says 'tạo video heygen', 'heygen avatar clips', 'tạo avatar video', 'upload heygen', 'generate heygen clips', 'tạo clip avatar từ plan'.

End-to-end AI video production workflow — finalized script → MP3 voiceover → SRT + segments → production plan → HeyGen avatar clips → Remotion composition → final MP4. Expects a ready-to-voice short video script as input (script writing is handled upstream). Handles MP3 voiceover and SRT extraction directly, then delegates planning and editing to specialized sub-agents (video-ai-planner, video-ai-editor) with user checkpoints between phases. USE WHEN user says 'tạo video AI', 'full video pipeline', 'video end to end', 'tạo video hoàn chỉnh từ script', 'full AI video', 'video từ script đến render', 'tạo video ngắn hoàn chỉnh', 'pipeline video đầy đủ', 'sản xuất video AI từ script', 'make full video', 'produce complete video', 'full ai video workflow'.

Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media handling. Use when writing Remotion code, building video generation pipelines, or creating data-driven video templates.

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Send messages, photos, and files to Telegram via Bot API. USE WHEN user says 'gửi telegram', 'send telegram', 'thông báo telegram', 'notify telegram', 'gửi tin nhắn telegram', 'báo cho tôi qua telegram', 'telegram notification', 'push to telegram', 'gửi file telegram', 'gửi ảnh telegram', or when a task completes and user wants notification. Also use after completing daily summaries, research reports, or any task where the user wants results delivered to Telegram.