Zackd Director
Turn ONE curiosity-driven topic or question into a finished Zack D Films-style 3D animated short video, end to end on the MuAPI platform + local ffmpeg — curiosity-loop script, character consistency sheets, 3D keyframe rendering, motion clips, cloned voiceover, zoom-ins, transitions, and captions, all automated. Use this whenever the user wants a "Zack D Films style short", a 3D medical / anatomical / educational explainer short, a curiosity-driven short video, or wants to automate 3D animated short production with an API-backed media pipeline. Triggers: "zack d films short", "zack d style", "
Install
npx skills add Anil-matcha/zack-d-films-ai-video-generator --skill zackd-directorgit clone --depth 1 https://github.com/Anil-matcha/zack-d-films-ai-video-generator.git /tmp/zack-d-films-ai-video-generator
mkdir -p ~/.claude/skills
cp -r /tmp/zack-d-films-ai-video-generator/. ~/.claude/skills/zackd-directorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 🎬 Zack D Director Turn a single topic or question into a finished **Zack D Films-style 3D short video**: a fast-paced, curiosity-hooking, 3D animated short where every line opens a question your brain needs closed, supported by consistent 3D character sheets, high-impact motion, cloned voice narration, key-beat zoom-ins, and screen shakes between scenes. Powered by **MuAPI Platform (api.muapi.ai)** + **Google Veo 3.1** + local **ffmpeg**. --- ## 💡 The Core Workflow & Principles The Zack D Films visual style and viral retention formula rely on 4 critical pillars: 1. **Curiosity-Loop Script Structure**: Every sentence opens an open loop (a question your brain physically needs answered), driving scroll-stopping retention. 2. **Character & Object Consistency Sheets**: Recurring characters, anatomical parts, or items are rendered on standard 3D turnaround sheets first. Every scene uses these sheets as visual anchors to guarantee exact visual identity across angles and wear. 3. **Signature 3D Render Style**: Stylized 3D digital art, smooth clay/plasticine subsurface scattering, crisp ambient occlusion, cross-section views, vibrant lighting, and cinematic depth of field. 4. **Fluid Editing Conventions**: Fast cuts (every 2–4 seconds), camera zoom-ins on key impact beats, and short transitions between scenes. --- ## 🛠️ Prerequisites 1. **MuAPI Key Setup**: - `export MUAPI_API_KEY="sk-..."` (get your key at https://muapi.ai) 2. **Local Tools**:
Details
- Skill name
zackd-director- Repository
- Anil-matcha/zack-d-films-ai-video-generator
- Repo updated
- 6 October 2026
FAQ
What does the Zackd Director skill do?
Turn ONE curiosity-driven topic or question into a finished Zack D Films-style 3D animated short video, end to end on the MuAPI platform + local ffmpeg — curiosity-loop script, character consistency sheets, 3D keyframe rendering, motion clips, cloned voiceover, zoom-ins, transitions, and captions, all automated. Use this whenever the user wants a "Zack D Films style short", a 3D medical / anatomical / educational explainer short, a curiosity-driven short video, or wants to automate 3D animated short production with an API-backed media pipeline. Triggers: "zack d films short", "zack d style", "
How do I install the Zackd Director skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Anil-matcha/zack-d-films-ai-video-generator --skill zackd-director. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Zackd Director popular?
It lives in Anil-matcha/zack-d-films-ai-video-generator, which has 31 GitHub stars and 4 forks.
Related skills
Read Anything
31heyuxuan0209/read-anything
即时分析：任意链接（网页/博客/YouTube/B站/小宇宙播客/X）或本地录音（会议录音/语音备忘录）→ 抓取或本地转写 → 中文结构化解读（精读稿/快扫/访谈拆解/会议纪要/论文拆解/选题素材六种模板+自定义）→ 基于材料的多轮问答。触发：用户丢链接/音频文件/粘贴纪要并说"分析/解读/精读/这是什么/讲了啥/值得看吗/提选题"，或明确说"即时分析"。
Live2d Halfbody
29bellisji233/live2d-halfbody-skill
从一张立绘或一段角色描述，做出能在 VTube Studio 里直播用的半身 Live2D 皮套，不用手动建模、不开 Cubism Editor：图像模型出图、See-through 拆层、代码补细节和绑定、自查后装进 VTS。默认带小角度转头、歪头、身体跟随、呼吸、眨眼和单眼眨眼、口型、四个表情、头发分段摆动（短发、过肩长发或双马尾，刘海可有可无，侧发可别在耳后）、挂件和耳坠摆动、眼镜、招手/摊手/指向三个手势和脸红。用于用户想新做一个皮套（有立绘、只有描述、或已有分层文件）、检查皮套素材、或调整已有角色的动作幅度时。Builds a half-body Live2D avatar for VTube Studio from one character illustration or a text description.
Douban Sync
33cosformula/douban-sync-skill
Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files (Obsidian-compatible). Use when the user wants to export their Douban reading/watching/listening/gaming history, set up incremental sync via RSS, or manage their Douban data locally.
Blender Claymation
28angrypenguinpng/blender-claymation-skill
Make stop-motion claymation videos in Blender from a one-line idea. Builds a miniature clay set and puppet in Python, animates it "on twos" at 12 fps with hand-made boil, renders with Cycles, encodes an mp4, and presents it in a video player. Use when the user asks for a claymation, stop-motion, plasticine or clay animation, a clay character or short film made in Blender, or "an animation that looks like a real studio made it".
Korean Thriller Asset to Video
29Work-Fisher/fisher-storylens
将韩剧式悬疑、复仇小说或剧本按角色生图提示词确认、场景生图提示词确认、用户上传图片后生成MiniMax视频提示词的三阶段流程制作，支持修改造型与连续片段，默认中文交付。
FigFox Gen Skill
33LawrenceRiver/FigFox-Gen-skill
Use when turning a scientific Methodology, with an optional reference image, into one evidence-grounded, human-editable final PNG figure.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.