Video & Animation
iambandirakesh/Yt-video-director
Turn topics, requirements, articles or scripts into stickman videos. Director mode creates approved storyboards and standalone video prompts; Autopilot mode produces narrated, captioned illustration-and-micro-animation videos through configured generation tools and a local renderer. Also guide installation handoff, first use and setup of this specific Skill.
$ npx skills add iambandirakesh/Yt-video-directorhyperspell/release-notes-video-skill
Make release-notes or weekly-update music videos using Suno, Gemini audio review, Dreamina/Seedance animation, Blender and a timed video composition. Use to plan an episode, write lyrics, compare takes, sync captions, build product demos, edit the video or prepare silent clips and a posting kit.
$ npx skills add hyperspell/release-notes-video-skilleternityspring/reelbench-skills
把拉片数据和原片合成一条**能直接看的视频**:一边是画面,一边是这一镜的分镜信息 (镜号、起止、时长、景别、类别、运镜、画面描述、台词),**镜头切了信息跟着切**, 镜头表自动滚动并高亮当前这一镜。 版式只看原片的宽高比:**横版 / 方版 → 画面在上、信息在下;竖版 → 画面在左、信息在右**, 画面永远原样缩放,不裁不拉。 镜头表**随播放滚动**:切点处滚一小段把当前镜头带到锚点、随后停住,高亮条同步滑过去。 实现上只截三张图(底板 + 铺开的长图 ×2),滚动与高亮由 ffmpeg 按时间裁窗, **布局全在 scripts/panel.css 里,改它就能改版式**,不用碰脚本。 吃 video-shots 产出的 shots.json(有 frames/ 就把关键帧当缩略图用)。 零 npm 依赖,用 ffmpeg 合成、无头浏览器渲面板。 Use when asked to 导出视频、合成视频、分镜视频、带分镜信息的视频、解说版视频、 video with shot info、annotated shot video。
$ npx skills add eternityspring/reelbench-skillseuchmob/Youtube
עורך סרטונים — making YouTube Shorts edits from Avatar series (currently Avatar: Seven Havens). Use for ANY request to make, plan, edit or improve a video/short/edit for the user's YouTube channel. Holds the user's taste rules, what they liked and disliked, and the working technical pipeline.
$ npx skills add euchmob/Youtubeguipi888/video-skill-router
想做视频却不知道用什么工具?想让 AI 帮你「找技能 → 装技能 → 做视频 → 一条龙」?视频创作技能路由器(Video Creation Skill Router)是一个 AI video skill / animation skill 元技能——视频创作能力的发现与编排层,自身不生产视频,只做匹配、下载、编排执行、善后询问。你只管说需求("把勾股定理做成讲解动画""给我的 APP 做个宣传片""剪掉这段口播的口误"),它自动完成:① 判定视频类别(商业宣传/知识科普/其他)并优先匹配本地已装技能;② 本地无命中则按类别走对应渠道(内置精选目录→GitHub 实时搜索→网络搜索)发现并下载安装;③ 编排执行所装技能,输出剪辑后的视频文件;④ 生成后说明所装技能的作用,问你要保留还是卸载。安装/卸载全程走安全协议(快照+校验+可回滚,禁 rm -rf)。覆盖 explainer video 知识讲解、product demo 商业宣传、talking-head 口播剪辑、motion graphics 动效、Manim 数学动画、Remotion 程序化视频。Use when 用户说「做视频」「找动画技能」「下载视频技能」「帮我剪辑口播」「video skill」「animation skill」「ai video skill」「how do I make a video with AI」「is there a skill for video editing」时触发。解决"想创作视频却不知道选什么工具、装了技能不敢卸"的问题。
$ npx skills add guipi888/video-skill-routereternityspring/reelbench-skills
拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面。 分工刻在骨子里:**能量的都由代码量**(切点来自 ffmpeg 场景检测,时长是切点相减, 运动量是逐帧差分的中位数),模型只判断它真正该判断的那几件事(景别 / 类别 / 运镜 / 画面 / 节奏), 然后每一条判断都被代码当场对账——**声称推拉摇移却实测几乎不动,门直接拦**。 看片走联系表(每镜起手帧 + 收尾帧各拼一张大图,一屏二十几个镜头,a/b 对照就是运镜), 不是一张张翻。检测漏刀多刀用 recut 补刀并刀,自动重编号重算时长,手改边界过不了门。 产出 shots.json + Markdown 镜头表 + **单页交互式拉片报告**:内嵌播放器(播放时同步高亮镜头、 点镜头跳转)、镜头节奏带、可搜索可筛选可排序的镜头表(列表 / 卡片两种视图、首尾关键帧并排、 点图开大图)、景别类别运镜分布、出场人物、质量门、导出 JSON。单文件零依赖,离线双击能开。 15 道质量门全部由脚本确定性检查。 零依赖、零 API key,只要 node 和 ffmpeg。 Use when asked to 拉片、拆镜头、分析视频镜头、镜头时长、景别、运镜、镜头表、 video shot breakdown、shot list from video。
$ npx skills add eternityspring/reelbench-skillseternityspring/reelbench-skills
把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**: GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨,全部留在原地。 走的是白名单而不是黑名单:不列要删什么,只说带什么过去(画面一条流、声音一条流), 隐私保证来自结构,不来自枚举。 难点不在容器 tag,在**看不见的那几层**:x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——`ffprobe` 一个都看不见。 五个藏身处逐一堵死,每一处都有实测。 默认 `--mode copy`:**画面逐字节照搬**(cmp 验证过),只重编音频,53 秒的片子 1.3 秒跑完; `--mode encode` 完整重编码,多杀掉码流域的东西。 验收不靠声称:把源片所有元数据字符串当「针」,在输出文件里做**字节级扫描**, 扎到一根就红。12 道门全部由脚本确定性检查。 零依赖、零 API key,只要 node 和 ffmpeg。 Use when asked to 清元数据、去元数据、抹掉视频信息、视频隐私、去水印信息、 strip video metadata、remove exif from video、scrub video。
$ npx skills add eternityspring/reelbench-skillseshaan-eshaan/motion-design-director
Creative-director and motion-design layer for Remotion video work. Use for motion graphics, product promo videos, SaaS launch videos, product demos, UI animation, kinetic typography, cinematic product videos, animated explainers, marketing videos, and any Remotion project where story, look, motion or polish matters. Decides story, art direction, motion language, camera choreography, UI choreography and visual QA (premium light mode by default), then delegates all Remotion implementation to the official remotion-* skills. Also adds named effects to new or existing videos, including presenter (talking-head) footage, such as /logo-orbit, /number-roll, /words-kinetic and /portal, applying, offering or pushing back on each under a decision policy. Invoke as /motion-director:motion-design with a brief such as "15-second promo for my AI calendar".
$ npx skills add eshaan-eshaan/motion-design-directorelevenlabs/skills
Dub audio and video into other languages using the ElevenLabs Dubbing API (dubbing_v2), preserving the original speakers' voices. Use when translating videos, podcasts, or recordings into other languages, localizing media content, reviewing or correcting dubbing transcripts and translations, or regenerating a dub after edits.
$ npx skills add elevenlabs/skillsduytienitptit/edit-hyperframe
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.
$ npx skills add duytienitptit/edit-hyperframecsm-kr/reference-motion-video
Plan and build product launch films, explainers, demo walkthroughs, and teasers from references and real product screens. Use HTML and GSAP with the bundled frame renderer and music composed to the picture's cues.
$ npx skills add csm-kr/reference-motion-videodmtrKovalenko/fframes
>- Create, animate, review and render videos in code with fframes (Rust, SVG scenes, ffmpeg encoding, Skia GPU rendering). Use whenever the user wants a video, animation, motion graphic, explainer, promo, social clip, title card, podcast visual, lyric/caption video or any rendered .mp4/.webm made programmatically, or asks to change, fix, speed up or check an fframes video. Covers installing fframes, creating a project, designing good-looking motion, 3D shots (`fframes::three_d`, three.js style scenes), sound (music, voice, SFX, loudness), watching it in a real-time preview window, and checking the result without watching it: frames and contact sheets as PNG, automatic problem detection, loudness numbers, fast draft and range renders.
$ npx skills add dmtrKovalenko/fframescloudhanfeng92-arch/automotive-promo-video-rhythm
参考汽车实拍短片设计有节奏的汽车宣传片,重点处理开场吸引力、细节快切、整车留白、内外饰转折、动作剪点和行驶段的速度变化。适用于用户要求分镜优化、音乐卡点、快慢层次或参考豪车混剪节奏的制作任务;先提交节奏结构与逐镜表,用户确认出图后以 Lib Image 2.5 Pro 生成外观/内饰多视角参考和分镜图,以 Seedance 2.5 首帧或多图参考生成并剪辑成片。
$ npx skills add cloudhanfeng92-arch/automotive-promo-video-rhythmcloudhanfeng92-arch/automotive-promo-video-reference
无分镜图的汽车宣传片制作。先写剧本和文字分镜表,再从上传汽车图片生成车辆四视图及必要的内饰多视角参考、主要场景多视角资料卡,直接编写并执行 Seedance 2.5 多图参考视频提示词。每段最多30秒,以约0.5秒粒度写多镜头时间轴、主体与场景参考、起止状态和切镜衔接;无需逐镜生图、首帧图或音色参考。适用于汽车四视图直接生视频、分段时间轴提示词、无分镜图广告制作。
$ npx skills add cloudhanfeng92-arch/automotive-promo-video-referencecloudhanfeng92-arch/automotive-promo-video
根据汽车照片、要求和可选参考视频,制作具有实拍汽车摄影质感的完整宣传短片。先分析车辆并提交分镜,使用 Lib Image 2.5 Pro 生成并锁定外观及内饰多视角参考,再生成分镜图,以 Seedance 2.5 的首帧或多图参考模式生成镜头,最后完成配乐、剪辑及导出。适用于豪华车展示、情绪汽车短片、车型宣传和汽车摄影混剪。所有出图须先得到用户确认;仅分析或编写提示词时不启动生成。
$ npx skills add cloudhanfeng92-arch/automotive-promo-videochensiyuan040-hash/skill
用 HyperFrames(HTML→MP4 逐帧渲染)制作中文讲解/科普视频的实战工作流与本机踩坑手册。当用户要"做视频/讲解视频/科普视频/动画演示视频"、"用 HyperFrames/hyperframes 做视频"、给已有 hyperframes 项目"加字幕/加配音/改场景/排查渲染问题"时使用。覆盖:项目初始化、场景 sub-composition 编写、逐句字幕系统、edge-tts 中文配音管线、lint/check 修复套路、真实网页截图采集、参考视频定量拆解。官方 12 个 hyperframes skill 讲通用规范,本 skill 讲本机实证过的坑与中文视频实战配方。
$ npx skills add chensiyuan040-hash/skillbeginsc/long-video-subtitles
以主代理统筹、岗位子代理协作的字幕组流程,将长视频、音频或已有字幕转写、分段翻译、校对、制作时间轴,并交付单语或双语 SRT、VTT、ASS。适用于课程、访谈、纪录片、演讲及游戏视频,支持领域术语核验、全片一致性检查和断点续做。
$ npx skills add beginsc/long-video-subtitlesatlantis-mk/three-dimensional-remotion-template
复用本项目三维微缩商业讲解 Remotion 模板,根据本期内容与素材制作、修改、预览、渲染视频及三种封面。也用于维护本模板制作工具;仅维护时不启动视频任务。
$ npx skills add atlantis-mk/three-dimensional-remotion-templateatlantis-mk/kinetic-tech-remotion-template
使用本仓库的科技透视动效模板制作一条视频与三种封面,支持参数化场景、横竖屏、程序音效及本地媒体输入。仅在开始实际制作时创建 work/。
$ npx skills add atlantis-mk/kinetic-tech-remotion-templatebtcson66-rgb/ecommerce-video-pipeline-skill
>- MANDATORY standard operating procedure (SOP) for producing vertical commercial short videos (9:16, 1080x1920, 30fps CFR) for multi-brand products (Fantini Pelletteria leather bags, ESPNER eyewear/sunglasses, etc.). Every video MUST be composed of 3 distinct real AI videos: S1 (Gemini App Veo lifestyle action), S2 (Gemini/Flow ambient close-up push-in), and S3 (Google Flow Omni 1.1 Flash 3D turntable rotation showcase). Pure static image slideshows or single-scene videos are STRICTLY PROHIBITED.
$ npx skills add btcson66-rgb/ecommerce-video-pipeline-skillatlantis-mk/remotion-video-template
用一个选题全自动制作深色信息图风格的口播视频:写口播稿、豆包配音、分镜与素材、Remotion 动画、渲染成片、封面与发布文案。用户说“开始制作”、要做口播/信息图/财经科技解说视频时使用。支持横屏与竖屏。
$ npx skills add atlantis-mk/remotion-video-templatealyshadotmd/video-editing
>- Add burned-in captions to a vertical (9:16) talking-head video: exact word timings, one word at a time or short chunks broken by meaning, white outlined Figtree Bold with an optional highlighted word, placed in the safe area clear of the face and the hook headline. Built for Claude Code and Runneth. Use after framing and the headline, when someone asks for captions, subtitles or on-screen words.
$ npx skills add alyshadotmd/video-editingappariciojunior/video-editor-skills
Keeps a video motion-graphics kit and its editable Figma boards in sync - the creator designs and tweaks in Figma, Claude ports the changes into the Remotion components and brand tokens, and mirrors code changes back. Use when the creator says they changed the boards, wants a new graphic designed, or wants the kit visible in Figma.
$ npx skills add appariciojunior/video-editor-skillsappariciojunior/video-editor-skills
Clean, readable burned-in style subtitles from the verbatim transcript - stutters and fillers removed, spoken slang written correctly, one short line at a time, names checked, every line read by Claude before import into DaVinci Resolve. Use for "subtitles", "captions", "legendas", or when the creator reports wrong words in the captions.
$ npx skills add appariciojunior/video-editor-skills