All authors
Claude Skills by Wanfeng1028
github.com/Wanfeng1028590 skills0 installs0 views
- Motion PhotoMake a looping product or photo reel, 8 to 15 seconds, from the user's own images (product shots, screenshots, cutouts, venue photos). Photos drift in crops (Ken Burns), reveal through wipes, circles, splits and shapes, float as parallax cutouts, slide past in a carousel or stack, compare in a before/after slider, assemble into a mosaic and carry price and feature tags on leader lines. Claude writes one HTML canvas file driven by a pure seek(t), critiques it (image resolution, text contrast o...Votes: 0GitHub stars: 5
- Motion PixelMake a pixel-art motion loop, 6 to 20 seconds, from a short brief. A low-resolution canvas scaled up by a whole number, a strict palette of at most 16 colours, ASCII-art sprites with run cycles, parallax strips, tile maps and a built-in bitmap font. Claude writes the film as one self-contained HTML file driven by a pure seek(t), checks it with an automated critique (every pixel a palette colour, whole-pixel positions, whole sprite cycles, text contrast on its real backdrop), and renders it to...Votes: 0GitHub stars: 5
- Motion ShapesMake a flat 2D motion-graphics loop, 6 to 20 seconds, from a short brief. Circles, rounded rects, polygons, stars, arcs, lines and SVG paths pop in, draw on, morph and ripple in grids and rings, with type, circle and bar wipes and a camera. Claude writes the film as one self-contained HTML canvas file driven by a pure seek(t), checks it with an automated critique, and renders it to MP4, GIF and poster with real motion blur and a verified seamless loop. Use it for an explainer-style product pr...Votes: 0GitHub stars: 5
- Motion StudioMake motion-graphics films in code, from short reels, promos, article trailers and launch films to long narrated YouTube explainers with rigged human figures, with a live scrub-and-annotate preview, licensed music cut to the beat, recorded foley, and a blind-read gate that proves the film still makes its source's point. Use whenever the user wants to turn an article, essay, newsletter or Substack post, inbox or notes digest, idea, product or brand into an animated video, reel, short, teaser, ...Votes: 0GitHub stars: 5
- Motion UiMake a looping app or product UI promo, 8 to 15 seconds, from the user's screenshots or live site. A phone, tablet or browser window shows their real screens, rebuilt from primitives in their colours and copy, driven like a live demo: a finger or cursor taps, scrolls and types, screens push and expand, sheets and toasts open, the camera focuses, with short callouts and a closing lockup. Claude writes one self-contained HTML canvas file driven by a pure seek(t), checks it with an automated cri...Votes: 0GitHub stars: 5
- Motion Video ProductionPlan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review. Use for video production, keyframes, character consistency, and Remotion assembly. 모션 그래픽·캐릭터 영상·오프닝 영상 제작에 사용한다.Votes: 0GitHub stars: 5
- Muse Video SkillWhen the user asks to 策划/构思/设计/写脚本/画分镜 for a video project — e.g. '帮我策划一个广告创意' '这个产品演示视频怎么拍' '帮我写科幻短片的分镜脚本' '给我这个品牌TVC的美术方向'。Not for actual video rendering/compositing or AI image/video generation.Votes: 0GitHub stars: 5
- Music Artist VisualsMusic videos, lyric videos, tour visuals, and audio visualizers for artists. Mood-led abstract design, beat-synced editing, and a mandatory asset-request protocol. Requires the actual audio track. Use for musicians, labels, and live visuals.Votes: 0GitHub stars: 5
- Narrative To Screen Reader将叙事文本转化为影视开发阶段可用的多用途读本。适用于长会话角色扮演记录、短篇小说、中长篇片段、剧情大纲、剧本初稿、互动叙事等；当用户要求"剧本解读、演员读本、导演阐述、影视化分析、改编分析、短篇小说转影视开发文档、故事转剧本前置分析、给演员/编剧/导演/制片看的分析、AI 剧本化提示包"等任务时触发。输出可按目标受众区分：完整开发读本、演员读本、编剧改编读本、导演视听读本、制片摘要、AI 剧本化提示包、快速诊断。Votes: 0GitHub stars: 5
- Nature Wildlife DocBlue-chip natural-history documentary: awe-led cinematography, character-framed animals, Attenborough-style narration, long-lens tracking, aerials, macro, night/IR, timelapse. Use for natural-history and wildlife films.Votes: 0GitHub stars: 5
- Neelshah1810 Explainer VideoCreate a clear, memorable EXPLAINER VIDEO as one self-contained HTML file: problem → how it works → proof → next step, told with kinetic typography, animated diagrams, before/after comparisons and product moments, synced to a voiceover (with captions) or carried by type and a synthesized score. Verified frame by frame and exportable to MP4. Use for \"explain how it works\", \"what is X\", feature explainers, one-video-per-feature series, concept and process explainers, service explainers and ...Votes: 0GitHub stars: 5
- Neelshah1810 Launch FilmCreate a cinematic product or feature LAUNCH FILM as one self-contained HTML video (kinetic typography, motion graphics, rebuilt product UI, a synthesized score that drops on the reveal), verified frame by frame and exportable to MP4. Use for launch videos, product announcements, \"we just shipped\" films, hero videos for a launch page, Product Hunt or keynote openers, and teaser trailers, for any brand, product, app, service or idea, in any style (professional, clean, bold, fun, premium, tec...Votes: 0GitHub stars: 5
- Neelshah1810 Tutorial VideoCreate a clear step-by-step TUTORIAL or HOW-TO VIDEO as one self-contained HTML file: a numbered step HUD with progress, the real UI rebuilt in HTML/CSS, a zoom to each control, a spotlight before each click, a cursor that clicks and types, keycap overlays, success states and a recap, with a synced voiceover or captions and a calm synthesized score. Verified frame by frame and exportable to MP4. Use for how-to videos, help-center videos, onboarding steps, training and enablement clips, featur...Votes: 0GitHub stars: 5
- Netflix DocuseriesStreaming-era docuseries: cinematic polish, Slow Media pacing, episodic cliffhangers, character-driven first-person narration, archival organised by decade and theme. Use for multi-part docuseries, personality docs and premium non-fiction series.Votes: 0GitHub stars: 5
- Novel To Ai Short Drama Skill将小说、网文或故事片段改编为可直接服务 AI 短剧生产的分集导演台本与逐镜头方案，包含时长规划、画面化改写、表演调度、景别、机位、运镜、声音、连续性与生成备注。适用于小说剧本化、短剧化、分镜化、导演化、AI 视频脚本和拍摄台本；不用于只做文学润色或续写小说。Votes: 0GitHub stars: 5
- Novel To Manju把任意小说做成抖音竖屏漫剧/短视频的全流程主控，完全自包含。当用户要"做漫剧、小说转视频、漫剧剧本、爆款改文、原创小说、人物提示词、场景提示词、三视图、分镜、镜头提示词、打斗特效、MiniMax H3 视频提示词、封面"等任一环节时使用。内含全部规则与输出格式，无需外部文件。Votes: 0GitHub stars: 5
- Op Docs ShortShort-form prestige documentary: one focused story told really well, under 20 minutes, form-forward and creative, paced for digital. Use for short documentaries, opinion docs and festival shorts.Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Autodl App InstancePowers AutoDL Art application instances on and off via official API, finds the ComfyUI panel by probing the instance's proxy service domains from the snapshot API (no SSH needed, works on macOS / Linux / Windows), and waits until ComfyUI is ready for MiniMax H3. Use when the user mentions AutoDL 应用实例, API开机, API关机, autodl.art, AUTODL_TOKEN, 远程服务器开关机, or wants the agent to boot a GPU box before minimax-h3 and shut it down after video generation. It can wrap a minimax-h3 job with boot-before-ge...Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Beauty Video Gen生成超写实、真实感、亲近感的美女时尚竖屏短视频（MiniMax H3 云端生成）。当用户要求"生成美女视频 / 真实感美女 / 亲近感美女视频 / 美女短视频 / 时尚美女视频 / 定制美女视频"，或用"可爱、亲切、性感、清纯、轻熟"等风格词，或用"夸张身材 / 大长腿 / 丰满身材 / 腿占画面大半 / 低机位拉腿"等身材词要求生成真人女性视频时使用；即使用户没提"美女"二字，只要是"生成真人女性出镜的短视频"也应触发。整合《真人时尚短视频提示词写作框架》提示词写作、可选的人物面部参考图生成（仅用户明确要求"先定脸/出面部参考图"时执行，默认直接文生视频；生图优先用当前 Agent 自带的生图能力，备选 cursor-image-gen）、minimax-h3 全流程（AutoDL 开关机、工作流发现、提交轮询、本地归一化、抽帧验收）。Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Character Three ViewPrepares reference art for video production from a script or asset list: character reference sheets (including outfit-state variants), prop references, and scene concept images, then verifies each generated image. Works for any project style — photoreal, anime, cartoon, fantasy creatures. Use when the user asks for 美术设定集, 人物三视图, 道具三视图, 场景概念图, 角色立绘, or visual refs before video. Prefer the running agent's own image generation tool (e.g. Codex ImageGen); use cursor-image-gen only when no nativ...Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Cursor Image GenGenerate or edit bitmap images by launching a local Cursor Agent (cursor-grok-4.6-high) and using Cursor GenerateImage, then saving files to an exact folder. Use when the running agent has no native image tool, or the user explicitly requests Cursor, for photos, illustrations, icons, banners, mockups, turnarounds, or reference-guided images, including 文生图, 图生图, 多参考图, and 改图. Do not use when the current agent already has a working image-generation tool, unless the user asks for Cursor. Do not ...Votes: 0GitHub stars: 5
- Open Source Video Gen Skill H3 Prompt WritingWrite MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, defining reference labels, or when the caller hands off a structured handoff (the production's own shot/segment notes, or a minimax-h3 brief) after choosing a workflow. Do not SSH, pick ComfyUI workflows, or submit GPU jobs.Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Minimax H3Use a remote SeetaCloud or AutoDL ComfyUI GPU instance to generate MiniMax H3 videos. Connects over SSH, discovers the current H3 workflows, helps choose U03/U06/U02, uploads references, submits a job, and downloads the result. MiniMax H3 supports 5–15 seconds per generation; choose the duration from the user's request and the scene instead of assuming a fixed default. Use when the user asks for MiniMax H3, ComfyUI, SeetaCloud, AutoDL video generation, text-to-video, image-to-video, or refere...Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Minimax Music Gen用 AutoDL GPU 实例上的 MiniMax Music 3（ComfyUI）生成音乐：人声演唱的完整歌曲 （自定义歌词、女声/男声、任意曲风）或纯音乐 BGM（instrumental）。Use when user wants to generate music, songs, or audio tracks — 生成音乐、写歌、把歌词变成歌曲、生成背景音乐/ 配乐/纯音乐、来首歌、MiniMax Music、BGM、伴奏、情歌 all trigger; match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or recommendations without generation.Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Qwen3 Tts用 AutoDL GPU 实例上的 Qwen3-TTS 生成配音语音（TTS）。当用户需要旁白、画外音、 配音、台词朗读、文字转语音、特定声线（如甜妹音、大叔音、御姐音）、克隆某个人的 声音，或为 MiniMax H3 视频补对白/旁白音轨时使用。触发词包括：TTS、配音、旁白、 语音合成、文字转语音、音色、声线、克隆声音、voiceover、text-to-speech。 三种音色控制：文字描述设计音色（VoiceDesign）、9 种内置音色+风格指令 （CustomVoice）、参考音频克隆（VoiceClone）。不要用于生成歌曲或背景音乐 （那用 minimax-music-gen）；不生成本地已有音频的转码或播放。Votes: 0GitHub stars: 5
- Open Source Video Gen Skill Short Drama ProductionOrchestrate an end-to-end short-drama or short-film production from a user's theme: approved brief, then — for multi-episode projects — a graded episode outline, then per-episode screenplay with dialogue, art reference assets, and video generation with optional music and dubbing, to a finished video. Single short films (about one minute, not a series) skip the outline stage. Use when a user wants an AI agent to turn a drama or short-film idea into a production, or to resume such a project. Pa...Votes: 0GitHub stars: 5
- Openmontage 3d World Generation为动画或电影项目构建连续可编辑的 Three.js 三维场景，支持浏览器原生 HyperFrames 与 Blender/FFmpeg 两条交付路线，适用于需要真实立体空间感、统一坐标系与可复用制作资产的成片场景。Votes: 0GitHub stars: 5
- Openmontage Animated Drawing让用户提供的类人简笔画或照片通过真实动捕数据动起来，输出透明 GIF 或 MP4；适用于已有手绘角色、希望其跳舞挥手跳跃的短视频场景，矢量自绘场景请改用 ink-art。Votes: 0GitHub stars: 5
- Openmontage Animation Asset Director动画管线的素材制作阶段，负责生成旁白、图表、数学渲染、动态背景、代码可视化以及可复用的字体与版式系统。适用于需要在批量生成前确定视觉系统、控制预算并保证风格一致性的动画项目。Votes: 0GitHub stars: 5
- Openmontage Animation Compose Director动画管线的渲染合成阶段，强调文字锐利度、时间完整性以及输出节奏的一致性。适用于图像驱动动画的合成 JSON 构建、音乐选取、渲染前校验与渲染后自检。Votes: 0GitHub stars: 5
- Openmontage Animation Edit Director动画管线的剪辑决策阶段，把场景规划转成达到动态分镜水准的剪辑方案，核心产出是时间设计。适用于需要为关键揭示留出停顿、为次级元素安排错位入场、并保证动效服务于层级的动画项目。Votes: 0GitHub stars: 5
- Openmontage Animation Executive Producer动画管线的总制片人角色，串行调度各阶段导演、审查其产出、决定放行或打回重做，并在各门禁处施加动画专属的跨阶段判断。适用于需要状态化编排、预算管控与反死循环保护的全流程动画制作。Votes: 0GitHub stars: 5
- Openmontage Animation Idea Director动画管线创意总监技能，用于确定动画模式、视觉路径与复用策略并产出创意简报，适用于运动图形、动态字体、图解说明、数学可视化和插画动画等以设计运动为核心的视频项目。Votes: 0GitHub stars: 5
- Openmontage Animation Pipeline规定 OpenMontage 中动画与动态图形的运行时选择、帧率、缓动、转场、构图与导出标准，适用于解说视频、产品宣传、动效包装等所有需要专业运动节奏的成片。Votes: 0GitHub stars: 5
- Openmontage Animation Proposal Director动画管线提案总监技能，把研究简报转化为可审批的制作方案，锁定渲染器家族与渲染运行时并给出成本估算，适用于动画视频在投入制作前的方案定稿与预算审批环节。Votes: 0GitHub stars: 5
- Openmontage Animation Publish Director动画管线发布总监技能，负责按实际动画模式与视觉体系包装元数据、缩略图概念与平台版本，适用于成片渲染完成后的发布打包与多平台分发环节。Votes: 0GitHub stars: 5
- Openmontage Animation Research Director动画管线研究总监技能，通过联网检索同时研究主题内容与动画技法，产出带数据点、受众洞察和技法参考的研究简报，适用于动画视频在创意决策前的素材收集阶段。Votes: 0GitHub stars: 5
- Openmontage Animation Runtime Selector根据视频需求选择合成运行时（Remotion、HyperFrames 或 FFmpeg）及对应动画库，并路由至正确的 Layer 3 技能。适用于提案阶段锁定 render_runtime、编写动画组件或不确定该用 GSAP 插件还是内建原语的场景。Votes: 0GitHub stars: 5
- Openmontage Animation Scene Director动画分镜导演技能，将剧本转化为可执行的动画分镜计划，适用于需要统一镜头语言、转场体系与工具路径的动画制作场景。Votes: 0GitHub stars: 5
- Openmontage Animation Script Director动画剧本导演技能，把已通过的提案转化为动画可用的叙事节拍与配音线索，适用于各类动画模式的脚本创作场景。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Asset Director为口播数字人流水线准备核心素材，包括旁白、数字人或口型同步画面、字幕文件、品牌背景与最低限度的辅助图形，适用于需要真实播报形象的短视频制作场景。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Compose Director负责数字人口播流水线的最终渲染，把控播报形象稳定、语音清晰、字幕与辅助卡片不遮挡人物，适用于需要交付成品口播视频的合成阶段。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Edit Director把数字人口播的计划场景与素材剪辑成连贯时间线，保证播报节奏稳、辅助层可读、CTA 落点清晰，适用于口播视频的剪辑决策阶段。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Executive Producer数字人口播视频流水线的执行制片人技能，按阶段串行调度七个导演技能并把控质量门。适用于口型同步、主播构图、音频清晰度与行动号召落地需要严格验收的口播项目。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Idea Director数字人口播流水线的创意总监技能，负责在写稿前判定虚拟形象路线、明确信息形态与素材现实。适用于口播广告、产品介绍、入职培训、内部通报与短脚本讲解的立项阶段。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Publish Director数字人口播流水线的发布总监技能，负责把成片与各衍生版本清晰打包并附上信息导向的元数据。适用于需要区分主剪、竖版方版衍生、多语言版本与审核版本的交付环节。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Scene Director为虚拟形象口播管线规划视觉系统，确定主讲人画面布局、背景规则、辅助图层与画幅变体策略，并覆盖无头像纯旁白回退方案，适用于口播视频分镜与画面设计阶段。Votes: 0GitHub stars: 5
- Openmontage Avatar Spokesperson Script Director将已批准的创意简报转化为虚拟形象可安全分场景的口播文案，强调口语清晰度、可信节奏与单场景单要点，并覆盖制作中事实核查流程，适用于口播视频脚本创作阶段。Votes: 0GitHub stars: 5
- Openmontage Bespoke Composition从零手写合成而非拼装现成场景类型的工坊模式指南，涵盖艺术方向、场景独立性和引擎机制。适用于主角作品、品牌片、发布会等质量至上的单次交付物。Votes: 0GitHub stars: 5
- Openmontage Bg Remove Usage说明 OpenMontage 中 bg_remove 抠图工具的使用方式，涵盖模型选择、alpha matting 取舍、批量帧处理与合成前质检，适用于产品演示、人物合成、缩略图与绿幕替代等资产准备场景。Votes: 0GitHub stars: 5