Agent skill · Media & Video

video-frame-extractor

视频反推工具,支持视频抽帧、视觉模型分析、提示词生成,适用于视频创作参考、内容提取、场景分析

anbeimegithub.com/anbeimeGitHub ↗
claude-codeships scripts
Install
npx skills add anbeime/skill --skill video-frame-extractor --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 5 KB
Bundled scripts: yes
Path: skills/video-frame-extractor/video-frame-extractor/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 4,714
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 视频反推工具 - 抽帧与视觉分析 ## 任务目标 - 本Skill用于: 从视频中提取关键帧,使用视觉模型分析每帧内容,生成结构化描述和提示词 - 能力包含: - 视频抽帧(支持间隔抽帧、均匀采样) - 视觉模型API调用(支持GPT-4V/Claude-3.5-Sonnet等) - 批量图片分析 - 结构化结果输出(JSON格式) - 触发条件: 用户需要分析视频内容、提取分镜参考、生成创作提示词 ## 前置准备 - 依赖说明: ``` opencv-python>=4.8.0 pillow>=10.0.0 requests>=2.28.0 ``` - 视觉模型配置: 需要配置视觉模型API密钥(如GPT-4V、Claude-3.5-Sonnet),环境变量格式: ```bash export VISION_API_KEY="your_api_key" export VISION_API_BASE="https://api.openai.com/v1" # 或其他API地址 export VISION_MODEL="gpt-4-vision-preview" # 模型名称 ``` - Coze Bot配置(推荐): 使用您发布的Coze Bot API进行视觉分析,环境变量格式: ```bash export COZE_BOT_ID="7572557757883383858" # 您的Bot ID export COZE_API_KEY="cztei_qHZQ0A5OSJjsmfZWmVb8bqu2BTbtB240YGbDYLhZpsIr8jER4aL4Aevyii8rnKfNs" # 您的API Key ``` Coze Bot的优势: 集成了官方抽帧插件和视觉模型,无需额外配置 ## 操作步骤 ### 标准流程 **步骤1: 视频抽帧** - 输入: 视频文件路径或URL - 调用脚本: `scripts/video_frame_extractor.py` - 参数: - `--input`: 视频文件路径或URL - `--output`: 输出图片目录 - `--interval`: 抽帧间隔(秒),默认1秒抽1帧 - `--max_frames`: 最大抽帧数,默认10帧 - 输出: 抽取的图片序列 ```bash # 示例: 抽取视频关键帧 python scripts/video_frame_extractor.py \ --input ./input/video.mp4 \ --output ./output/frames \ --interval 3 \ --max_frames 10 ``` **步骤2: 视觉分析** **方案A: 使用Coze Bot API(推荐)** - 输入: 抽帧图片目录 - 调用脚本: `scripts

What's inside
Steps it walks through
  1. 任务目标
  2. 前置准备
  3. 操作步骤
  4. 标准流程
  5. 可选参数
  6. 资源索引
  7. 注意事项
  8. 使用示例
  9. 示例1: 完整反推流程(使用Coze Bot)
  10. 示例2: 仅抽帧(不分析)
  11. 示例3: 单张图片分析
  12. 输出格式
  13. 技术说明
Ships with 4 files
  • references/analysis-guide.md
  • scripts/coze_bot_client.py
  • scripts/video_frame_extractor.py
  • scripts/visual_analyzer.py
Commands it runs
export VISION_API_KEY="your_api_key"
export VISION_API_BASE="https://api.openai.com/v1"  # 或其他API地址
export VISION_MODEL="gpt-4-vision-preview"  # 模型名称
export COZE_BOT_ID="7572557757883383858"  # 您的Bot ID
export COZE_API_KEY="cztei_qHZQ0A5OSJjsmfZWmVb8bqu2BTbtB240YGbDYLhZpsIr8jER4aL4Aevyii8rnKfNs"  # 您的API Key
python scripts/video_frame_extractor.py \
python scripts/coze_bot_client.py \
python scripts/visual_analyzer.py \
More from skill
All skills →
baoyu-format-markdownFormats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists…Design & Presentationbaoyu-post-to-wechatPosts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting…Backend & APIagentkit-multimedia-shopping基于ByteDance agentkit-samples多媒体用例的小省导购员数字人带货视频生成技能，整合多模态内容生成能力（图像、视频、音频），支持AI绘画、语音合成、视频生成，与小省导购员人设融合…Otherchrome-automationConnect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools…AI & Agentscontent-creation-publisher内容创作与发布全流程技能，整合网页采集、Markdown格式化、智能配图、多平台发布（微信公众号、X/Twitter）功能，实现从内容获取到发布的一站式解决方案Content & Marketingbaoyu-post-to-xPosts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles…Content & Marketing
About this skill
What does the video-frame-extractor skill do?

视频反推工具,支持视频抽帧、视觉模型分析、提示词生成,适用于视频创作参考、内容提取、场景分析

How do I install it?

Run `npx skills add anbeime/skill --skill video-frame-extractor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From anbeime/skill, a repository with 4,714 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.