Video & Animation

Write a platform-tuned caption plus a researched, non-spammy hashtag set for a post. Use when finishing a social post, asked for 'caption and hashtags', or optimizing reach for Instagram/TikTok/X/LinkedIn.

Builds and maintains an interactive travel diary website (dark satellite map with 3D terrain, animated day-by-day "replay" of routes, photos and videos pinned where they were taken, points of interest with Wikimedia images, mobile-first) from a trip's raw material - diary text, photos/videos, GPX tracks and optionally a Google Timeline export. Use this whenever someone wants a trip website, travel blog with a map, road-trip / camper / bike-tour / hiking diary, "photos on a map with the route", a Komoot-style flyover of their days, or wants to add a new day of material (new photos, GPX, timeline, diary text) to such a project - even if they just say "there are new pictures and tracks". Three modes - init (scaffold a new project with a local setup web app for drag-and-drop input), day (process new material into the site), deploy (single HTML file, web space via SSH, or Synology nginx).

>- Make a game's Google Play store listing: the promo FEATURE GRAPHIC (1024x500) and phone/tablet SCREENSHOTS captured from the real game running in headless Chromium, plus the listing TEXT (short / full description). Use when the user asks to "make store images / store assets / Play Store screenshots / feature graphic / store description / ストア画像 / スクショ(スクリーンショット)一式 / フィーチャーグラフィック / 簡単な説明 / 詳しい説明 / Play Console の説明文", or to capture many gameplay screenshots to choose from. Also builds a PICKER page (an Artifact with checkboxes, per-section comments and copy buttons) so the user ticks the store set -- screenshots, feature graphic, listing text, and app icon candidates too ("選定用の artifact", "チェックして選びたい", "アイコンも一緒に選びたい"). Works for Phaser/PixiJS/Three.js/plain-canvas games served locally. Sibling of `game-icon-from-screenshot` (that one makes the square app icon; its candidates can go in this picker). Not for hand-drawn/from-scratch promo art.

Read live Zoromi (zoromi.studio) prices and plans for short videos, vertical short dramas and illustrated books, and, with the user's own ZOROMI_API_KEY, their Gems balance, daily cap, books, video projects, job status, recent charges and a quote for filming video clips; and, with a key the user allowed to spend, make one picture or one video clip, paid in US dollars from their API balance, after the user says yes to its quoted price, or start a short drama from a script that the user then finishes on the website. Use when the user mentions Zoromi or zoromi.studio, asks what a short drama, video clip or illustrated book would cost there, asks about their own Zoromi account, books, projects, jobs or Gems, or asks for a picture, a video clip or a short drama made there. Prices, plans and what Zoromi does need no key; which other tools are open, the server's tools/list says, so call it first and ask for a key only when it lists tools that need one. Nothing is charged until the user approves the exact price.

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Run a Scribe signature marketing campaign: build the banner content, target it, schedule/pause/resume it, and measure it. Use when the user wants to promote an event, launch, or offer through the banner under everyone's email signature.

Build and publish AI web apps on RunApps (runapps.ai) through its MCP tools, and write the app code with the RunApps JavaScript SDK (@runappsai/sdk). Covers getting authorized and connected (device-code flow, agent key, Bearer header, scopes), the platform model (apps, slugs, bundles, visibility and review, creator fee), every MCP tool, the SDK (sign-in, chat, images, audio, video, per-user files, IndexedDB sync, private prompts), the bundle rules (zip layout, dot files, entry page) and the safety rules. Use whenever the runapps MCP server is connected, or when a task mentions RunApps, runapps.dev, publishing an app there, the RunApps SDK, or an rk_ key.

Use SkillLens (this repository) to turn SKILL.md files into animated flowcharts, and to make skills chart well. Use it when someone wants to understand or present a skill's workflow, check whether the auto-extracted chart is right, add a skillflow block to a skill, export a web page / image / video of a skill, or change SkillLens itself.

PikPak cloud storage CLI (pikpak). Run every cloud-drive operation from the command line: browse and search files, cloud-download magnets/torrents/links, manage download tasks, stream videos, upload local files and folders, download to disk, share files and restore others' shares, move/copy/rename/delete, register accounts and manage access tokens. Use this skill when the user mentions PikPak or a cloud drive, or asks to: - cloud-download a magnet, torrent or link, or check task progress - upload a local file or folder, or download cloud files to disk - play or watch a video, movie or series stored in the cloud - share files, or save/restore someone else's share - browse, search, move, copy, rename or delete files, or create folders - log in, register an account, or save a personal access token - check account info, storage space or VIP status Trigger it even without the word "PikPak" (e.g. "download this link", "upload this file", "what's in my cloud drive", "play that video", "share this file").

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

>- 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.

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.

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 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 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 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.

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).

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.

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.