[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F6PCZ7MMV59CDT2BF4SF9D":3,"skill-same:01M7F6PCZ7MMV59CDT2BF4SF9D":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M7F6PCZ7MMV59CDT2BF4SF9D","video-content-extractor",null,"Extract key frames from MP4 videos at configurable intervals, run Tesseract OCR, and generate structured Markdown reports with video metadata and timestamped text transcripts.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fvideo-content-extractor\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: video-content-extractor\ndescription: \"Extract key frames from MP4 videos at configurable intervals, run Tesseract OCR, and generate structured Markdown reports with video metadata and timestamped text transcripts.\"\ncategory: media-processing\nrisk: safe\nsource: community\nsource_repo: 274326424\u002Fvideo-content-extractor\nsource_type: community\ndate_added: \"2026-06-06\"\nauthor: 274326424\ntags: [video, ocr, ffmpeg, tesseract, frame-extraction, media]\ntools: [codex]\n---\n\n# Video Content Extractor\n\n## Overview\n\nAutomatically extracts key frames from MP4 video files at configurable time intervals, performs OCR text recognition on each frame, and generates a structured Markdown report. The report includes video metadata (duration, resolution, codecs) and frame-by-frame OCR transcripts with timestamp references.\n\nThis skill is designed for Codex CLI and requires FFmpeg and Tesseract OCR installed on the local machine.\n\n## When to Use This Skill\n\n- Use when you need to extract text content from video presentations, lectures, or screencasts.\n- Use when you want to create searchable transcripts from video files without embedded subtitles.\n- Use when you need to analyze video content programmatically and generate structured summaries.\n- Use when the user asks to \"read what is on screen\" or \"extract the content from this video.\"\n\n## How It Works\n\n### Step 1: Analyze Video Metadata\n\nThe skill uses ffprobe to extract video metadata: duration, resolution, frame rate, codec information, and file size.\n\n### Step 2: Extract Key Frames\n\nUsing FFmpeg, the skill captures frames at the configured interval (default: every 30 seconds). Each frame is saved as a timestamped JPEG image.\n\n### Step 3: OCR Text Recognition\n\nEach extracted frame is processed by Tesseract OCR. If the default PSM mode returns no meaningful text, it falls back to fully automatic page segmentation.\n\n### Step 4: Generate Markdown Report\n\nAll extracted data is assembled into a structured Markdown document.\n\n## Examples\n\n### Example 1: Basic Extraction\n\nAgent prompt:\nUse the video-content-extractor skill to extract content from lecture.mp4\n\nOutput generates lecture.md and lecture_frames\u002F directory.\n\n### Example 2: Custom Interval\n\nParameters: video_path, output_dir, interval(seconds), lang\nExtract every 60 seconds with English-only OCR:\npython scripts\u002Fextract_video.py recording.mp4 .\u002Foutput 60 eng\n\n### Example 3: Bilingual Content\n\nExtract with default Chinese + English OCR:\npython scripts\u002Fextract_video.py lecture.mp4 . 15 chi_sim+eng\n\n## Best Practices\n\n- Use shorter intervals (10-15s) for fast-paced content with frequent text changes.\n- Use longer intervals (30-60s) for presentation slides or slow lectures to reduce duplicate frames.\n- For Chinese content, ensure Tesseract Chinese language pack is installed (chi_sim).\n\n## Limitations\n\n- Requires FFmpeg and Tesseract OCR to be installed and accessible via PATH.\n- Tesseract OCR accuracy depends on video quality, text size, and font clarity.\n- Does not extract audio or perform speech-to-text transcription.\n- Frame extraction is time-based (not scene-change-based), which may produce near-duplicate frames.\n- Large videos with short intervals can generate many frames - ensure sufficient disk space.\n\n## Security and Safety Notes\n\n- This skill only reads video files and writes extracted frames and Markdown reports.\n- It does NOT send any data over the network - all processing is local.\n- FFmpeg and Tesseract are invoked with fixed, pre-vetted arguments.\n- The skill does not modify or delete the original video file.\n\n## Common Pitfalls\n\n- Problem: Tesseract returns garbled text\n  Solution: Ensure the correct language pack is installed. Run tesseract --list-langs to verify.\n\n- Problem: FFmpeg fails with \"not found\"\n  Solution: Make sure FFmpeg is on PATH. Run ffmpeg -version to verify.\n\n- Problem: OCR is slow on large videos\n  Solution: Increase the interval parameter to reduce frames processed.\n\n## Related Skills\n\n- @media-summarizer - For summarizing video content using visual and audio cues.\n- @document-ocr - For OCR on static images or scanned documents without video processing.\n","# Video Content Extractor\n\n## Overview\n\nAutomatically extracts key frames from MP4 video files at configurable time intervals, performs OCR text recognition on each frame, and generates a structured Markdown report. The report includes video metadata (duration, resolution, codecs) and frame-by-frame OCR transcripts with timestamp references.\n\nThis skill is designed for Codex CLI and requires FFmpeg and Tesseract OCR installed on the local machine.\n\n## When to Use This Skill\n\n- Use when you need to extract text content from video presentations, lectures, or screencasts.\n- Use when you want to create searchable transcripts from video files without embedded subtitles.\n- Use when you need to analyze video content programmatically and generate structured summaries.\n- Use when the user asks to \"read what is on screen\" or \"extract the content from this video.\"\n\n## How It Works\n\n### Step 1: Analyze Video Metadata\n\nThe skill uses ffprobe to extract video metadata: duration, resolution, frame rate, codec information, and file size.\n\n### Step 2: Extract Key Frames\n\nUsing FFmpeg, the skill captures frames at the configured interval (default: every 30 seconds). Each frame is saved as a timestamped JPEG image.\n\n### Step 3: OCR Text Recognition\n\nEach extracted frame is processed by Tesseract OCR. If the default PSM mode returns no meaningful text, it falls back to fully automatic page segmentation.\n\n### Step 4: Generate Markdown Report\n\nAll extracted data is assembled into a structured Markdown document.\n\n## Examples\n\n### Example 1: Basic Extraction\n\nAgent prompt:\nUse the video-content-extractor skill to extract content from lecture.mp4\n\nOutput generates lecture.md and lecture_frames\u002F directory.\n\n### Example 2: Custom Interval\n\nParameters: video_path, output_dir, interval(seconds), lang\nExtract every 60 seconds with English-only OCR:\npython scripts\u002Fextract_video.py recording.mp4 .\u002Foutput 60 eng\n\n### Example 3: Bilingual Content\n\nExtract with default Chinese + English OCR:\npython scripts\u002Fextract_video.py lecture.mp4 . 15 chi_sim+eng\n\n## Best Practices\n\n- Use shorter intervals (10-15s) for fast-paced content with frequent text changes.\n- Use longer intervals (30-60s) for presentation slides or slow lectures to reduce duplicate frames.\n- For Chinese content, ensure Tesseract Chinese language pack is installed (chi_sim).\n\n## Limitations\n\n- Requires FFmpeg and Tesseract OCR to be installed and accessible via PATH.\n- Tesseract OCR accuracy depends on video quality, text size, and font clarity.\n- Does not extract audio or perform speech-to-text transcription.\n- Frame extraction is time-based (not scene-change-based), which may produce near-duplicate frames.\n- Large videos with short intervals can generate many frames - ensure sufficient disk space.\n\n## Security and Safety Notes\n\n- This skill only reads video files and writes extracted frames and Markdown reports.\n- It does NOT send any data over the network - all processing is local.\n- FFmpeg and Tesseract are invoked with fixed, pre-vetted arguments.\n- The skill does not modify or delete the original video file.\n\n## Common Pitfalls\n\n- Problem: Tesseract returns garbled text\n  Solution: Ensure the correct language pack is installed. Run tesseract --list-langs to verify.\n\n- Problem: FFmpeg fails with \"not found\"\n  Solution: Make sure FFmpeg is on PATH. Run ffmpeg -version to verify.\n\n- Problem: OCR is slow on large videos\n  Solution: Increase the interval parameter to reduce frames processed.\n\n## Related Skills\n\n- @media-summarizer - For summarizing video content using visual and audio cues.\n- @document-ocr - For OCR on static images or scanned documents without video processing.\n",{"name":5,"risk":24,"tags":25,"tools":32,"author":34,"source":35,"category":36,"date_added":37,"description":7,"source_repo":38,"source_type":35},"safe",[26,27,28,29,30,31],"video","ocr","ffmpeg","tesseract","frame-extraction","media",[33],"codex",274326424,"community","media-processing","2026-06-06","274326424\u002Fvideo-content-extractor","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fvideo-content-extractor",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content-extractor",{"tool":53,"command":54},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content-extractor",{"tool":56,"command":57},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fvideo-content-extractor\u002FSKILL.md",true,[],[62,69,74,81,88,95],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":70,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]