Token导航 LogoToken导航TokenDH.com
待分类需要联网github未标认证来源可访问许可证需确认审计通过

video-script视频脚本

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

2,271

周安装

91

GitHub Stars

67

下载量

735
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:video-script(视频脚本)
来源仓库:https://github.com/indranilbanerjee/digital-marketing-pro
仓库路径:skills/video-script
安装命令:
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill video-script
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill video-script

简介

video-script 用于辅助视频生成和动画合成项目开发,适合组织镜头和生成素材说明。

  • 适用于 Remotion 等视频项目,可维护合成代码和排查渲染问题。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态。
  • 使用时需确认分辨率、时长和导出格式;涉及外部素材时应核对版权授权要求。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

/dm:video-script

Purpose

Write a production-ready video marketing script with hook variants, timestamps, visual direction notes, CTA placement, and platform-specific formatting. Produces a complete script package ready for production with visual and audio columns, accessibility notes, and thumbnail concepts.

Input Required

The user must provide (or will be prompted for):

  • Video type: The format of the video — ad spot, explainer, testimonial, product demo, social short, educational tutorial, brand story, or event recap
  • Target platform: Where the video will be published — YouTube, TikTok, Instagram Reels, LinkedIn, YouTube Shorts, Facebook, or multi-platform
  • Target length: Desired duration — 15s, 30s, 60s, 90s, 2-3 min, 5-10 min, or long-form 10+ min
  • Key message or topic: The core idea, value proposition, or subject matter the video must communicate
  • Call to action: What the viewer should do after watching — visit URL, subscribe, purchase, sign up, download, follow, etc.
  • Target audience: Who the video is for — demographics, psychographics, awareness level, and platform behavior
  • Brand tone: Desired tone and energy level — professional, casual, humorous, inspirational, educational, urgent, or conversational
  • Available assets: What production resources are available — on-camera talent, b-roll footage, product samples, graphics/animation capability, studio vs. location, screen recordings
  • Competitor video references: Optional — links or descriptions of competitor or aspirational videos to benchmark against
  • Performance goals: What success looks like — views, watch-through rate, click-through rate, conversions, engagement, or brand lift

Process

  1. Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/dm:brand-setup)?" — or proceed with defaults.
  2. Determine platform specs and format constraints: Reference platform-specific requirements — aspect ratio (16:9, 9:16, 1:1), max duration, safe zones for text overlays, caption placement areas, and native content conventions. Apply platform algorithm preferences (e.g., TikTok favors native-feeling content, LinkedIn rewards professional storytelling, YouTube prioritizes watch time).
  3. Select script structure: Choose the optimal narrative framework based on video type and goals — AIDA (Attention-Interest-Desire-Action), PAS (Problem-Agitate-Solution), problem-solve-CTA, storytelling arc (setup-tension-resolution), listicle, before/after, or direct response. Justify the choice based on audience awareness level and platform norms.
  4. Write 3 hook variants: Craft three distinct opening hooks for the first 3 seconds — each using a different hook technique (bold claim, question, visual shock, pattern interrupt, relatable pain point, or curiosity gap). Provide rationale for why each hook works for the target audience and platform.
  5. Draft full script with timestamps: Write the complete script with second-by-second or scene-by-scene timestamps. Include speaker dialogue or voiceover lines, pause beats, transition cues, and pacing notes. Ensure the script hits the target duration within a 10% margin.
  6. Add visual direction notes: Create a visual column alongside the script specifying camera angles (wide, medium, close-up, overhead), b-roll suggestions, graphics and text overlay placements, transitions (cut, dissolve, swipe), product shots, and screen recordings where applicable.
  7. Place CTAs at optimal points: Position call-to-action moments at strategically timed intervals based on video length — verbal CTA, on-screen CTA overlay, end card CTA, and pinned comment CTA. For shorter videos, place a single CTA at the natural climax; for longer videos, use a soft mid-roll CTA and a strong end CTA.
  8. Add accessibility notes: Write a closed caption script ensuring all spoken content and meaningful sound effects are transcribed. Include audio description notes for key visual-only moments. Specify caption styling (font size, positioning, background contrast) per platform requirements.
  9. Create thumbnail and cover frame concept: Design a thumbnail concept for YouTube or a cover frame for Reels/TikTok — specify text overlay (7 words max), facial expression or product shot, color treatment, and contrast elements that drive click-through. Include 2 thumbnail variant ideas for A/B testing.
  10. Review against brand voice and platform best practices: Audit the complete script against brand voice settings, compliance requirements, and platform content policies. Flag any potential issues with claims, disclosures, music licensing, or platform-specific restrictions. Verify pacing matches platform consumption patterns.

Output

A structured video script package containing:

  • 3 hook variants with rationale explaining the technique used and expected audience response for each
  • Full script with timestamps — second-by-second or scene-by-scene timing from open to end card
  • Visual direction column specifying what the viewer sees at each timestamp — camera angles, b-roll, graphics, text overlays, transitions, and product shots
  • Audio direction column covering voiceover delivery notes, background music cues (genre, energy, licensing notes), sound effects, and silence beats
  • On-screen text callouts with exact copy, timing, positioning, font size guidance, and animation style
  • CTA placement map with timing rationale — why each CTA appears where it does based on viewer retention curves
  • Platform-specific formatting notes — aspect ratio, duration compliance, safe zones, caption areas, and algorithm optimization tips
  • Accessibility package — closed caption script, audio description notes, and caption styling specifications
  • Thumbnail/cover frame concept — 2 variant ideas with text overlay, imagery, color treatment, and click-through optimization rationale
  • Production notes — talent requirements, location suggestions, props and wardrobe, equipment recommendations, and lighting direction
  • Estimated production complexity rating (low/medium/high) with justification based on required assets, talent, locations, and post-production
  • Alternative cut guidance — how to create a shorter or longer version from the same shoot, specifying which sections to cut or expand

Agents Used

  • content-creator — Script writing, hook development, narrative structure, visual and audio direction, CTA placement, accessibility scripting, thumbnail concept, brand voice alignment, and platform-specific formatting

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

40.83%
按下载量换算300

Claude

29.4%
按下载量换算216

Cursor

18.11%
按下载量换算133

Gemini CLI

9.28%
按下载量换算68

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills