Video & Animation

Use this skill for any task involving writing Thai-language social media captions, posts, or short-form copy. Trigger whenever the user asks to: write a caption for Facebook, Instagram, TikTok, Threads, X (Twitter), Pantip, or LINE TIMELINE in Thai, draft a Thai social post, write a Thai product/review/giveaway post, pick hashtags for a Thai audience, or adapt copy for a Thai social channel. Also trigger for requests like \"เขียนแคปชั่น\", \"caption ภาษาไทย\", \"เขียน TikTok caption\", \"โพสต์ Facebook\", \"ลงไอจี\", \"caption social media Thai\", \"เขียนรีวิว\", or any variation. If the output is a short Thai post designed to be published on a social platform, use this skill.

Generate, repair, and validate 2D raster sprite-sheet animations from character art or separated body parts. Use for directional walk cycles, flipbook loops, joint anchoring, occlusion, stable origins, runtime packing, and game-scale visual QA. Do not use for native 3D animation or runtime skeletal rigs unless their rendered output must become raster sheets.

Use when 总结视频/音频内容（B站/YouTube/本地）。

Use when the user asks to watch/understand/summarize a video — Bilibili (BV id / URL), YouTube, or a local video/GIF file. Fetches metadata and subtitles, extracts keyframes, then reads them with vision.

Prepare a reviewable preview, verify the final encoded video and hand off a versioned editing project. Use before export or when diagnosing black borders, crop errors, missing assets, drift, color or audio problems; do not claim creative QA from a successful build alone.

Cull and rank photos or video excerpts, remove repetitive selections, and compare blurry versus sharp takes. Use for bursts, near-duplicates, contact sheets and best-moment selection; never delete source media or judge focus only from a blurred background.

把「為什麼森林」podcast 的某一集做成精華 Reel：補時間軸 → 選段 → 等使用者確認 → make-props → 檢查畫格 → 輸出 mp4。使用者說「做 epNN 的 Reel」「幫我做新一集的 Reel」「/new-reel epNN_xxx」時使用；可以一次給好幾集。

Fit portrait photos or videos into landscape edits, or reframe mixed aspect ratios with a blurred copy of the same media. Use to prevent black borders and cropped faces or bodies; not for privacy anonymization or sharpening a blurry subject.

Onboard a new user to the VideoEditting toolkit by choosing all or selected editing skills, assessing useful MCP integrations and setting up approved tools before the film brief. Use for first-time adoption or setup changes, not every editing revision or repository maintenance task.

Add playful video gags such as person cutouts, spins, loading effects, face-zoom transitions or tracked scooter flames. Use when humor is requested in the current brief; do not add unsolicited meme edits to a serious film.

Reconstruct capture order, trip chapters and road/ferry map segments from photo/video metadata and visible evidence. Use when travel chronology or route labels matter; do not invent exact dates or transport links from filenames alone.

Establish a film or reel brief, including tone, humor, travel type, route and relevant vehicle details. Use when these choices are missing or the user changes direction; skip for a small revision with an established brief.

Learn a creator's or channel's video style from reference YouTube links and save it as a new project skill (story structure, narration voice, visual language, Remotion recipes). Use when the user says "learn creator X from these", "study these videos", "make a skill in the style of …", or pastes reference video links to imitate.

Write and build videos in the style of Johnny Harris — first-person investigative explainers that turn one question into a story, told on camera and through paper-textured collage, hand-drawn charts, highlighted documents and archival footage. Use when the user asks for a "Johnny Harris style" video, a documentary/video-essay explainer, or paper/collage/hand-drawn explainer visuals in Remotion.

Mix music, dialogue, authentic location sound and comedic sound effects for an edit. Use for ducking, song transitions, J/L cuts, intelligibility and clean endings; not as a substitute for beat detection or actual listening.

Cut photos or video on audible musical beats, downbeats and phrase changes, or diagnose an edit that feels off beat. Use for music-led timing and transitions; do not equate waveform peaks or automatic markers with verified musical accents.

Write and build videos in the style of Fireship's "X in 100 Seconds" (Jeff Delaney) — dense, deadpan, meme-laced tech explainers on a dark code-editor canvas. Use when the user asks for a "Fireship style", "100 seconds", "fast tech explainer", or a short punchy programming/tool explainer in Remotion.

Create only configuration-driven map route videos that connect multiple places in order, when the user asks for 地图视频、路线视频、路线动画、探店路线、citywalk、打卡路线、旅游路线视频 or 行程地图. It does not create other kinds of videos.

Turn an idea, topic or transcript into a ByteByteGo / Fazt Code style animated explainer video (9:16 and 16:9) with the remotion-system-design-challenges project. Topic packs - tech (system design, backend, programming) and science (the brain, biology, health, learning, languages). Use for /make-video or any explainer video request.

This skill should be used when the user runs '/video-meta' or '/quancoder-video:video-meta', or asks for 'meta để đăng video', 'caption TikTok', 'tiêu đề YouTube Shorts', 'hashtag Reels', 'mô tả video', 'metadata upload', or wants titles, captions, hashtags, tags and a pinned comment for posting a vertical video (especially one made with /paper-tear-video or /affiliate-video-01) to TikTok, YouTube Shorts, Instagram/Facebook Reels.

This skill should be used when the user runs '/stickman-history [chủ đề]' or '/quancoder-video:stickman-history …', or asks for a 'video lịch sử người que', 'kể chuyện lịch sử bằng người que', 'video người que chuyển động', 'video Remotion minh hoạ người que', a narrated 16:9 history story drawn with animated stick figures on old paper, or wants to change its channel names, voice, colours or render settings ('đổi tên kênh', 'sửa config stickman').

把一篇选定文档做成程序绘制的竖屏知识科普短片：先说清知识点、结论和做法，按原文论证结构写场景代码，事实对照一手来源，逐句配音并按录音排节奏，如实区分已核对与未实听。

This skill should be used when the user runs '/paper-tear-video [chủ đề]' or '/quancoder-video:paper-tear-video [chủ đề]', or asks to 'tạo video 9:16', 'làm video paper tear', 'video xé giấy', 'video dọc có lồng tiếng', 'video Shorts/Reels/TikTok về chủ đề X', 'làm video giống video tu tiên', or wants an end-to-end narrated vertical video built with Remotion, VieNeu-TTS voiceover and Creative Commons photos from the internet in the paper-tear collage style, including donghua/anime character analyses that use official stills of the work.

This skill should be used when the user runs '/affiliate-video-01 [url sản phẩm] [thời lượng] [giọng] [style giọng]' or '/quancoder-video:affiliate-video-01 …', or asks to 'làm video affiliate', 'video tiếp thị liên kết', 'video bán hàng cho link Shopee/TikTok Shop/Lazada', 'video review sản phẩm có FOMO', or wants a short 9:16 product video with hook, zoom-punch product shots, social proof, struck-through price, countdown-free FOMO and a 'bấm giỏ hàng' CTA, narrated with VieNeu-TTS in a chosen voice style (hài hước, nhí nhảnh, nghiêm túc, nhẹ nhàng, kịch tính, hào hứng).