Chat Screenrec Extractor
将群聊滚屏录屏视频切帧、交互式框选配置ROI、本地Apple Vision OCR识别,并通过去重算法与LLM整合输出分群Markdown聊天记录
Install
npx skills add cafe3310/public-agent-skills --skill chat-screenrec-extractorgit clone --depth 1 https://github.com/cafe3310/public-agent-skills.git /tmp/public-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/public-agent-skills/skills/chat-screenrec-extractor ~/.claude/skills/chat-screenrec-extractorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 技能:群聊录屏记录提取器 (Chat Screenrec Extractor)
## 概述
此技能用于将包含群聊滚屏录屏的一系列视频文件(.mp4 / .mov 等)转化为结构化、分群归档的 Markdown 聊天记录。支持:
1. **交互式 Web 调参与 ROI 标定**:可视化调整切帧采样周期(步长/帧率),并在大图上交互式框选「群聊标题栏」与「聊天消息正文区」ROI,一键保存配置。
2. **高精度本地 OCR**:调用 macOS 原生 Apple Vision 框架,零外部 Python 繁重依赖,快速输出文本与精确像素/归一化坐标。
3. **滚屏时序去重与聚类**:利用群聊滚屏在垂直方向移动的坐标连续性与文本相似度算法,自动剔除重叠帧中的冗余行并完成消息段聚合。
4. **分群独立成文**:根据标题栏识别自动识别群聊切换,输出包含发送人、消息内容、时间戳与系统提示的标准 Markdown 文件。
---
## 核心工作流
### 第一阶段:交互式采样调参与 ROI 框选标定 (Calibration)
1. **启动服务**:调用 `server.py`,传入包含录屏视频的目录:
```bash
python3 <path_to_skill>/scripts/server.py --input-dir /path/to/videos --port 8765
```
2. **浏览器标定**:
- 访问 `http://localhost:8765`。
- 拖动采样滑块(如 0.5s ~ 1.5s/帧),观察当前视频不同时刻的帧画面。
- 在主画布上拖拽框选:
- **Title ROI (红色框)**:锁定顶部群聊名称区域(用于自动识别群名及群切换)。
- **Body ROI (蓝色框)**:锁定消息展示区域(排除顶部状态栏与底部输入键盘)。
- 点击 **保存配置 (Save Configuration)**,参数将自动写入目标目录下的 `roi_config.json`。
### 第二阶段:批量切帧与原生 OCR 识别 (Batch OCR)
1. **执行提取与识别**:
```bash
python3 <path_to_skill>/scripts/extract_and_ocr.py --config /path/to/videos/roi_config.json
```
2. **处理逻辑与产物存放**:
- 脚本使用 `ffmpeg` 按配置周期将视频抽帧保存至 `<video_dir>/video-frames/` 目录。
- 图片命名遵循 **`原始名称-mmssSSS.jpg`**(例如 `recording-0133500.jpg`,精确到毫秒)。
- 同时调用 macOS 原生 OCR CLI 工具对每帧进行文本识别,并在 `video-frames/` 目录下生成同名的文本文件 **`原始名称-mmssSSS.txt`**,记录时间戳、Title 标题和消息区域识别行,便于人工直接快速对照复核。
- 汇总数据保存为 `.cache/ocr_results/all_frames_data.json`。
### 第三阶段:滚屏去重与消息聚合 (Dedup & Stitching)
1. **执行去重合并**:Details
- Skill name
chat-screenrec-extractor- Repository
- cafe3310/public-agent-skills
- Path
skills/chat-screenrec-extractor/SKILL.md- License
- Apache-2.0
- Repo updated
- 15 November 2026
FAQ
What does the Chat Screenrec Extractor skill do?
将群聊滚屏录屏视频切帧、交互式框选配置ROI、本地Apple Vision OCR识别,并通过去重算法与LLM整合输出分群Markdown聊天记录
How do I install the Chat Screenrec Extractor skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add cafe3310/public-agent-skills --skill chat-screenrec-extractor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Chat Screenrec Extractor popular?
It lives in cafe3310/public-agent-skills, which has 260 GitHub stars and 30 forks.
Related skills
Skill Creator
260cafe3310/public-agent-skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Impeccable
260cafe3310/public-agent-skills
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Not for backend-only or non-UI tasks.
Agent Browser
260cafe3310/public-agent-skills
为 Agent 设计的自动化浏览器 CLI 工具,也能操作 Electron 桌面应用。当需要与网站交互(包括页面导航)时使用
Open Computer Use
260cafe3310/public-agent-skills
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.
Plugin Search and Use
260cafe3310/public-agent-skills
使用的 Claude Plugin 完成特定任务,可利用如 Knowledge Work Plugins 中的专业技能
Principle Build the Lever
107Dimon94/skills
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.