Video & Animation

cartoon-video

github.com

Create original vertical animated cartoon shorts from an idea, script, or uploaded voiceover. Use when a user wants a short-form cartoon video planned, scripted, timed to narration, animated with a Three.js world and illustrated characters, sound-designed, rendered, or exported as an MP4. Also use when adapting the included soldier example or troubleshooting this workflow.

$ npx skills add Alone-legacy/cartoon-video-skill
Skill anzeigen→

cancion-video-karaoke

github.com

Writes a custom song (lyrics plus a Suno style) and a vertical karaoke video from the client's photos, with the lyric locked to the beat word by word. Use for a birthday, anniversary, or gift song and a captioned karaoke cut.

$ npx skills add dialejo0720-maker/skills-edicion-video
Skill anzeigen→

edit

github.com

Builds a video version from the user's recording: the speaker cut, then one edit plan with all inserts (2D scenes, 3D scenes, recordings, keywords), sound and music, built with one command (crewcut render). Use for: edit the video, build the cut, speaker cut, rough cut, insert, b-roll, 2D scene, 3D insert, counter, keyword, music bed, sound, assemble, render the preview, new plan version, short from the long video.

$ npx skills add marcopatzelt/crewcut
Skill anzeigen→

ui-clone

github.com

Use for frontend work when the user wants to clone, copy, recreate or match a UI, section, component, effect or animation from a reference: a live URL, their local dev server, a video, GIF or screen recording (web or mobile app), or a Figma design. Covers pixel-accurate UI (layout, fonts, spacing, colours), animations and interactions (load, hover, click, scroll, page transitions, loaders, marquees, springs), and effects (gradients, blurs, shaders, canvas/WebGL backgrounds), rebuilt in the user's stack (HTML/CSS, React, Next.js, Vue, Svelte, Tailwind, Framer Motion, GSAP, Web Animations, three.js, React Native, SwiftUI), then verified against the reference with screenshot diffs and frame-by-frame timing. Not for the user's documentary channel videos (documentary-animation) or video-only motion studies (motion-match).

$ npx skills add stazdev/ui-clone
Skill anzeigen→

video-guard

github.com

Interview users and preflight AI image and video generation or edits. Use for prompts, storyboards, reference images, model selection, credits, failed renders, and image-to-video handoffs with Higgsfield, Runway, Kling, Veo, Seedance, GPT Image, Nano Banana, or similar tools.

$ npx skills add icedracon/VideoGuard
Skill anzeigen→

video2threejs

github.com

Rebuild a room/scene from a reference VIDEO (AI-generated or filmed) as a code-only procedural Three.js diorama, 1:1 in layout, color, light, objects, characters and their motion timeline. Use when the user shares a video/tweet and asks to rebuild/replicate it in three.js, or asks how to model a specific object (bedding, hair, lamps, rugs) procedurally. Built around live preview, multi-frame analysis, perspective solving, detail sculpting, research-when-unsure and screenshot-verified iteration.

$ npx skills add pacb9148/Video2ThreeJS
Skill anzeigen→

motionsnip-studio

github.com

Build motion graphics in code and review them in MotionSnip Studio, a local player where the user watches the render, fixes words in place, swaps music, circles problems on the frame and sends one prompt back. Use it whenever the user asks for a motion graphic, launch video, explainer, product video, animated promo or similar video made in code (Remotion or any other renderer), when they want to review or iterate on such a video, or when they paste a line like "Apply the MotionSnip Studio feedback in <path>" or share a "MotionSnip Studio feedback" markdown file.

$ npx skills add jishanpathan7/motionsnip-studio
Skill anzeigen→

motion-match

github.com

Use when the user gives a reference video, GIF or screen recording of any animation and wants that motion measured and rebuilt in their own design or checked against it; gives still images and wants Claude to direct smooth motion for them (a UI entrance, a reel, an explainer); or gives video clips (UGC, AI-generated such as Google Flow, or filmed) to cut into an ad with captions and motion graphics. Not for the user's documentary channel videos, which use documentary-animation.

$ npx skills add stazdev/motion-match
Skill anzeigen→

sd25-pe

github.com

Use when a user asks an Agent to optimize text, stories, or optional multimodal references for Seedance 2.5 text-to-video, multi-reference generation, keyframes, storyboards, blockouts, video editing, audio editing, or extension.

$ npx skills add sliu2024/laoliu-ai-prompt-skills
Skill anzeigen→

scripted-video

github.com

Plan, research, write, review and export videos that are written as scripts (data and code, not timeline editing) and rendered to mp4. Use this whenever the user wants to make a video, tutorial, explainer, lesson, course module, product walkthrough, how-to, animated presentation, YouTube video, short vertical clip or in-app tutorial, or asks to research a topic "for a video", write or review a video script, add narration, captions, chapters, a voice-over, sound effects, music or translations to a video, improve or correct a video made this way, or turn a document, a lesson or a slide deck into a video. It covers the whole job (research method, research in a few checked rounds that goes one level deeper than the video tells and finds subjects for later videos, counter-views and real examples, a mind map, a storyboard, a core-length script with longer versions on request, accuracy and comprehension reviews, a frame-by-frame visual review, voice, generated sound effects and music, export,

$ npx skills add utoappia/skill-tutorial_video_creation
Skill anzeigen→

gertie

github.com

Writes a small scene file and compiles it to checked Lottie JSON and animated SVG, plus GIF, video and multi-scene films with captions and music. For icons, loaders, logo stings, stickers and short loops. It renders in a browser, compares outputs frame by frame, and does not hand over a scene that fails QA.

$ npx skills add ajithonmain/gertie
Skill anzeigen→

launch-video

github.com

Makes a launch, promo, teaser or demo of an app, site or product in 16:9 and 9:16, light and dark, rendered locally to MP4. It interviews first, reads the real site, writes a storyboard, captures pan, zoom, typing and phone scroll, then adds titles, counters, an end card and music on the cuts.

$ npx skills add Matteoikarieth96/launch-video-skill
Skill anzeigen→

off-grid-ai/skills

github.com

Stop babysitting your AI. 49 free skills that make Claude Code, Codex, Cursor and 60+ agents build, test and ship like a senior team.

$ npx skills add off-grid-ai/skills
Skill anzeigen→

manimgl-notebook

github.com

Render ManimGL scenes inside Jupyter or VSCode notebooks with the %%manim magic from manimgl_jupyter. Use when writing, running or debugging a notebook cell that renders a manimgl Scene, choosing flags (-l -m --hd -s -i -t -r --fps -c -n -a --prerun), sizing or embedding the output, or when `from manimlib import *` fails in a kernel with SystemExit 2 or "ambiguous option --f".

$ npx skills add zavden/manimgl_jupyter
Skill anzeigen→

animate-my-work

github.com

Use when I want my own designs animated, such as "animate this Figma file", "make a launch film from these frames", "explainer for X" or "/animate-my-work". It storyboards in Figma, then Remotion renders it, with synced music and loud SFX.

$ npx skills add zazzygfx/skills
Skill anzeigen→

manimgl-vs-manimce

github.com

ManimGL (3b1b's manimlib) API essentials and how it differs from ManimCE (the `manim` community package). Use when writing or fixing a scene for manimlib or manimgl_jupyter, when code mixes ManimCE names (Create, MathTex, MovingCameraScene, self.camera.frame, config.frame_width, set_camera_orientation, add_fixed_in_frame_mobjects, GRAY_A) into a manimlib project, or when unsure which name ManimGL uses for something.

$ npx skills add zavden/manimgl_jupyter
Skill anzeigen→

pptx-animation

github.com

给 python-pptx 生成的 .pptx 加"点击触发"的进入动画。python-pptx 没有动画 API,动画只能手写 p:timing XML 注入,写错会让文件报"已损坏"。本 skill 用"从本机真实 PowerPoint 文件提取基准 + 逐节点比对"的方式保证手写 XML 正确。当用户说"给 ppt 加动画""太枯燥了""让它动起来",或要做带演示动画的幻灯片时使用。

$ npx skills add zjy053231-crypto/agent-skills
Skill anzeigen→

video-qc

github.com

Quality control and critique for short videos (ad spots, reels, shorts) before delivery. A script uses ffmpeg to measure everything measurable (resolution, fps, BT.709 color, cut pacing, loudness, true peak) and generates contact sheets plus silhouette, low-brightness and phone-speaker tests; a 5-axis rubric judges the visuals. Binary verdict: deliver or do not deliver. ALWAYS use before delivering a video or a generated image, and to analyze or compare a reference. Keywords: QA, quality check, video review, loudness, LUFS, true peak, contact sheet, critique.

$ npx skills add z-intraptable/tomake-autoeditson-control-calidad
Skill anzeigen→

trackbox-seedance-prompt-en

github.com

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

$ npx skills add weiduhezi/trackbox-ai
Skill anzeigen→

scene-verify

github.com

Verifica una escena WebGPU (index.html) contra los dos gates del spec — un critic visual (subagente que ve SÓLO los renders, nunca el código) sobre 6 poses fijas a 2560×1440 + grabación del fly-through, y rendimiento vía GPU timestamp queries y log de frame-times (avg/p99/max). Úsala tras /scene-build, o cuando el usuario diga "verifica la escena", "/scene-verify", "pasa los gates". Itera hasta que el critic no reporte nada por encima de "minor" y la perf cumpla el TARGET.

$ npx skills add whatevaaar/webgpu-scene-skills
Skill anzeigen→

scene-build

github.com

Construye una escena 3D procedural en tiempo real como un único index.html autocontenido, renderizado con WebGPU, sin motores (nada de Three.js/Babylon), todo procedural (sin archivos de textura/modelo) y con cero asignaciones de JS por frame. Úsala tras tener un scene-spec.md (de /scene-spec) o cuando el usuario diga "construye la escena", "/scene-build", "genera el index.html". Implementa el render, reporta el tamaño minificado, y deja la escena lista para /scene-verify.

$ npx skills add whatevaaar/webgpu-scene-skills
Skill anzeigen→

trackbox-kling-3-prompting

github.com

Write better prompts for Kling 3.0 text-to-video, image-to-video, keyframes, multi-shot sequences, and dialogue scenes.

$ npx skills add weiduhezi/trackbox-ai
Skill anzeigen→

animated-step-slides

github.com

Make a single-file HTML slide deck where each press of → moves a diagram one step - a dot travels along a path of nodes and the nodes and lines it passes light up - and slides switch instantly with no transition. Use it to write a spec document that explains how a system works (requests, data pipelines, jobs, protocols) one hop at a time. Comes with a template and two checkers (every slide fits the screen, every step plays). Trigger: animated slides, step slides, slides where the diagram moves, explain the flow step by step, 1 手ずつ動くスライド, アニメーションスライド.

$ npx skills add TakashiAihara/claude-skills
Skill anzeigen→

motion-graphics-2d

github.com

Guidance for designing and building 2D motion graphics, explainer animations, logo/brand animations and kinetic typography. Use when asked to storyboard, design, script or code an animated video, loop, text animation, or motion design piece (After Effects, Jitter, Lottie, CSS/JS, Remotion, etc.).

$ npx skills add vrijesh123/motion-graphics-kit
Skill anzeigen→