[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KJVC9M3VJHGAHTYRACCVPS":3,"skill-same:01M6KJVC9M3VJHGAHTYRACCVPS":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6KJVC9M3VJHGAHTYRACCVPS","video-to-grayscale-frames",null,"Extract keyframes from MP4 video files and convert them to grayscale. Use this skill when you need to process video files for analysis by extracting I-frames (keyframes) and converting them to grayscale images for computer vision tasks.","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",92,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb4-skill-creator-claude-haiku-4-5\u002Fvideo-object-counting\u002Fvideo-to-grayscale-frames\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"video to grayscale frames","Video","use","for","you","extracting","keyframes","files","images","vision","tasks","process","extract","computer","mp4","convert","analysis","Computer Vision","2026-11-10 10:12:30",false,"---\nname: video-to-grayscale-frames\ndescription: Extract keyframes from MP4 video files and convert them to grayscale. Use this skill when you need to process video files for analysis by extracting I-frames (keyframes) and converting them to grayscale images for computer vision tasks.\n---\n\n# Video to Grayscale Frames\n\nThis skill guides you through extracting keyframes from MP4 video files and converting them to grayscale images for analysis.\n\n## Overview\n\nThe workflow has two main steps:\n1. **Extract keyframes** from the MP4 video using FFmpeg\n2. **Convert to grayscale** and save frames as PNG files\n\n## Step 1: Extract Keyframes from MP4\n\nUse the `ffmpeg` skill to extract I-frames (keyframes) from the video.\n\n### Command Structure\n```bash\nffmpeg -i \u003Cinput.mp4> -vf \"select=eq(pict_type\\,I)\" -vsync vfr \u003Coutput_pattern>\n```\n\n### Parameters\n- `input.mp4`: Path to your video file\n- `output_pattern`: Output file pattern (e.g., `\u002Froot\u002Fkeyframes_%03d.png`)\n  - `%03d` creates zero-padded numbers: keyframes_001.png, keyframes_002.png, etc.\n\n### Example\nFor a video at `\u002Froot\u002Fsuper-mario.mp4`, extracting to `\u002Froot\u002Fkeyframes_%03d.png`:\n```bash\nffmpeg -i \u002Froot\u002Fsuper-mario.mp4 -vf \"select=eq(pict_type\\,I)\" -vsync vfr \u002Froot\u002Fkeyframes_%03d.png\n```\n\nThis creates: keyframes_001.png, keyframes_002.png, keyframes_003.png, etc.\n\n## Step 2: Convert Extracted Frames to Grayscale\n\nUse the `image_editing` skill to convert each extracted keyframe to grayscale IN-PLACE (overwriting the original RGB image).\n\n### Conversion Process\nFor each keyframe image:\n- Input: `\u002Froot\u002Fkeyframes_001.png` (RGB)\n- Operation: Convert to grayscale\n- Output: `\u002Froot\u002Fkeyframes_001.png` (grayscale, overwrites original)\n\n### Batch Processing\nWhen converting multiple frames, process them sequentially or in parallel depending on available resources. Ensure each frame is converted and saved before proceeding to analysis.\n\n## Output Format\n\nAfter this skill completes:\n- Keyframes are stored as `\u002Froot\u002Fkeyframes_001.png`, `\u002Froot\u002Fkeyframes_002.png`, etc.\n- All files are in grayscale format\n- Files are ready for object detection and counting\n\n## Common Issues\n\n- **FFmpeg not installed**: The ffmpeg skill should handle installation\n- **No keyframes extracted**: Video may have no I-frames; consider extracting all frames with `-fps 1` instead\n- **Image format errors**: Ensure images are valid PNG files before grayscale conversion\n","# Video to Grayscale Frames\n\nThis skill guides you through extracting keyframes from MP4 video files and converting them to grayscale images for analysis.\n\n## Overview\n\nThe workflow has two main steps:\n1. **Extract keyframes** from the MP4 video using FFmpeg\n2. **Convert to grayscale** and save frames as PNG files\n\n## Step 1: Extract Keyframes from MP4\n\nUse the `ffmpeg` skill to extract I-frames (keyframes) from the video.\n\n### Command Structure\n```bash\nffmpeg -i \u003Cinput.mp4> -vf \"select=eq(pict_type\\,I)\" -vsync vfr \u003Coutput_pattern>\n```\n\n### Parameters\n- `input.mp4`: Path to your video file\n- `output_pattern`: Output file pattern (e.g., `\u002Froot\u002Fkeyframes_%03d.png`)\n  - `%03d` creates zero-padded numbers: keyframes_001.png, keyframes_002.png, etc.\n\n### Example\nFor a video at `\u002Froot\u002Fsuper-mario.mp4`, extracting to `\u002Froot\u002Fkeyframes_%03d.png`:\n```bash\nffmpeg -i \u002Froot\u002Fsuper-mario.mp4 -vf \"select=eq(pict_type\\,I)\" -vsync vfr \u002Froot\u002Fkeyframes_%03d.png\n```\n\nThis creates: keyframes_001.png, keyframes_002.png, keyframes_003.png, etc.\n\n## Step 2: Convert Extracted Frames to Grayscale\n\nUse the `image_editing` skill to convert each extracted keyframe to grayscale IN-PLACE (overwriting the original RGB image).\n\n### Conversion Process\nFor each keyframe image:\n- Input: `\u002Froot\u002Fkeyframes_001.png` (RGB)\n- Operation: Convert to grayscale\n- Output: `\u002Froot\u002Fkeyframes_001.png` (grayscale, overwrites original)\n\n### Batch Processing\nWhen converting multiple frames, process them sequentially or in parallel depending on available resources. Ensure each frame is converted and saved before proceeding to analysis.\n\n## Output Format\n\nAfter this skill completes:\n- Keyframes are stored as `\u002Froot\u002Fkeyframes_001.png`, `\u002Froot\u002Fkeyframes_002.png`, etc.\n- All files are in grayscale format\n- Files are ready for object detection and counting\n\n## Common Issues\n\n- **FFmpeg not installed**: The ffmpeg skill should handle installation\n- **No keyframes extracted**: Video may have no I-frames; consider extracting all frames with `-fps 1` instead\n- **Image format errors**: Ensure images are valid PNG files before grayscale conversion\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb4-skill-creator-claude-haiku-4-5\u002Fvideo-object-counting\u002Fvideo-to-grayscale-frames",7,"https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench","https:\u002F\u002Fcxcscmu.github.io\u002FSkillLearnBench","https:\u002F\u002Fgithub.com\u002Fcxcscmu","2026-10-02 22:55:36",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill video-to-grayscale-frames",{"tool":60,"command":61},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill video-to-grayscale-frames",{"tool":63,"command":64},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill video-to-grayscale-frames","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb4-skill-creator-claude-haiku-4-5\u002Fvideo-object-counting\u002Fvideo-to-grayscale-frames\u002FSKILL.md",true,[],[69,80,104,121,140,152],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":76,"publishedAt":41},"01M6KM5KH175P5ABP5JMX2SBDQ","object_counter","Count occurrences of an object in the image using computer vision algorithm.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Fvideo-object-counting\u002Fobject_counter\u002FSKILL.md",[75],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[77,78,32,36,40,79],"object counter","object","image",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":89,"publishedAt":41},"01M6KM51TMVXG79MMPCS6Y8G86","travel-planning-workflow","Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Ftravel-planning-workflow\u002FSKILL.md",[86],{"categoryNo":87,"categoryName":88,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[90,91,92,93,94,95,96,97,98,26,99,100,101,102,103],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","user","it","requirements","essential","itineraries",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":41},"01M6KM4DY820XHS9YTSK5QP5HD","bundled-dataset-search-tool","invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Fbundled-dataset-search-tool\u002FSKILL.md",[],[111,112,113,114,115,116,117,93,118,119,94,27,26,120,91],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","up","look","flights","database",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":41},"01M6KM465BB9PQ0B548HQSVAWZ","glm-output","Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final \u002Froot\u002Fmetrics.json.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-output\u002FSKILL.md",[],[128,129,130,26,33,131,132,133,134,135,136,137,27,138,139],"glm output","output","glm","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":41},"01M6KM40KY3QWDW5W97S39R2BC","glm-calibration","Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-calibration\u002FSKILL.md",[146],{"categoryNo":87,"categoryName":88,"taxonomyType":20,"taxonomyTypeDesc":21},[148,139,130,129,134,133,33,149,150,26,151],"glm calibration","setup","companion","metric",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":41},"01M6KM3VHHVSGMGHJQB3PPT6YG","glm-basics","A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-basics\u002FSKILL.md",[],[159,130,133,160,148,139,26,129,161,30,162,25,163,164,33],"glm basics","inspect","relevant","good","how","Evaluation"]