All authors
Claude Skills by Wanfeng1028
github.com/Wanfeng1028590 skills0 installs0 views
- DirectoryDirect and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解), and new films cut from real archi...Votes: 0GitHub stars: 5
- 02ui Video CopyMake product-launch / motion-graphics videos in HyperFrames, in two modes. ORIGINAL (no reference): pick a category from the type files and build a launch video from scratch with the skill's motion rules. CLONE: rebuild a reference video as closely as possible — same shots, timing, easing, transitions and type — in HyperFrames, optionally re-skinned for a different brand. Opus can't watch video, so a burst-frame analyzer turns the reference into per-shot frame sequences, motion trails, easing...Votes: 0GitHub stars: 5
- 0xadvait Ai VideoGenerate AI video of any kind, end to end — write the prompt, create first-frame stills, run the generation across six video models (Seedance 2.0, Kling 3.0, Wan 2.7, Veo 3.1, OmniHuman 1.5, VEED Fabric), synthesize voiceover, stitch clips into a finished cut, and upscale for delivery. Use whenever the user wants to make or improve a video: cinematic shots, character dialogue, action, dance, native SFX, image-to-video, motion transfer, lip-sync, talking-avatar / "a video of me", real-person p...Votes: 0GitHub stars: 5
- 0xsline Short Drama短剧编剧全流程：选题立项、故事骨架、四层反派人物、带钩子和付费卡点的分集目录、逐集剧本、五维评分自检和合规审核，可切出海英文格式Votes: 0GitHub stars: 5
- 24fps BriefTurn "I want to make a short talking-head video about X", or no idea at all, into a confirmed brief and a teleprompter script before anything is recorded or edited. Use whenever the user wants to plan, script or research a short video (Shorts, Reels, TikTok, YouTube, LinkedIn, X), asks "what should I talk about", wants video ideas, topics or hooks, a daily news or new-tools or trending-repos video, a teleprompter script, an outline with sources, or a brief.md. Writes brief.md, research.md, so...Votes: 0GitHub stars: 5
- 24fps MotionSearch a library of 4,600+ AI motion graphics with their prompts and 2,100+ video-editor presets before building any motion graphic or video edit from scratch. Use whenever the user wants styled captions on video (karaoke, word-by-word, TikTok, Reels, Shorts), hooks, kinetic typography, titles, lower thirds, text behind the subject, transitions, colour grades and film looks, split-screen layouts, font pairings, logo reveals, intros, product launch videos or explainer videos, in HyperFrames, R...Votes: 0GitHub stars: 5
- 5min Drama Contest引导参赛者从零推演并写出高质量的五分钟短剧剧本。适用于五分钟短剧大赛选题、世界与角色设定、首尾设计、四幕卡点大纲、正式剧本和分镜脚本创作；强调前 30 秒入戏、结构承诺兑现与设定一致性。Votes: 0GitHub stars: 5
- A Roll MattingA-roll prep: get a talking character OFF their background (matte) or onto green BEFORE any editing. Covers chroma key, temporal AI video matting (RVM/MODNet/backgroundremover), per-frame AI matting (rembg), and roto - with verified local recipes, quality checks, and output formats. Use as the FIRST job on any voiceover / talking-head / avatar / podcast video.Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Assets角色、场景、道具、关键帧的全资产规划与GPT Image独立提示词。Votes: 0GitHub stars: 5
- Scene DesignRoute the external scene-concept-art-director specialist into Acheng assets without creating a second production truth.Votes: 0GitHub stars: 5
- ExternalTurn a brief, approved moodboard, or existing scene image into a structured scene-art direction contract, model-ready environment prompts, reference upload rules, multi-view continuity notes, and evidence-based visual QA. Use for film, animation, game, commercial, architectural, fantasy, sci-fi, historical, interior, landscape, and repair workflows.Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Continuity跨镜跨集事实重放、冷档恢复与分层交付验收。Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Effects Scale按效果家族创建或优化视效，并设计可信巨构尺度。Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Model Output将已批准制作数据编译成GPT Image与H3的独立请求及上传清单。Votes: 0GitHub stars: 5
- H3 Prompt WritingMiniMax H3 视频生成提示词撰写与优化专家 (T2VA, I2VA, FL2VA, L2VA, Ref2VA)。 Write and optimize structured MiniMax H3 video generation prompts for all five generation modes: T2VA (文生视频+音效), I2VA (首帧图生视频), FL2VA (首尾帧生成), L2VA (尾帧逆推), and Ref2VA (全参考模式). Composes integrated_multimodal_description, overall_soundscape, non_diegetic_music, shot breakdowns, and reference anchors. Trigger when user mentions 'minimax h3', 'h3 prompt', 'h3 提示词', 'h3-prompt-writing', '视频提示词', or asks to write/rewrite prompts for MiniM...Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Performance Action文戏的表演因果、动作的受力因果以及从上游表演交接到镜头的适配。Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Shots根据叙事功能设计分镜、摄影、剪辑与4–15秒生成切片。Votes: 0GitHub stars: 5
- Acheng Director Skill Acheng Story多线剧本、角色弧光、信息权限、伏笔与局部润色。Votes: 0GitHub stars: 5
- Acheng Director SkillAcheng Director 用于编写和生产影视剧本、分镜、文戏表演、动作、视效、角色场景资产及 MiniMax H3 或 Seedance 提示词；用场景登记、双时长、132 运镜索引和连续性账本保持跨镜一致性。已有确认稿时仅进入缺失阶段，支持冻结时间线的视效原位优化。Votes: 0GitHub stars: 5
- ColossalDirect colossal-scale images and prompts for megastructures, monumental architecture, giant artifacts, kaiju, cosmic entities, and pure-organic giants. Use for 巨构、超巨构、巨物、巨像、巨兽、巨怪、克苏鲁巨物、有机巨物, or when scale feels small, flat, toy-like, fragmented, over-detailed, or lacks depth. Own scale proof, framing, spatial hierarchy, decisive event, and anti-fragmentation; preserve the requested medium and hand off general style and model syntax.Votes: 0GitHub stars: 5
- Im2Default material, information-density hierarchy, clean-rendering, negative-prompt hygiene, and evidence-preserving photo-repair layer for IM2 / GPT Image 2 / gpt-image-2 / image_gen. Use for clean generation/redraws, artifact cleanup, focal-detail control, atmospheric depth, physically coherent light paths, air scattering, volumetric light, light ratio, material realism, architecture/terrain/hard-surface scene mass and structural grounding, and 企业/公司活动/门店/团队合影/商品/餐饮/证件文档照片修复. Preserve identit...Votes: 0GitHub stars: 5
- Prompt Library提示词资产库与结构拆解技能 (Prompt Library Skill by hong hou zi)。 对用户输入的提示词进行 6 要素结构拆解、8 种技巧识别、5 维度质量评估、适用性分析与智能归档。Votes: 0GitHub stars: 5
- Ad AgentDirect Creatify's Ad Agent MCP to make or edit a video ad end to end. It generates Boreal-H3 footage, keyframes, music and voice lines into a persistent project, you judge every clip from contact sheets, you assemble one index.html page, and it ships a gated MP4. Use it whenever the user wants to make a video ad with Creatify, compose a video from references, use the Ad Agent, resume a composer project, give notes on a take, regenerate shot N, edit this take, or change a cut, caption, CTA or ...Votes: 0GitHub stars: 5
- Ad From Product UrlStart a Creatify video ad from a product page URL. Researches the page, creates an Ad Agent project seeded with the product's real images and logo, and returns the project_id, then hands off to the ad-agent workflow to generate, judge and ship the ad. Use when the user says "make an ad for this product" or pastes a store/product URL. Requires the creatify-ad-agent MCP server (composer_* tools).Votes: 0GitHub stars: 5
- Adu Motion Video使用完整动画工程包，把新口播、文案与自有素材制作成可编辑动效视频和 60fps MP4；也支持轻量 TPL、手绘续接、字幕与改旧片。支持 Windows、macOS、Linux，以及 Codex、Claude Code、豆包、DeepSeek、WorkBuddy 等可读写文件并运行命令的助手。Votes: 0GitHub stars: 5
- Agency ShowreelAgency, studio and freelancer showreel and case-study video: 60-90 s reels, capability films and project case studies. Best-work-first rhythm, beat-matched montage, credit and rights handling, with a mandatory asset-request protocol. Use for video studios, motion designers, production companies and creative agencies.Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Character Performance Assets将已锁定的剧本事件和原文台词转换为可调用的人物表演方案，建立角色表演DNA、场景目标、阻碍、策略变化、听者反应、身体行为、表演节拍和跨镜状态继承。适用于人工智能漫剧与视频分镜的对白、独白、沉默、威胁、喜剧和关系戏；不负责改写台词、决定分集、设计摄影机或输出最终视频提示词。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Cinematic Directing Assets为人工智能漫剧、动画短片和视频生成提示词提供可调用的专业导演语言资产，协调人物表演、镜头功能、摄影机、动作特效和执行连续性，并返回中性导演镜头表示。适合由“人工智能漫剧导演”在生成 Seedance 2.0 或2.5分镜组前调用；不负责拆集、改写原剧本、管理项目资产或直接替代最终模型提示词。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Comic Scene Assets将完整小说或剧本中的跨集场景整理为可继承的一致场景资产体系，建立场景家族、空间关系、固定视觉DNA、区域母资产、机位资产、状态变体和生图提示词。适用于人工智能漫剧场景资产规划与一致性生产；不负责人物、道具、拆集、分镜或改写剧情。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Shot Execution Continuity对人工智能漫剧和视频的既定镜头方案执行第一帧、人物站位、身体朝向、视线、道具手、摄影机轴线、光线方向、动作物理、音轨承接与切镜状态检查，并返回可编译的局部修复锁。适用于分镜设计完成后、生成最终视频提示词前；不负责改写剧情、重新拆集、默认改成一镜到底或替代最终提示词。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Storyboard Asset Grounding将用户已经完成的场景、角色、道具和声音资产逐项查看、核验并转换为分镜可调用的身份、空间、光线、道具状态与声音绑定锚点。适用于用户提供剧本和成品资产后、设计视频分镜提示词之前；不负责生成资产、改写剧情、决定分集、设计镜头或输出最终视频提示词。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Ai Storyboard Blocking Assets在已有剧本与本地成品资产基础上，为每个分镜组制作真实场景中含对应角色的站位参考图，按空间关系判断相邻组复用，保存图片并绑定分镜提示词。适用于漫剧跨分镜组人物位置与状态连续性；不替代剧本改编、分镜导演或视频生成。Votes: 0GitHub stars: 5
- Ai Comic Drama Director Skills Make Ai Comic Drama根据当前剧本和用户提供的资产，制作连贯紧凑、表演明确、空间可执行、声音完整的分镜组提示词；默认轻量提示词流程，用户明确要求完整项目制作时才启用资产生产与项目管理流程。Votes: 0GitHub stars: 5
- Ai Film Skills Ai Storyboard Director根据剧本与已定导演方案设计观看顺序、人物调度、电影摄影和剪辑，编写或修订分镜与视频提示词；支持创意镜头思路、打戏和运镜诊断。创意思路可单独交付或并列于主分镜，采用后才纳入；分镜、提示词与实际生成按当前阶段分别执行。Votes: 0GitHub stars: 5
- Ai Film Skills Character ConsistencyKeep one character identical across every generated shot. Expand a short Character Brief into ultra-detailed generation prompts, build a three-panel character sheet (bust-up, full body front, full body rear) from a single close-up, and attach it as an identity reference on every generation. Use when the user wants the same character to stay consistent across multiple shots, scenes, or takes.Votes: 0GitHub stars: 5
- Ai Film Skills Director AgentCreate, revise, or diagnose screenplays and develop director treatments or pre-storyboard decisions covering causality, character action, dialogue, performance, visual storytelling, sound, editing, and optional AI-executable screenplay compilation. Exclude editing an existing image, static visual polishing, static character/scene/prop reference-image design, and shot expansion from an already approved director plan. Use for "导演Agent", "导演思维", "导演分析", "导演方案", "写剧本", "改剧本", "剧本编辑", "剧本诊断", "AI可...Votes: 0GitHub stars: 5
- Ai Film Skills Prop Asset根据剧情、使用方式与美术方向设计道具形制、结构、材质及多视角/关键细节设定图。用于道具设计、道具资产、道具设定图、道具细节图、prop、物品图；输出静态参考图任务说明与资产合同， 本 Skill 独立完成静态参考图任务说明、资产锁定、审核字段、负向约束和可供后续制作直接读取的资产合同。Votes: 0GitHub stars: 5
- Ai Film Skills Scene Asset根据剧本设计电影场景的美术、构图、光色与氛围，常规场景默认主图加反打图；按用户需要扩展同空间多机位或九宫格，无指定画风时默认摄影写实。用于场景资产、环境图、房间多角度和场景机位设定；输出静态参考图任务说明与资产合同， 本 Skill 独立完成静态参考图任务说明、空间锁定、审核字段、负向约束和可供后续制作直接读取的资产合同。Votes: 0GitHub stars: 5
- Ai Film Skills Video Prompt DirectorTurn a short scene direction into one submit-ready, Seedance 2.5-optimized prompt for reference-to-video (R2V) generation. Use when the user gives a scene idea, action choreography, or shot description with reference images and wants a full video prompt built from it — reference role mapping, staged event script, camera and audio design included.Votes: 0GitHub stars: 5
- Ai Manga Drama Ai Manga Drama EnProduction assistant for AI dynamic comics and short anime drama - concept and script, episode briefs and storyboards, character and location design, image and video prompts, motion and camera work, voice, lip sync, mixing and subtitles, continuity management, review and scoring, multi-platform delivery and release, and commercial review. Use when the user mentions making an AI manga drama, dynamic comic, comic video, animated short, storyboarding, character consistency, face repair, first an...Votes: 0GitHub stars: 5
- Ai Manga DramaAI 动态漫画与漫剧（动漫短剧）制作助手，覆盖全流程：选题与剧本、单集任务卡与分镜、角色与场景设定、图像与视频提示词、动态化与运镜、配音口型与混音字幕、连续性管理、审片评分、多平台交付与发布、商业化复盘。当用户提到做漫剧、AI 动态漫画、漫画视频、动漫短剧、漫剧项目、分镜、角色一致性、换脸修复、首尾帧、对口型、竖屏交付、AI 标识或完善漫剧项目时使用；也适用于只想要提示词与制作清单、暂不生成成片的场景。Votes: 0GitHub stars: 5
- Ai Short Drama Drama Script爽剧短剧剧本创作技能。基于专业爽点模型，把一个想法、故事或明确创作需求发展成快节奏、强冲突、可拍摄、可续写、可改写，并能继续提取角色、空镜场景、道具和拆分视频分镜的完整爽剧剧本。适用于霸总、赘婿、重生、复仇、逆袭、战王、神医、甜宠等爽剧题材；不承担通用影视剧本、专业小说改编或上传剧本解析。Votes: 0GitHub stars: 5
- Ai Short Drama Drama Shot Prompt把已确认的单集剧本和可用角色、场景、道具资产拆成连续的镜头级视频片段，并为每个片段编写可直接提交 Seedance 2.0 系列的视频提示词。适用于短剧分镜、镜头节奏设计、参考图绑定、对白音效编排和视频生成前的提示词生产。Votes: 0GitHub stars: 5
- Ai Short Drama Script Brief将一句话、零散设定或模糊的爽剧想法扩展为结构化、可编辑、可直接交给 drama-script 的专业创作需求；用户点击 AI 优化需求，或输入缺少角色、冲突、转折、结局等关键信息时使用。Votes: 0GitHub stars: 5
- Ai Short Drama Sd2 PeOptimizes user prompts for Seedance 2.0 multi-modal video generation. Invoke when a user provides an initial prompt or multimedia assets for video generation, or explicitly requests prompt optimization.Votes: 0GitHub stars: 5
- Ai Short Drama Sd25 PeUse 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.Votes: 0GitHub stars: 5
- Ai Short Drama Skill Dramake面向 Codex、Claude Code、WorkBuddy 和其他 Agent Skills 客户端，把一句话点子、故事梗概、小说、文案、剧本、分镜或已有素材，串成可理解、可衔接、可发布的 AI 短剧与 AI 短片。适用于抖音、红果短剧、视频号、快手、B站、YouTube 等横屏或竖屏内容；支持真人、独立短片、单元剧、连续剧、宠物、拟人奇幻、动画/漫剧、UGC 和品牌剧情。用于故事诊断、编剧、分镜、角色/重复道具一致性、Wan 3、Seedance 2.5/2.0/Fast、MiniMax H3 等模型选路、15–30 秒长段、原生对白、参考音频、配音、付费预算、连续性剪辑、物理质检和冷观众验收，尤其用于避免碎片硬拼、随机跳切、站桩对白、身份/服装/道具漂移、文字变形、运动方向错误、穿模、平淡观察镜头、口型/声线不一致、音乐重启和剧情看不懂。Votes: 0GitHub stars: 5
- Ai Short Drama設計、編劇、製作與迭代爆款 AI 短劇／漫劇／仿真人直式連載。用於「AI短劇」「AI漫劇」「爽劇」「微短劇」「爆款情景」「一鏡到底」「宮格成片」「故事連鏡」「角色三視圖」「假廢物真強者」「扮豬吃虎」「重生」「轉生／穿越」「系統流」「隱藏大佬／隱藏身份」「逆襲／打臉／復仇」「真假千金」「末世」「修仙」「規則怪談」「ReelShort／DramaBox 風」「分集大綱」「每集鉤子」「季節拍」「短劇角色一致性」「把小說改短劇」「短劇為什麼不爆」「規劃一季／寫下一集」「從故事到AI成片」「一鍵做短劇」「100%自動化」「全部你來」等任務。負責題材雷達、片型路由、概念綠燈、系列 Bible、資產註冊、逐鏡時間線、爽點與揭露階梯、分集編劇、連載狀態、production pack、可續跑生成、成片 QA 與成效回填；實際媒體提示詞交給 ai-media-generator，完整剪輯交付可串接 video-autopilot 或相容執行器。Votes: 0GitHub stars: 5
- Ai Video ProductionRoute AI video production work to the right skill for ad analysis and dialogue-led recreation, Blender previs, Seedance 2.5, MiniMax H3, Wan 3.0, supporting GPT Image 2.5 still images, or local video metadata cleanup. Use for multi-stage production, reference planning, or choosing among these skills; go directly to the named skill for a simple specific request.Votes: 0GitHub stars: 5
- Analyze Hit Novel系统拆解商业小说、网文、悬疑或类型小说的爆款机制。用于用户提供小说全文、章节、梗概或阅读笔记，并要求拆书、分析人物关系与冲突、还原故事时间线、比较叙事顺序、评估章节钩子和节奏曲线、提炼人物弧光与可迁移创作规律，或生成不照搬原作的新故事灵感时。Votes: 0GitHub stars: 5