Video Spec Builder

当用户说想做一个视频、宣传片、产品演示、动画短片、抖音/YouTube 内容，或者说要改分镜、调节奏、换镜头、调字幕、加配音、改转场时使用。通过苏格拉底式追问收集视频需求，主动激发渲染层的全部能力（TTS / 字幕 / 3D / shader / 音频反应等），输出标准化的 video-spec.md 用于渲染。

1,058 stars 125 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add feicaiclub/video-spec-builder --skill video-spec-builder
Manual install
git clone --depth 1 https://github.com/feicaiclub/video-spec-builder.git /tmp/video-spec-builder
mkdir -p ~/.claude/skills
cp -r /tmp/video-spec-builder/. ~/.claude/skills/video-spec-builder

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

[任务]
    **0-1 模式**：通过深入对话收集视频需求，主动告知可用能力（用户往往不知道能做什么），用直白甚至刺耳的追问逼用户在镜头粒度上想清楚，输出包含**分镜表**的 `video-spec.md`。

    **迭代模式**：用户对已有 video-spec.md 提出修改（换镜头/改节奏/换音乐/调字幕/换配色）时，通过追问帮用户想清楚变更，检测与现有 spec 的冲突，更新 `video-spec.md`。

[启动检查]
    1. 扫描项目目录查找 video-spec 文档：
        - 精确匹配：`video-spec.md`
        - 模糊匹配：`*video-spec*.md`、`*分镜*.md`、`*storyboard*.md`
        - 找到 1 个 → 迭代模式（read `references/workflow-iteration.md`）
        - 找到多个 → 列出文件名问用户"你要改的是哪个？"
        - 没找到 → 0-1 模式（read `references/workflow-0-1.md`）
    2. 检查项目根目录有没有 `design.md` / `DESIGN.md`（自定义主题文件；视觉风格阶段才用到，启动时不强制）

[第一性原则]

    [能力优先]
        用户提出的每个需求，你的第一反应是"渲染层能不能做得更好"。
        告诉用户能做什么时，说"它能让画面变成什么样"，不说技术名字。

        - 用户说"加段旁白" → 主动问"要不要我直接帮你生成 AI 配音，省得你录？30 秒搞定，
                              不过会有点'课件感'，没有真人那种小停顿和情绪"
        - 用户说"加字幕" → 主动问"字幕要整句一起跳出来，像看电影那种安静呈现？
                              还是一个字一个字蹦，像 Karpathy 推文那种讲到哪个词亮哪个？"
        - 用户说"想要 3D 感" → 主动问"你想要 Apple 发布会那种产品 360° 真实旋转的沉浸感？
                              还是 Stripe 文档那种卡片飘过的轻盈感？前者更震撼但你得有 3D 模型"
        - 用户说"配乐想有节奏感" → 主动问"要不要让画面跟着鼓点跳？像 DJ 打碟那种，
                              鼓一响元素就缩放、字就抖，跟音乐同呼吸"
        - 用户没主动提某个能力 → 对照 [能力对照表] 主动告知能做什么（说画面，不说技术）
        - 做不到的事 → 直接说做不到，不要假装能做

    [视觉风格的处理]
        用户一旦定下视觉主题，该主题的颜色 / 字体 / 字重 / 动效 / 间距 / 圆角全部跟着定下来，
        别再回头追问这些维度。但**定下来之前**，主题本身是开放的，2 条路径任选。

        - 没定主题前：2 条路径开放（8 个 HyperFrames 预设 / 用户自定义 design.md）
        - 定了之后：该主题的全部细节跟着定下来
        - 不要追问已被主题定下来的维度（如选了 Swiss Pulse 后不要再问"用什么字体"）
Read the full skill on GitHub

Details

Skill name
video-spec-builder
Repository
feicaiclub/video-spec-builder
License
MIT
Repo updated
18 May 2026

FAQ

What does the Video Spec Builder skill do?

当用户说想做一个视频、宣传片、产品演示、动画短片、抖音/YouTube 内容，或者说要改分镜、调节奏、换镜头、调字幕、加配音、改转场时使用。通过苏格拉底式追问收集视频需求，主动激发渲染层的全部能力（TTS / 字幕 / 3D / shader / 音频反应等），输出标准化的 video-spec.md 用于渲染。

How do I install the Video Spec Builder skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add feicaiclub/video-spec-builder --skill video-spec-builder. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Video Spec Builder popular?

It lives in feicaiclub/video-spec-builder, which has 1,058 GitHub stars and 125 forks.

Related skills

Visio Image Rebuilder

1.1k

pengjunchi0/codex-visio-paper-figure-skill

Rebuild or restyle editable Microsoft Visio diagrams from reference images and existing .vsdx files, then export deliverables as .vsdx, PNG, SVG, PDF, or PPTX. Use when the user asks Codex to open Visio, recreate a diagram from a PNG/JPG/screenshot/reference image, match a scientific model figure, update colors/typography/layout in a .vsdx, calibrate panel coordinates to avoid shifted or overlapping submodules, or make publication/presentation outputs while preserving Visio native editable shapes rather than embedding the reference image as a flat picture.

Images, Video & Audio55

Firecrawl Search

676

firecrawl/cli

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.

Images, Video & AudioIn 1 list117

Yuwen Publish Precheck

798

yuwen-cool/yuwen-publish-precheck

国内自媒体发布前风险自审与保意修复：审口播稿、文章、图文笔记、字幕、封面文字能不能发抖音/小红书/微信视频号，给出具体位置、依据和可直接替换的改稿；被限流/删除/处罚后帮你复盘归因；你的行业敏感词、误报白名单和踩坑案例会沉淀成个人规则库，越用越准。Use when 用户说"能不能发""审一下稿子""查违禁词/敏感词""会不会限流/被限流了""帮我改成能发的版本""发布前检查""被平台处罚/删除了""帮我盯着这个词""导入违禁词表"。Not for 海外平台(X/YouTube)内容审核、起号涨粉策略、写稿创作本身。

Images, Video & AudioIn 1 list76

Watch

1.1k

taoufik123-collab/claude-watch

Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.

Images, Video & Audio216

Higgsfield

829

OSideMedia/higgsfield-ai-prompt-skill

Writes and refines prompts for Higgsfield AI's video and image models, and picks the model, camera controls and motion presets for each shot. Use whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema Studio 2.5/3.0, Vibe Motion, troubleshooting failed generations, credit optimization, Photodump, or any mention of higgsfield.ai. Also trigger on generic "write me

Images, Video & Audio142

Ppt Image First

1.2k

NyxTides/ppt-image-first

Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs. Use when the user asks to create a PPT, presentation, deck, 答辩稿, 路演 deck, 产品介绍 PPT, 汇报 PPT, or when the user has only a topic or rough materials and needs help clarifying structure, style, and page planning before generation.

Images, Video & Audio92

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.