[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDXB44W5KWYBAYTC3N7HH9":3,"skill-same:01M6XDXB44W5KWYBAYTC3N7HH9":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":13,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6XDXB44W5KWYBAYTC3N7HH9","filler-word-processing",null,"Process filler word annotations to generate video edit lists. Use when working with timestamp annotations for removing speech disfluencies (um, uh, like, you know) from audio\u002Fvideo content.","Waaaalnut\u002Fskillsbench","Waaaalnut","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103995656?v=4","01M6XCS9K1V51EY3JMB7DGMX24","01M6XCS9Q4WPW88W62C55G1H44",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks-no-skills\u002Fvideo-filler-word-remover\u002Fenvironment\u002Fskills\u002Ffiller-word-processing\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"filler word processing","Word","processing","process","when","video edit","for","you","with","video content","use","generate video","edit","timestamp","annotations","Audio","Video","content","speech","generate","2026-11-10 10:12:30",false,"---\nname: filler-word-processing\ndescription: \"Process filler word annotations to generate video edit lists. Use when working with timestamp annotations for removing speech disfluencies (um, uh, like, you know) from audio\u002Fvideo content.\"\n---\n\n# Filler Word Processing\n\n## Annotation Format\n\nTypical annotation JSON structure:\n```json\n[\n  {\"word\": \"um\", \"timestamp\": 12.5},\n  {\"word\": \"like\", \"timestamp\": 25.3},\n  {\"word\": \"you know\", \"timestamp\": 45.8}\n]\n```\n\n## Converting Annotations to Cut Segments\n\nEach filler word annotation marks when the word starts. To remove it, use word-specific durations since different fillers have different lengths:\n\n```python\nimport json\n\n# Word-specific durations (in seconds)\nWORD_DURATIONS = {\n    \"uh\": 0.3,\n    \"um\": 0.4,\n    \"hum\": 0.6,\n    \"hmm\": 0.6,\n    \"mhm\": 0.55,\n    \"like\": 0.3,\n    \"yeah\": 0.35,\n    \"so\": 0.25,\n    \"well\": 0.35,\n    \"okay\": 0.4,\n    \"basically\": 0.55,\n    \"you know\": 0.55,\n    \"i mean\": 0.5,\n    \"kind of\": 0.5,\n    \"i guess\": 0.5,\n}\nDEFAULT_DURATION = 0.4\n\ndef annotations_to_segments(annotations_file, buffer=0.05):\n    \"\"\"\n    Convert filler word annotations to (start, end) cut segments.\n\n    Args:\n        annotations_file: Path to JSON annotations\n        buffer: Small buffer before the word (seconds)\n\n    Returns:\n        List of (start, end) tuples representing segments to remove\n    \"\"\"\n    with open(annotations_file) as f:\n        annotations = json.load(f)\n\n    segments = []\n    for ann in annotations:\n        word = ann.get('word', '').lower().strip()\n        timestamp = ann['timestamp']\n        # Use word-specific duration, fall back to default\n        word_duration = WORD_DURATIONS.get(word, DEFAULT_DURATION)\n        # Cut starts slightly before the word\n        start = max(0, timestamp - buffer)\n        # Cut ends after word duration\n        end = timestamp + word_duration\n        segments.append((start, end))\n\n    return segments\n```\n\n## Merging Overlapping Segments\n\nWhen filler words are close together, merge their cut segments:\n\n```python\ndef merge_overlapping_segments(segments, min_gap=0.1):\n    \"\"\"\n    Merge segments that overlap or are very close together.\n\n    Args:\n        segments: List of (start, end) tuples\n        min_gap: Minimum gap to keep segments separate\n\n    Returns:\n        Merged list of segments\n    \"\"\"\n    if not segments:\n        return []\n\n    # Sort by start time\n    sorted_segs = sorted(segments)\n    merged = [sorted_segs[0]]\n\n    for start, end in sorted_segs[1:]:\n        prev_start, prev_end = merged[-1]\n\n        # If this segment overlaps or is very close to previous\n        if start \u003C= prev_end + min_gap:\n            # Extend the previous segment\n            merged[-1] = (prev_start, max(prev_end, end))\n        else:\n            merged.append((start, end))\n\n    return merged\n```\n\n## Complete Processing Pipeline\n\n```python\ndef process_filler_annotations(annotations_file, word_duration=0.4):\n    \"\"\"Full pipeline: load annotations -> create segments -> merge overlaps\"\"\"\n\n    # Load and create initial segments\n    segments = annotations_to_segments(annotations_file, word_duration)\n\n    # Merge overlapping cuts\n    merged = merge_overlapping_segments(segments)\n\n    return merged\n```\n\n## Tuning Parameters\n\n| Parameter | Typical Value | Notes |\n|-----------|---------------|-------|\n| word_duration | varies | Short fillers (um, uh) ~0.25-0.3s, single words (like, yeah) ~0.3-0.4s, phrases (you know, i mean) ~0.5-0.6s |\n| buffer | 0.05s | Small buffer captures word onset |\n| min_gap | 0.1s | Prevents micro-segments between close fillers |\n\n### Word Duration Guidelines\n\n| Category | Words | Duration |\n|----------|-------|----------|\n| Quick hesitations | uh, um | 0.3-0.4s |\n| Sustained hums (drawn out while thinking) | hum, hmm, mhm | 0.55-0.6s |\n| Quick single words | like, yeah, so, well | 0.25-0.35s |\n| Longer single words | okay, basically | 0.4-0.55s |\n| Multi-word phrases | you know, i mean, kind of, i guess | 0.5-0.55s |\n\n## Quality Considerations\n\n- **Too aggressive**: Cuts into adjacent words, sounds choppy\n- **Too conservative**: Filler words partially audible\n- **Sweet spot**: Clean cuts with natural-sounding result\n\nTest with a few samples before processing full video.\n","# Filler Word Processing\n\n## Annotation Format\n\nTypical annotation JSON structure:\n```json\n[\n  {\"word\": \"um\", \"timestamp\": 12.5},\n  {\"word\": \"like\", \"timestamp\": 25.3},\n  {\"word\": \"you know\", \"timestamp\": 45.8}\n]\n```\n\n## Converting Annotations to Cut Segments\n\nEach filler word annotation marks when the word starts. To remove it, use word-specific durations since different fillers have different lengths:\n\n```python\nimport json\n\n# Word-specific durations (in seconds)\nWORD_DURATIONS = {\n    \"uh\": 0.3,\n    \"um\": 0.4,\n    \"hum\": 0.6,\n    \"hmm\": 0.6,\n    \"mhm\": 0.55,\n    \"like\": 0.3,\n    \"yeah\": 0.35,\n    \"so\": 0.25,\n    \"well\": 0.35,\n    \"okay\": 0.4,\n    \"basically\": 0.55,\n    \"you know\": 0.55,\n    \"i mean\": 0.5,\n    \"kind of\": 0.5,\n    \"i guess\": 0.5,\n}\nDEFAULT_DURATION = 0.4\n\ndef annotations_to_segments(annotations_file, buffer=0.05):\n    \"\"\"\n    Convert filler word annotations to (start, end) cut segments.\n\n    Args:\n        annotations_file: Path to JSON annotations\n        buffer: Small buffer before the word (seconds)\n\n    Returns:\n        List of (start, end) tuples representing segments to remove\n    \"\"\"\n    with open(annotations_file) as f:\n        annotations = json.load(f)\n\n    segments = []\n    for ann in annotations:\n        word = ann.get('word', '').lower().strip()\n        timestamp = ann['timestamp']\n        # Use word-specific duration, fall back to default\n        word_duration = WORD_DURATIONS.get(word, DEFAULT_DURATION)\n        # Cut starts slightly before the word\n        start = max(0, timestamp - buffer)\n        # Cut ends after word duration\n        end = timestamp + word_duration\n        segments.append((start, end))\n\n    return segments\n```\n\n## Merging Overlapping Segments\n\nWhen filler words are close together, merge their cut segments:\n\n```python\ndef merge_overlapping_segments(segments, min_gap=0.1):\n    \"\"\"\n    Merge segments that overlap or are very close together.\n\n    Args:\n        segments: List of (start, end) tuples\n        min_gap: Minimum gap to keep segments separate\n\n    Returns:\n        Merged list of segments\n    \"\"\"\n    if not segments:\n        return []\n\n    # Sort by start time\n    sorted_segs = sorted(segments)\n    merged = [sorted_segs[0]]\n\n    for start, end in sorted_segs[1:]:\n        prev_start, prev_end = merged[-1]\n\n        # If this segment overlaps or is very close to previous\n        if start \u003C= prev_end + min_gap:\n            # Extend the previous segment\n            merged[-1] = (prev_start, max(prev_end, end))\n        else:\n            merged.append((start, end))\n\n    return merged\n```\n\n## Complete Processing Pipeline\n\n```python\ndef process_filler_annotations(annotations_file, word_duration=0.4):\n    \"\"\"Full pipeline: load annotations -> create segments -> merge overlaps\"\"\"\n\n    # Load and create initial segments\n    segments = annotations_to_segments(annotations_file, word_duration)\n\n    # Merge overlapping cuts\n    merged = merge_overlapping_segments(segments)\n\n    return merged\n```\n\n## Tuning Parameters\n\n| Parameter | Typical Value | Notes |\n|-----------|---------------|-------|\n| word_duration | varies | Short fillers (um, uh) ~0.25-0.3s, single words (like, yeah) ~0.3-0.4s, phrases (you know, i mean) ~0.5-0.6s |\n| buffer | 0.05s | Small buffer captures word onset |\n| min_gap | 0.1s | Prevents micro-segments between close fillers |\n\n### Word Duration Guidelines\n\n| Category | Words | Duration |\n|----------|-------|----------|\n| Quick hesitations | uh, um | 0.3-0.4s |\n| Sustained hums (drawn out while thinking) | hum, hmm, mhm | 0.55-0.6s |\n| Quick single words | like, yeah, so, well | 0.25-0.35s |\n| Longer single words | okay, basically | 0.4-0.55s |\n| Multi-word phrases | you know, i mean, kind of, i guess | 0.5-0.55s |\n\n## Quality Considerations\n\n- **Too aggressive**: Cuts into adjacent words, sounds choppy\n- **Too conservative**: Filler words partially audible\n- **Sweet spot**: Clean cuts with natural-sounding result\n\nTest with a few samples before processing full video.\n",{"name":5,"description":7},"main","7eeb258ada72b7f58119b0e7a2c00ea89d9beedd","tasks-no-skills\u002Fvideo-filler-word-remover\u002Fenvironment\u002Fskills\u002Ffiller-word-processing","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench","https:\u002F\u002Fgithub.com\u002FWaaaalnut","student of Zhejiang University","2026-04-21 23:16:23",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Waaaalnut\u002Fskillsbench --skill filler-word-processing",{"tool":64,"command":65},"bunx","bunx skills add Waaaalnut\u002Fskillsbench --skill filler-word-processing",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Waaaalnut\u002Fskillsbench --skill filler-word-processing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks-no-skills\u002Fvideo-filler-word-remover\u002Fenvironment\u002Fskills\u002Ffiller-word-processing\u002FSKILL.md",true,[],[73,87,100,120,141,158],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":83,"publishedAt":46},"01M6XEWMJ6VY3ZC53MPDCPG3GH","data-reconciliation","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fxlsx-recover-data\u002Fenvironment\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[84,85,86],"data reconciliation","reconciliation","data",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":46},"01M6XEW8MNPMF1KRXV6ATGFRQF","speech-to-text","Transcribe video to timestamped text using Whisper tiny model (pre-installed).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-tutorial-indexer\u002Fenvironment\u002Fskills\u002Fspeech-to-text\u002FSKILL.md",[],[44,94,95,96,97,98,42,99],"text","speech to text","transcribe video","whisper","model","transcribe",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":46},"01M6XEW3FQZP0T1RKQQJFXVY9T","video-processor","Process videos by removing segments and concatenating remaining parts. Use when you need to remove detected pauses\u002Fopenings from videos, create highlight reels, or batch process segment removals using ffmpeg filter_complex.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fvideo-processor\u002FSKILL.md",[106],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[42,108,109,110,111,112,30,113,114,29,115,33,116,117,118,36,119],"processor","video processor","batch","create","reels","parts","segments","videos","segment","filter","ffmpeg","remove",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":127,"publishedAt":46},"01M6XEVXJ5KZ0NTY3XZKRY4AS1","silence-detector","Detect initial silence segments in audio\u002Fvideo using energy-based analysis. Use when you need to find low-energy periods at the start of recordings (title slides, setup time, pre-roll silence).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsilence-detector\u002FSKILL.md",[126],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[128,129,130,131,30,33,132,133,134,135,136,114,137,41,42,138,139,140,36],"detector","silence detector","title","slides","time","energy","at","recordings","detect","find","analysis","start","setup",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":46},"01M6XEVT3NGRN1FT7JPMAPXS6M","segment-combiner","Combine multiple segment detection results into a unified list. Use when you need to merge segments from different detectors, prepare removal lists for video processing, or consolidate detection outputs.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",[],[116,148,42,149,150,151,152,32,30,153,154,114,33,28,155,36,156,157],"segment combiner","detection","prepare","merge","video processing","outputs","combine","consolidate","results","list",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":167,"publishedAt":46},"01M6XEVMPVASGS2KX86QK4FMT7","report-generator","Generate compression reports for video processing. Use when you need to create structured JSON reports with duration statistics, compression ratios, and segment details after video processing.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Freport-generator\u002FSKILL.md",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000034","行政与办公人员",[168,169,170,116,30,32,33,34,28,171,172,173,36,152,174,42,175,45,111],"generator","report generator","report","statistics","structured","reports","json","compression"]