Video & Animation

yt-dlp 下载 → 上传 PikPak → 在线观看 → 清理本地 的一条龙管道：断点续跑、上传校验后才删本地、支持 URL 清单批量处理。覆盖 YouTube、TikTok、X(Twitter)、Facebook、B站 等 yt-dlp 支持的站点。支持 Windows / macOS / Linux。 One-shot pipeline: yt-dlp download -> upload to PikPak via WebDAV -> watch online -> clean local copies. Covers YouTube, TikTok, X(Twitter), Facebook, Bilibili and other yt-dlp-supported sites. Resume-safe; local files are deleted only after verified upload. Cross-platform. Must use this skill when: - 用户想「下载视频并存到 PikPak」「看完就删，本地不留」/ download a video straight into PikPak - 用户给了一堆 yt-dlp 支持的链接（YouTube、TikTok、X、Facebook、B站等），想批量转存云盘 / batch-save TikTok/X/YouTube links to cloud - 用户磁盘空间紧张，想把下载成果直接入云 / save disk space by downloading straight to cloud 关键词：yt-dlp / PikPak / 管道 / pipeline / 下载转存 / download to cloud / TikTok / Twitter / X 视频下载

Gestiona el Instagram @marcvallfisio (fisioterapeuta, Tonus Fisioterapia, Camp de Tarragona) para ganar seguidores locales y captar pacientes. Úsala para ideas de contenido, guiones de Reels, copys y hashtags, calendario semanal, respuestas a comentarios/DM y revisión de métricas.

>- Write comments on other people's Instagram posts and reels that read as a person with an opinion, not a bot. Use when the user pastes a post or a reel and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch for their daily engagement round.

>- Post-mortem on what the user has already posted - which reels actually worked, why, and what to stop making. Use when the user pastes their Instagram insights or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to do more of.

Plan a month of email campaigns with audience, purpose, angle, CTA, proof, timing, and frequency coordination. Use when users ask what to email each week, need a 30-day campaign calendar, or are sending too many promotions.

Record short clips of NPC conversations that look like real gameplay, ready to post. Covers scripted exchanges at chosen places and times, the gameplay camera held still behind the player, both lines rendered before the clip rolls so it plays back to back, the game's own HUD and subtitles with nothing of the mod on screen, timeline markers for cutting, screen and audio sync, 5-10 s cuts in 16:9 (and 9:16), pinning lines to re-voice an approved take, and re-taking clips that run long. Use when the user wants demo videos, clips or a montage of talking NPCs.

Use when the user wants a multi-perspective brainstorm on a feature, app, or product area — "spin up agents with different personalities/job titles", "look at it from different angles", "panel of experts", "come up with 30 ideas and a top 5", "how can we make X more useful", "brainstorm what to do next with X" — especially when they also want to DECIDE on the ideas (implement / hold / reject) rather than just read a list. Also use when they ask to re-run or extend a previous panel, or to "make the ideas decidable like dev-to-prod-promotion-review".

Use when collecting or revising requirements for an OMR video: обсудить идею ролика, провести интервью, выбрать Remotion/Manim/гибрид и сохранить requirements.md. Owns video requirements, not general interviews, content research, scene scripting, rendering, or development of OMR itself.

Use when collecting or revising source-backed content for an OMR video: собрать материалы по теме ролика, проверить факты и внешние источники, создать content/index.md и тематические Markdown-файлы. Not for requirements interviews, final narration or scene scripting, rendering, general research unrelated to a video, or development of OMR itself.

Score any app (the user's own or a competitor's) on a research-backed rubric and produce a reusable, comparable scorecard — 0–5 per dimension with an evidence grade, noncompensatory gates checked first, and one "smallest fix" per weak dimension. Adapts to product stage: a pre-PMF app under ~100 users is scored on 9 dimensions, a growth-stage app on the full 23. Use whenever the user says "score this app", "grade the app", "rate the UI/UX", "how good is [app]", "app scorecard", "run the scorecard on [app]", "how does [app] stack up", "is this ready to launch / promote to prod", or wants a before/after number after a build sprint or a beta round. Reads the codebase + deploy + docs, optionally beta feedback / analytics, and refuses to invent retention, revenue, or PMF from code alone. Outputs a chat table plus a published HTML scorecard artifact. Pairs with ui-usability-audit (UI depth), qa-sweep (functional pass), dev-to-prod-promotion-review (release gate).

Use when implementing or revising an OMR video from a script and delivering out/video.mp4: собрать, отрендерить или экспортировать ролик на Remotion, Manim или гибриде, подготовить медиа и проверить готовое видео. Not for requirements interviews, content research, script-only requests, generic media questions, or development of OMR itself.

Generates new footage with Higgsfield and puts it on the edit's timeline. Prices every generation first, asks the user with the dollar amount (and, for their own footage, whether it may be uploaded to Higgsfield), then submits, waits, downloads into the edit's generated/ folder and adds the result to the timeline's Generated track. Covers motion transfer on a clip of the user's video (their moves onto a character or styled look), b-roll from a sentence (text to video), a still brought to life (image to video) and stills for cards (text to image). Use when the user says "generate b-roll", "make a shot of", "AI b-roll", "generate a clip", "use Higgsfield", "motion transfer", "put my moves on", "restyle this part with AI", or asks for footage they did not film. Not for animated diagrams or motion graphics (motion), not for real screenshots and logos (overlays, logo-pack), and not for the cut (cut).

For the editor's maintainers. Turns what users corrected into lasting fixes in this repo, for every user, enforced by code and tests rather than notes. Reads the suggestions users marked "would help everyone" (~/.ai-video-editor/suggestions.jsonl), taste rules said twice (taste.py report), preview corrections (edits/*/corrections.jsonl), review-page notes (*/review.json) and open GitHub issues labelled feedback; groups repeats; for each item the maintainer accepts, writes the general rule into PRINCIPLES.md and the skill that owns it, adds or tightens the check that enforces it, adds a test that fails before and passes after, and runs the full test set. Use when the maintainer says "improve the editor", "turn feedback into fixes", "process suggestions", "what are users complaining about", "go through the feedback issues". Not for one user's own preferences (that is taste), and not for editing a video.

Cuts raw talking-head footage into a clean jump cut. Takes one take or several joined (mp4 or mov, any aspect, 4K phone footage is fine), transcribes it word by word, removes retakes, false starts, fillers and dead pauses, and renders cut.mp4 at the source resolution plus words.json timed to the cut. The user approves the cut on a page with the whole transcript and every removed word struck through. Use when the user says "cut my video", "just cut it", "remove my mistakes", "cut out the retakes", "remove the pauses", "clean up this take", "jump cut this", "tighten this clip", or asks only for the cut of a raw take; start calls it for a full edit. Runs before style-edit. Not for a general request to edit a video or to make it look like a creator (that is start), not for adding captions, zooms or cards (style-edit), and not for analysing someone else's videos (creator-teardown).

Reverse-engineers a short-form creator's video format from their real numbers. Pulls a TikTok or YouTube Shorts profile (or pasted links, Instagram reels too) with view, like and save counts, transcribes the top videos word for word, measures pace, pauses and fillers, maps each video into timed beats, and writes a teardown.md someone can film from, a teardown.html page of their graphics, motion and sound, and the style.json the style-edit skill edits from (on its own it can write an edit plan as a table and .srt). Use when the user wants to analyse, break down or study a creator ("analyse @handle", "tear down @handle", "teardown of @handle", "break down this creator", "what makes this creator's videos work"), pastes TikTok, YouTube or Instagram links and asks what the pattern is, or asks to set up creator-teardown. Not for editing the user's own video like a creator (that is start), not for researching a topic, and not for cutting raw footage.

Turns one long video or podcast (a local file or a YouTube link) into the best 3-5 short vertical clips, each cut and styled in the user's profile style. Transcribes once, splits the talk into candidate clips at sentence boundaries inside the chosen length, scores every candidate in code (speech rate, loudness, laughter, numbers and names said), shows the shortlist on one page with a preview of each, then trims, cuts and style-edits each pick as its own edit. Use when the user says "clip this video", "make shorts from my podcast", "find the best clips", "cut this into TikToks", "turn this YouTube video into reels", "repurpose this long video", or drops a long video (over about 3 minutes) or a YouTube link and wants short clips. Not for editing one short take (that is start or cut), and not for measuring someone else's style (that is creator-teardown).

Draft, rewrite, polish, structure, humanize, or compress computer-science research manuscripts and manuscript sections, including abstracts, introductions, related work, theory, methods, experiments, captions, limitations, conclusions, and LaTeX. Use for reader-centered scientific storytelling, semantic naming of experiments and theorems, CS-appropriate terminology, removal of defensive or research-log prose, and evidence-preserving revisions. Do not use as the primary workflow for independent peer review, experiment execution, or mathematical/data integrity audits.

Prepare masked video clips for Flow and composite returned patches into original footage, including eye or face repairs, continuous head-to-collar replacements, tracked crops, explicit frame mapping, and independent patches for multiple people. Use for the Flow local video repair workflow; requires external Flow generation and local media tools.

Create or substantially revise a finished HyperFrames video from a topic, brief, song, narration, or visual references. Covers reference study, timing, art direction, kinetic typography, character assets, internal prototypes, local rendering, and evidence-based delivery review. Use for complete motion-graphic films; a single overlay or minor trim usually needs only its specific editing tools.

Trigger: editar vídeo, brutos, montaje, shorts, reels, tiktok, linkedin, miniatura, anuncio, Remotion. Pipeline de vídeo con IA: corta silencios por energía de voz, sincroniza multicámara, anima escenas 3D y entrega cada red.

Capture real GAMEPLAY VIDEO of a running web/canvas game and turn it into a finished AD VIDEO (e.g. Meta / TikTok, 800x1000 or 1080x1920, 15-30 s, with sound). Records in Chromium (canvas.captureStream + MediaRecorder -> ffmpeg) with the game's WebAudio sound and a per-frame timeline, then cuts a cut list (JSON) into the ad: speed changes, fades, a music bed, cuts and gate passes landing on the beat, loudness normalised. Also covers making the footage reproducible (seeded, fixed-step), a human-looking autopilot that always clears, and recording-only level scripts. Use when the user asks to "capture gameplay video / record the game / make an ad video / 広告動画を作りたい / 広告用の動画 / プレイ動画を撮る / ゲームプレイをキャプチャ / mp4 で録画 / カットをつないで / 音楽に合わせて / 倍速にして / 人間っぽい自動操作 / 録画用のステージ", or wants footage to edit later (After Effects etc.). Works for Phaser/PixiJS/Three.js/plain-canvas games served locally. Sibling of `game-store-assets` (store screenshots + feature graphic) and `game-icon-from-screenshot` (square app icon).

Search YouTube videos by keyword with date, duration, feature and sorting filters. Return video IDs, channels and available statistics. Uses the paid FlashData API.

Read YouTube video details, descriptions, statistics and available chapters. Inspect formats or prepare timestamped chapter navigation. Uses the paid FlashData API.

Write and critique viral hooks for short-form video: the opening 1 to 3 seconds that decide whether anything else gets seen. Use this when you need a batch of hook ideas for a video, want to make a weak opening line stronger, are picking which hook archetype fits an idea, or want a critique of a draft hook against proven patterns. Covers the three-layer hook (visual, verbal, on-screen text), the named-creator frameworks (Kallaway, MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway), scroll-stopping hook tactics, and the anti-patterns that tank first-three-seconds retention. Works across TikTok, Reels, and Shorts. Pattern-based guidance that improves the odds. It does not guarantee virality.