Communityビデオ＆アニメーションgithub.com

mason0510/video-frame-analysis-skills

Installable Codex skill repo for local video frame analysis with ffprobe, timestamped frames, contact sheet, OCR, and summary output.

対応✓Claude Code✓Codex CLI~Cursor✓OpenCode
npx skills add mason0510/video-frame-analysis-skills
オリジナルを見る→すべてのスキルを見る

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

ドキュメント

video-frame-analysis

Overview

把“本地视频 → ffprobe → 带时间戳抽帧 → contact sheet → OCR → summary.txt / ocr.json 落盘”固化成一个可复用的轻量 skill。

适合给 Codex、Claude Code、OpenCode 这类 agent 处理本地 demo 视频、录屏、竞品页面 walkthrough。

When to Use

适用于：

  • 用户丢来一个本地视频，让你判断产品做到哪一步
  • 需要把视频拆成可复查的帧图、OCR 文本、摘要文件
  • 需要先做轻量证据提取，再做人工判断或进一步分析
  • 想避免每次手拼 ffmpeg / tesseract 命令

不适用于：

  • 网络视频下载
  • 批量视频队列
  • 实时流分析
  • GUI 或 Web 平台
  • 重型视频理解模型

Quick Start

bash scripts/video-frame-analysis.sh /path/to/demo.mp4 ./out/demo-analysis

默认输出：

  • ffprobe.txt
  • frame_*.jpg
  • contact.png
  • ocr.txt
  • ocr.json
  • summary.txt

Installation

推荐直接安装到 Codex / Claude Code / OpenCode：

npx skills add https://github.com/mason0510/video-frame-analysis-skills -g --all

安装后重启 agent 会话，再按需触发本 skill。

Input / Output

输入

  • 本地视频路径
  • 输出目录路径

输出

  • 视频元信息
  • 带时间戳帧图
  • contact sheet
  • OCR 文本
  • OCR JSON
  • 摘要文本

Config

FRAME_INTERVAL_SECONDS=5 FRAME_WIDTH=420 OCR_LANG=eng \
  bash scripts/video-frame-analysis.sh ./demo.mp4 ./out/demo
变量说明默认值
FRAME_INTERVAL_SECONDS抽帧时间间隔（秒）8
FRAME_WIDTH单帧宽度360
OCR_LANGOCR 语言候选chi_sim+eng

Project Files

  • scripts/video-frame-analysis.sh：主脚本
  • tests/test_video_frame_analysis.sh：最小闭环测试
  • references/output-format.md：输出目录说明
  • agents/openai.yaml：OpenAI/Codex 侧显示信息

Common Mistakes

  • 把它当成重型视频理解模型
  • 抽帧过密导致 OCR 噪声暴涨
  • 忽略 contact sheet，只盯 OCR 文本
  • 没检查本机是否装了 ffmpeg / tesseract

関連スキル

coreyhaines31/social

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' 'grow my following,' 'TikTok video,' 'Reels,' 'Shorts,' 'video script,' 'video hook,' 'short-form video,' or 'create a reel.' Use this for social media content creation, repurposing, scheduling, and short-form video scripting. For broader content strategy, see content-strategy. For paid video ads, see ad-creative.

community

forcedotcom/building-ui-bundle-frontend

MUST activate before editing ANY file under uiBundles/*/src/ for visual or UI changes to an EXISTING app — pages, components, sections, layout, styling, colors, fonts, navigation, animations, or any look-and-feel change. Use this skill when modifying pages, components, layout, styling, or navigation in an existing UI bundle app. Activate when the project contains appLayout.tsx, routes.tsx, src/pages/, src/components/, or global.css. This skill contains critical project-specific conventions (appLayout.tsx shell, shadcn/ui components, Tailwind CSS, Salesforce base-path routing, module restrictions) that override general knowledge. Without this skill, generated code will use wrong imports, break routing, or ignore project structure. Do NOT use when creating a new app from scratch (use building-ui-bundle-app instead).

community

remotion-dev/remotion-best-practices

Best practices for Remotion - Video creation in React

community

agentspace-so/seedance-v2

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance pro", "bytedance video", or any explicit ask to generate video with this model.

community

sergeyramas/3d-website-builder-skill

Claude Code skill: ready MP4 → vanilla HTML/CSS/JS scroll-driven hero (GSAP video.currentTime, no FFmpeg)

community

jimmylv/bibi

AI video & audio summarizer + repackager. Summarize YouTube, Bilibili, podcasts, TikTok, Twitter/X, Xiaohongshu, and any online video or audio, then optionally turn the takeaway into a TikTok-style vertical music video. Use when the user wants to summarize a video, extract transcripts/subtitles, get chapter-by-chapter summaries, understand video content quickly, or remix a long-form video into a short vertical MV. Triggers: "summarize this video", "what's this video about", "extract subtitles", "总结这个视频", "帮我看看这个视频讲了什么", "video summary", "podcast notes", "YouTube summary", "B站总结", "get transcript", "video to notes", "video to TikTok MV", "把视频变成 TikTok", "video to song", "做一个 TikTok 视频". Works via bibi CLI (macOS/Windows) or OpenAPI (Linux / any platform without CLI).

community
← More ビデオ＆アニメーション skills