hoanghd218

Find breakout YouTube videos with 2x+ view-to-subscriber ratio. USE WHEN user says 'find breakout videos', 'search for breakout video ideas', 'find viral video angles', 'youtube breakout research', 'find videos that overperformed', 'research video ideas for breakout potential', 'find underperforming videos that went viral', 'youtube video opportunity research'.

Tìm top GitHub trending repositories (daily/weekly/monthly) để làm content AI/tech. Scrape github.com/trending, lọc theo language, lưu JSON + Markdown. USE WHEN user says 'github trend hôm nay', 'top github trending', 'tìm github trending', 'github trending daily', 'top 10 github repo', 'research github trend', 'github trend for content', 'lấy github trending', 'github hot hôm nay', 'trending repo'.

Phân tích nội dung bài viết Facebook, đưa ra prompt tạo ảnh minh họa bằng Nano Banana Pro. Hỗ trợ dạng: các bước, so sánh, ẩn dụ, concept.

Generates detailed prompts for creating high-quality educational infographics in tech/modern style (Health, AI, Productivity).

Create landing page content for online assessment/quiz-based lead generation. Use when users need landing page copy, quiz questions, and dynamic results pages that convert visitors into qualified leads. Input can be a niche, product, service, or target audience. Output is a complete landing page content system (hook, value proposition, credibility, CTA, 15 quiz questions, and dynamic results page) following the ScoreApp assessment methodology.

Aggregate AI news from Perplexity, GitHub Trending, and X.com (via xAI Grok) into a unified digest. USE WHEN user says 'ai news today', 'tin AI hôm nay', 'research AI news', 'tìm tin AI', 'aggregate AI news', 'github trending AI', 'ai news digest'.

Transcribe an MP3 voiceover into an SRT subtitle file and a word-level segments JSON using local OpenAI Whisper. Input is a single MP3 path; output is `<stem>.srt` + `<stem>_segments.json` written next to the MP3 (or to a custom output dir). USE WHEN the user says 'extract srt from mp3', 'trích srt từ mp3', 'transcribe voiceover', 'tạo file srt và segments', 'whisper transcribe', 'bóc transcript có timestamp', 'extract voiceover segments', 'tách SRT từ audio', or any time a downstream skill (plan-short-video-edit, heygen-remotion-short-video-editor) needs an SRT + word-level segments JSON from a voiceover MP3 and one does not already exist.

Extract wisdom from books and create viral Facebook wisdom posts in Vietnamese. Supports 6 proven formats: Progressive Reduction, Never Too Late List, Contrast Pairs, Numbered Skills List, Intangible Assets, Bold Statement. Input is a book name, book excerpt, knowledge passage, or topic. Output is 2-3 ready-to-post Facebook posts with caption + image text. USE WHEN user says 'tạo bài từ sách', 'book to post', 'bóc kiến thức từ sách', 'wisdom post', 'tạo content từ sách', 'bài viết từ sách', 'extract book wisdom', 'sách ra content', 'tạo post triết lý', 'content sách', 'viết bài từ kiến thức sách'.

Nâng cấp xác thực trang /admin (và /admin/affiliates) của landing page Next.js App Router từ **password popup** (ADMIN_PASSWORD + header x-admin-pass) sang **đăng nhập Google qua Supabase Auth + allowlist** — chỉ email nằm trong bảng `admin_users` mới vào được, có khái niệm **super admin** (hard-code, không tự xoá được mình) và tab **Quản trị viên** ngay trong dashboard để super admin thêm/xoá quản trị viên khác. Skill scaffold: migration Supabase (`admin_users` table RLS deny-all + hàm SECURITY DEFINER `is_admin_email`), `lib/admin-auth.ts` (`requireAdmin`/`requireSuperAdmin`/`adminAuthError` verify Bearer token offline qua getClaims), `lib/admin-client.ts` (browser PKCE OAuth + `loginWithGoogle`/`logout`/`adminFetch`), `lib/admin-users.ts` (allowlist CRUD + `isSuperAdmin`), 2 API route (`/api/admin/me`, `/api/admin/admin-users`), component `components/AdminUsersTab.tsx` (tab Quản trị viên). Sau đó PATCH các route `/api/admin/*` đã có (thay `checkAdminPass()` → `requireAdmin()`) và PATCH `app/admin/page.tsx`

Scaffold trang `/admin` CRM-style trực quan vào Next.js project (Supabase backend) — KHÔNG còn variant Vercel KV. Layout 1CRM-inspired: sidebar 3 tab (Tổng quan / Khách hàng / Email marketing) + popup nhập mã đăng nhập. **Tab Tổng quan**: 4 KPI cards (Tổng leads / Đã thanh toán / Tỷ lệ chuyển đổi / Doanh thu) có delta arrow vs kỳ trước, line chart leads+paid+revenue theo ngày dùng `recharts`, donut trạng thái paid/pending/expired, period selector pill 7d/30d/90d, list 5 thanh toán gần nhất. **Tab Khách hàng**: bảng leads + search + filter trạng thái + filter ngày + CSV export. **Tab Email marketing**: form soạn chiến dịch (tên + tiêu đề + body chọn định dạng **văn bản thường HOẶC HTML** + placeholder `{{name}}` + audience 4 loại all/paid/pending/last_days + tên người gửi) — có nút **Xem trước** mở modal iframe render đúng email thật (text → auto convert + wrap khung; HTML fragment → wrap khung, HTML đầy đủ giữ nguyên) → gửi bulk qua SMTP (reuse `nodemailer` của `biz-email-setup` — KHÔNG cài provider mới), log

Thêm hệ thống affiliate (tiếp thị liên kết) cho landing page Next.js App Router đã có Sepay payment + Supabase lead store — đối tác gắn link aff `?aff=CODE`, skill tự động gán đơn theo last-touch cookie 30 ngày, tính hoa hồng theo tier (Pro 30% / Elite 40%, chỉnh được), tạo bản ghi hoa hồng khi đơn được thanh toán, theo dõi trạng thái chi trả (chờ duyệt → đã duyệt → đã trả). Skill scaffold 3 bảng Supabase (affiliates / affiliate_clicks / affiliate_commissions) + ALTER `leads` thêm cột `aff_code`, thư viện `lib/affiliate.ts`, component `AffiliateTracker` bắt `?aff=` ghi cookie + đếm click, 3 API route (`/api/affiliate/click` public, `/api/affiliate` portal data, `/api/admin/affiliates` quản trị), trang quản trị `/admin/affiliates` (thêm/sửa đối tác, xem doanh thu + hoa hồng từng aff, duyệt + đánh dấu đã trả hoa hồng) và portal đối tác `/affiliate` (đối tác đăng nhập bằng mã aff + email để tự xem link, click, đơn giới thiệu, hoa hồng). Patch 4 file có sẵn (`leads-supabase.ts`, `api/register`, `api/sepay-webhook

Deploy landing page / website (React, Next.js, Vite, static HTML) lên Vercel — tự kiểm tra Vercel CLI hoặc Vercel MCP đã cài chưa, nếu chưa thì cài qua npm/pnpm và hướng dẫn user authenticate (vercel login), tự detect framework (Next.js / Vite / CRA / static), auto-generate vercel.json khi cần, chạy `vercel --prod`, trả về live URL + inspect URL + hướng dẫn custom domain. USE WHEN user says 'deploy lên vercel', 'đẩy landing page lên vercel', 'publish website', 'go live', 'deploy nextjs', 'deploy react', 'deploy vite', 'tạo URL live', 'đưa lên production', 'biz-deploy-vercel', 'host landing page', 'vercel deploy', 'ship lên vercel', 'đẩy code lên vercel'. Skill này áp dụng cho cả case dùng Vercel CLI lẫn Vercel MCP server.

Setup SMTP-based email auto-responder cho landing page bán hàng — tự động gửi email sau khi user điền form (tên/SĐT/email), KHÔNG cố định vào provider nào. Skill này (1) hỏi user chọn SMTP provider (Gmail/Google Workspace, Resend SMTP, SendGrid, Mailgun, Brevo, Zoho, hoặc SMTP custom của hosting VN) và detect Next.js stack đang dùng, (2) đọc context từ `offer.json` + `conversion-copy.md` (từ `/biz-offer-alex-hormozi`) HOẶC đọc trực tiếp Next.js project đã build qua `ui-ux-pro-max` (file `app/page.tsx`) HOẶC đọc HTML landing page đã deploy để hiểu offer, dream outcome, mechanism, bonus. Lưu ý: skill `biz-sales-page-layout` đã DEPRECATED 2026-05-14 — pipeline mới skip layout/copy.json, (3) **draft 2 email**: email A — auto-responder gửi cho lead (warm welcome + deliver lead magnet/booking confirm/payment link tuỳ offer type), email B — notification gửi cho owner (lead alert + thông tin liên hệ), (4) **show draft cho user duyệt và chỉnh sửa** trước khi wire vào code, (5) cài `nodemailer` và wire form HTML/React

Thêm đa ngôn ngữ (i18n) cho landing page Next.js đã build sẵn — biến trang viết bằng 1 ngôn ngữ thành trang đa ngôn ngữ với nút pill chuyển ngôn ngữ cố định góc trên bên phải, đổi tức thì không reload không đổi URL. Workflow 8 phase: (0) detect Next.js App Router project trong output/ — TS/Tailwind/src wrapper/path alias @/, hỏi user chọn nếu có nhiều landing page; (1) **PHỎNG VẤN user qua AskUserQuestion**: hỏi muốn hỗ trợ ngôn ngữ nào (gợi ý Tiếng Việt / English / 中文 / 한국어 — và Other cho 日本語, Thái...) và ngôn ngữ nào làm mặc định hiện khi mới vào trang; (2) quét toàn bộ copy hardcode trong app/page.tsx + mọi component con (Hero/Pricing/FAQ/Footer/form...) + metadata layout.tsx, gom thành dictionary key theo section; (3) **tự dịch** sang mọi ngôn ngữ đã chọn — bản địa hoá marketing chứ không dịch máy, giữ nguyên tên brand + giá VND + SĐT + URL; (4) scaffold hệ thống i18n client-side trong app/i18n/ — React Context + JSON dictionaries + localStorage + auto-detect ngôn ngữ trình duyệt, KHÔNG đổi URL, KHÔNG đụn

Cài chatbot AI dạng floating widget góc dưới phải vào project Next.js có sẵn (App Router hoặc Pages Router), responsive đầy đủ web + tablet + mobile, gọi LLM qua OpenRouter (mặc định google/gemini-3-flash-preview, có thể đổi sang anthropic/claude-sonnet-4.6), streaming response, RENDER MARKDOWN trong assistant bubble (bold / list / link / code) qua react-markdown + remark-gfm — KHÔNG hiện raw **bold** dạng text — có knowledge base từ FAQ + tài liệu sản phẩm/khóa học do user cung cấp để chatbot tự động trả lời khách hàng, và TỰ ĐỘNG EXTRACT + LƯU LEAD (tên + SĐT + email) vào Upstash Redis/Vercel KV dưới namespace `chat-lead:{phone}` khi user cung cấp đầy đủ thông tin trong chat — dedupe theo SĐT, TTL 90 ngày, fire-and-forget không block stream. Skill tự detect số lượng project Next.js — nếu có nhiều hơn 1 sẽ hỏi user chọn project nào để cài; tự detect TypeScript/JS, App Router/Pages Router, Tailwind/CSS module, KV/Upstash availability (skip auto-save nếu chưa có); tự install react-markdown + remark-gfm; tự app

Đóng gói offer **không thể chối từ** (grand slam offer) theo phương pháp Alex Hormozi ($100M Offers) — nhận input pains/gains/customer jobs theo Value Proposition Design (Osterwalder 2014) + sản phẩm/dịch vụ, rồi sinh ra: (1) markdown report tiếng Việt đầy đủ Value Equation scoring + Core Offer + 3-4 Bonus stack + Guarantee + Urgency + Pricing, (2) offer.json structured cho pipeline downstream (`ui-ux-pro-max` build sales page production-ready), (3) conversion copy block (headline + subheadline + CTA) sẵn sàng paste landing page. 2 input mode: (B) user paste sẵn pains + gains + product, (C) user chỉ có sản phẩm — skill phỏng vấn theo VPD framework để surface pain/gain trước. Bonus stack mode hybrid: skill brainstorm 5-7 candidate có justification value rồi user pick/chỉnh 3-4 cái. Tiếng Việt thuần (xưng anh/chị), giá VND charm pricing (X99K), 3-tier decoy structure. USE WHEN user says 'đóng gói offer', 'tạo offer', 'thiết kế offer Hormozi', 'grand slam offer', 'value stack', 'offer stack', 'làm offer hấp dẫn'

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

Audit bài Facebook / Reels / YouTube để phát hiện 4 downward drivers (over-branding, over-production, stock imagery, standardized aesthetic) + frequency-over-quality. Mỗi anti-pattern bị drop ~75% performance nếu hiện diện. USE WHEN user says 'audit content', 'check anti pattern', 'content có lỗi gì không', 'kiểm tra over branding', 'vì sao video bị chết', 'vì sao post không ai xem', 'content audit', 'kiểm tra chất lượng content'.

Tìm viral pattern ở ngành khác (bác sĩ, luật sư, tài chính, bất động sản, thủ công) có thể apply cho niche AI/automation của Hoang. Ngách AI educator VN còn ít format được khai thác — cross-industry adaptation là blue ocean. USE WHEN user says 'tìm format ngành khác', 'cross industry research', 'học format từ ngành khác', 'blue ocean format', 'tìm format chưa ai làm', 'adapt format từ niche khác', 'cross industry viral'.

Rewrite CTA kiểu autocratic (Mua ngay! Follow ngay! Đăng ký liền!) sang 3 variants Democratic / Benevolent / Laissez-faire — reach 85% dân số thay vì chỉ 5% (action-based). Áp dụng cho landing page, caption FB, CTA video, email. USE WHEN user says 'rewrite cta', 'sửa cta', 'cta không autocratic', 'viết lại kêu gọi hành động', 'cta cho landing page', 'cta nhẹ nhàng hơn', 'inclusive cta', 'cta democratic benevolent'.

Bắt đầu ideation từ Effect on Viewer (emotion/reaction mong muốn) → reverse-engineer ra format + hook + tactic + Last Dab. Ngược với cách thường (có message → tìm cách truyền đạt). Áp dụng cho FB post / Reels / YouTube. USE WHEN user says 'ideation từ cảm xúc', 'start với eov', 'muốn viewer cảm thấy x', 'reverse engineer content', 'eov đi trước', 'thiết kế cảm xúc trước', 'design for emotion', 'eov first'.

Viết bài Facebook blend Feelings (30%) + Facts (25%) + Fun (20%) — tổng ≥75% — theo 5 Rules Communication Algorithm của Brendan Kane. Tự score % từng style sau khi viết + self-audit. Reach 85% audience thay vì chỉ 30% bài khô fact-only. USE WHEN user says 'viết fb post 5 rules', 'post feelings facts fun', 'viết fb blend cảm xúc data vui', 'communication algorithm post', 'fb post reach 85%', 'post có đủ 3 style', 'bài fb đa style'.

Viết bài Facebook theo Golden Triangle của Brendan Kane: Personal story + Evidence/data + Timeless wisdom. Phù hợp Pillar 4 Mindset + P2 One Person Business. Kết hợp 3 element tạo post có depth + credibility + universal appeal. USE WHEN user says 'viết facebook golden triangle', 'bài facebook 3 tầng', 'personal + data + wisdom', 'post có chiều sâu', 'bài mindset', 'bài triết lý facebook', 'golden triangle post', 'fb post với câu chuyện và data'.

Generate Amazon KDP A+ Content ("From the Publisher") modules tailored to a coloring book's theme. Produces aplus_content.json (module copy + 970x600 image prompts) and appends the A+ image prompts into the book's image_prompts.json. USE WHEN user says 'tao content A+', 'create A+ content', 'kdp a plus', 'from the publisher', 'a+ modules', 'lam content a+', 'enhanced brand content', 'tao a+ cho sach', 'add a+ content', 'make a+ for book'.

Batch-assemble KDP coloring books after planning is done. Scans output/ folders, finds books with plan.json but no interior.pdf, then generates images, reviews, and builds PDF + cover for each — inline, no sub-agents. USE WHEN user says 'batch build', 'batch assemble', 'dong goi sach', 'build all books', 'assemble all books', 'continue batch', 'dong goi tat ca'.

Batch-plan KDP coloring books from the ideas folder. Scans ideas/*.md and writes one complete plan (page prompts + cover prompt + SEO metadata) per idea — inline, no sub-agents. USE WHEN user says 'plan all ideas', 'batch plan', 'create plans from ideas', 'plan ideas folder', 'lap ke hoach sach', 'plan tat ca'.

Create a KDP coloring book end-to-end (planning, image generation & review, and book assembly) running every step inline — no sub-agents. USE WHEN the user says 'tao sach', 'create coloring book', 'kdp create book', 'build coloring book end to end', 'make a coloring book', 'tao sach to mau', or otherwise asks to produce a complete KDP coloring book from a concept. Trigger even when the user only gives a concept (e.g. "a book about cozy cats") without explicitly naming the pipeline.

Create KDP-ready coloring book cover PNG/PDF using ChatGPT built-in image generation for front/back artwork, then deterministic Python composition for spine, back-cover text, barcode/stamp safe zone, bleed, DPI, and PDF dimensions. Use when the user asks to create, regenerate, fix, or rebuild a KDP cover with ChatGPT imagegen, especially when prompt-generated text, prompt-generated blank barcode areas, or manual cover composition caused errors.

Replace a KDP coloring book's plain text title / copyright / thank-you pages with illustrated front and back matter, add an optional "This Book Belongs To" page, auto-generate the page images with the configured IMAGE_RENDERER, and merge them into interior.pdf. USE WHEN user says 'tao trang bia trong sach', 'frontmatter pages', 'thay trang thank you', 'title page dep', 'this book belongs to page', 'trang dau cuoi sach', 'decorative interior pages', 'lam trang title va thank you', 'ghep frontmatter', 'illustrated title page', 'personalize thank you page', 'generate frontmatter images', 'tu tao anh frontmatter', 'tao anh trang dau cuoi'.

Research trending and profitable KDP coloring book ideas using web search, Amazon trends, and seasonal analysis. Can interview the user for preferences. Saves each idea to ideas/ folder. USE WHEN user says 'research coloring book ideas', 'find book ideas', 'kdp idea research', 'what coloring books sell', 'trending coloring books', 'tim y tuong sach', 'nghien cuu y tuong kdp'.

Find PROFITABLE, low-competition KDP coloring-book niches using REAL Amazon data (Apify top-10 BSR/reviews/price) and a deterministic Opportunity Score — not vibes. Sweeps many candidate keywords, computes Opp = demand/competition for each, corrects for the common traps (single-winner inflation, off-season seasonal reads, low-demand floors), and returns a ranked, evidence-backed shortlist of money niches plus a 5-10 book series for each. USE THIS whenever the user wants to find/research/validate KDP or coloring-book niches, asks "what book should I make", "find a niche", "is this niche worth it", "tim ngach", "ngach kiem tien", "research niche", "blue ocean niche", wants to AVOID saturated markets, or wants to verify a niche idea with hard Amazon numbers. Prefer this over guessing from WebSearch — Amazon blocks direct page fetches, so Apify is the only reliable hard-data source here.

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.

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

ALWAYS activate this skill before implementing EVERY feature, plan, or fix.

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.

Integrate payments with SePay (VietQR, Vietnamese bank transfers) and Polar (global SaaS subscriptions, billing). Use for checkout flows, webhooks, QR codes, subscription management.

Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text pr

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions, managing Docker containers and images, setting up CI/CD pipelines, optimizing cloud infrastructure costs, implementing global caching strategies, working with cloud databases, or building cloud-native applications.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

This skill should be used when fixing bugs, errors, issues, or problems of any complexity. It provides intelligent issue resolution with mode selection (autonomous/human-in-the-loop/quick). The skill auto-classifies issue complexity (simple/moderate/complex/parallel), activates relevant skills (debugging, problem-solving, sequential-thinking, brainstorming, context-engineering), and routes to appropriate workflow. This skill should be activated when users report bugs, test failures, type errors, CI/CD failures, log errors, UI issues, or any code that needs fixing.

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

Implement payment integrations with SePay (Vietnamese payment gateway with VietQR, bank transfers, cards) and Polar (global SaaS monetization platform with subscriptions, usage-based billing, automated benefits). Use when integrating payment processing, implementing checkout flows, managing subscriptions, handling webhooks, processing bank transfers, generating QR codes, automating benefit delivery, or building billing systems. Supports authentication (API keys, OAuth2), product management, customer portals, tax compliance (Polar as MoR), and comprehensive SDK integrations (Node.js, PHP, Python, Go, Laravel, Next.js).

Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.

Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.

View markdown files with calm, book-like reading experience via HTTP server. Use for long-form content, documentation preview, novel reading, report viewing, distraction-free reading.

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.

View plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status overview, phase progress, milestone tracking, project visibility.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks.

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Create or update Claude skills with eval-driven iteration. Use for new skills, skill scripts, references, benchmark optimization, description optimization, eval testing, extending Claude's capabilities.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks.