[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BSCCP20MX5AWB2S4XT63C4":3,"skill-same:01M7BSCCP20MX5AWB2S4XT63C4":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BSCCP20MX5AWB2S4XT63C4","pause-detector",null,"Detect pauses and silence in audio using local dynamic thresholds. Use when you need to find natural pauses in lectures, board-writing silences, or breaks between sections. Uses local context comparison to propose pause candidates for review.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FHumanAnnotated-CrossModel-10Tasks-20261008\u002Fgemini31\u002Ftasks\u002Fvideo-silence-remover\u002Frepaired_skill\u002Fpause-detector\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pause-detector\ndescription: Detect pauses and silence in audio using local dynamic thresholds. Use when you need to find natural pauses in lectures, board-writing silences, or breaks between sections. Uses local context comparison to propose pause candidates for review.\n---\n\n# Pause Detector\n\nDetects pauses and low-energy segments using local dynamic thresholds on pre-computed energy data. This compares energy to surrounding context. Low energy relative to nearby speech proposes a pause candidate; it does not by itself establish silence.\n\n## Use Cases\n\n- Detecting natural pauses in lectures\n- Finding board-writing silences\n- Identifying breaks between sections\n\n## Usage\n\n```bash\npython3 \u002Froot\u002F.claude\u002Fskills\u002Fpause-detector\u002Fscripts\u002Fdetect_pauses.py \\\n    --energies \u002Fpath\u002Fto\u002Fenergies.json \\\n    --audio \u002Fpath\u002Fto\u002Faudio.wav \\\n    --output \u002Fpath\u002Fto\u002Fpauses.json\n```\n\n### Parameters\n\n- `--energies`: Path to energy JSON file (from energy-calculator)\n- `--audio`: Extracted 16-bit mono PCM WAV from the same recording (required)\n- `--output`: Path to output JSON file\n- `--start-time`: Start analyzing from this second (default: 0)\n- `--threshold-ratio`: Ratio of local average for low energy (default: 0.5)\n- `--min-duration`: Minimum pause duration in seconds, inclusive (default: 2)\n- `--window-size`: Local average window size (default: 30)\n\n### Output Format\n\n```json\n{\n  \"method\": \"local_dynamic_threshold_with_audio_audit\",\n  \"segments\": [\n    {\"start\": 610, \"end\": 613, \"duration\": 3},\n    {\"start\": 720, \"end\": 724, \"duration\": 4}\n  ],\n  \"total_segments\": 2,\n  \"total_duration_seconds\": 7,\n  \"parameters\": {\n    \"threshold_ratio\": 0.5,\n    \"window_size\": 30,\n    \"min_duration\": 2\n  }\n}\n```\n\n## How It Works\n\n1. Load pre-computed energy data\n2. Calculate local average using sliding window\n3. Mark seconds where energy \u003C local_avg × threshold_ratio\n4. Group consecutive low-energy seconds into segments\n5. Filter segments by minimum duration\n6. Audit each candidate against 20 ms RMS frames from the original audio; require at least two-thirds of its frames in the recording-derived quiet class. Save the cutoff and every accepted\u002Frejected candidate in audio_audit.\n\n## Dependencies\n\n- Python 3.11+\n- numpy\n- scipy\n\n## Example\n\n```bash\n# Set OPENING_END from the opening detector result, then detect long pauses\npython3 \u002Froot\u002F.claude\u002Fskills\u002Fpause-detector\u002Fscripts\u002Fdetect_pauses.py \\\n    --energies energies.json \\\n    --audio audio.wav \\\n    --start-time \"$OPENING_END\" \\\n    --output pauses.json\n\n# Review the returned candidates before combining them with the opening.\n```\n\n## Preserve teaching content when selecting pauses\n\nThe script uses one-second energy bins to propose candidates with an inclusive\ntwo-second minimum. These are approximate boundaries: increasing the minimum\nalone can discard real pauses while leaving longer quiet speech.\n\nPass the extracted audio to the detector. It fits two RMS levels in log space\nafter the opening, then requires a robust two-thirds majority of 20 ms frames\nbelow the midpoint of those levels. This rejects candidates whose average only\nlooks low relative to louder neighbors while tolerating occasional transient\nsounds. The cutoff is estimated from this recording, not a universal amplitude.\n\nRead audio_audit before combining segments: each candidate has its measured\nquiet-frame fraction and an acceptance decision. Only accepted candidates appear\nin segments. This check is still an energy heuristic; compare uncertain\ncandidates with adjacent audio and preserve audible teaching. Keep the audit JSON\nwith the final outputs so decisions remain reviewable. Use one-second\nenergy-calculator windows for this script's candidate timestamps.\nKeep the opening detector's result separate from the pause-duration rule.\nAvoid widening a cut across an intervening audible interval simply to combine\nnearby candidates. Render the video and generate the report from the same final,\nsorted, non-overlapping removal list.\n\n## Parameters Tuning\n\n| Parameter | Lower Value | Higher Value |\n|-----------|-------------|--------------|\n| `threshold_ratio` | Lower cutoff; fewer low-energy candidates | Higher cutoff; more low-energy candidates |\n| `min_duration` | Shorter pauses | Longer pauses only |\n| `window_size` | Local context | Broader context |\n\n## Notes\n\n- Requires energy data from energy-calculator skill\n- Use --start-time to skip detected opening\n- Local threshold adapts to varying speaker volume\n","# Pause Detector\n\nDetects pauses and low-energy segments using local dynamic thresholds on pre-computed energy data. This compares energy to surrounding context. Low energy relative to nearby speech proposes a pause candidate; it does not by itself establish silence.\n\n## Use Cases\n\n- Detecting natural pauses in lectures\n- Finding board-writing silences\n- Identifying breaks between sections\n\n## Usage\n\n```bash\npython3 \u002Froot\u002F.claude\u002Fskills\u002Fpause-detector\u002Fscripts\u002Fdetect_pauses.py \\\n    --energies \u002Fpath\u002Fto\u002Fenergies.json \\\n    --audio \u002Fpath\u002Fto\u002Faudio.wav \\\n    --output \u002Fpath\u002Fto\u002Fpauses.json\n```\n\n### Parameters\n\n- `--energies`: Path to energy JSON file (from energy-calculator)\n- `--audio`: Extracted 16-bit mono PCM WAV from the same recording (required)\n- `--output`: Path to output JSON file\n- `--start-time`: Start analyzing from this second (default: 0)\n- `--threshold-ratio`: Ratio of local average for low energy (default: 0.5)\n- `--min-duration`: Minimum pause duration in seconds, inclusive (default: 2)\n- `--window-size`: Local average window size (default: 30)\n\n### Output Format\n\n```json\n{\n  \"method\": \"local_dynamic_threshold_with_audio_audit\",\n  \"segments\": [\n    {\"start\": 610, \"end\": 613, \"duration\": 3},\n    {\"start\": 720, \"end\": 724, \"duration\": 4}\n  ],\n  \"total_segments\": 2,\n  \"total_duration_seconds\": 7,\n  \"parameters\": {\n    \"threshold_ratio\": 0.5,\n    \"window_size\": 30,\n    \"min_duration\": 2\n  }\n}\n```\n\n## How It Works\n\n1. Load pre-computed energy data\n2. Calculate local average using sliding window\n3. Mark seconds where energy \u003C local_avg × threshold_ratio\n4. Group consecutive low-energy seconds into segments\n5. Filter segments by minimum duration\n6. Audit each candidate against 20 ms RMS frames from the original audio; require at least two-thirds of its frames in the recording-derived quiet class. Save the cutoff and every accepted\u002Frejected candidate in audio_audit.\n\n## Dependencies\n\n- Python 3.11+\n- numpy\n- scipy\n\n## Example\n\n```bash\n# Set OPENING_END from the opening detector result, then detect long pauses\npython3 \u002Froot\u002F.claude\u002Fskills\u002Fpause-detector\u002Fscripts\u002Fdetect_pauses.py \\\n    --energies energies.json \\\n    --audio audio.wav \\\n    --start-time \"$OPENING_END\" \\\n    --output pauses.json\n\n# Review the returned candidates before combining them with the opening.\n```\n\n## Preserve teaching content when selecting pauses\n\nThe script uses one-second energy bins to propose candidates with an inclusive\ntwo-second minimum. These are approximate boundaries: increasing the minimum\nalone can discard real pauses while leaving longer quiet speech.\n\nPass the extracted audio to the detector. It fits two RMS levels in log space\nafter the opening, then requires a robust two-thirds majority of 20 ms frames\nbelow the midpoint of those levels. This rejects candidates whose average only\nlooks low relative to louder neighbors while tolerating occasional transient\nsounds. The cutoff is estimated from this recording, not a universal amplitude.\n\nRead audio_audit before combining segments: each candidate has its measured\nquiet-frame fraction and an acceptance decision. Only accepted candidates appear\nin segments. This check is still an energy heuristic; compare uncertain\ncandidates with adjacent audio and preserve audible teaching. Keep the audit JSON\nwith the final outputs so decisions remain reviewable. Use one-second\nenergy-calculator windows for this script's candidate timestamps.\nKeep the opening detector's result separate from the pause-duration rule.\nAvoid widening a cut across an intervening audible interval simply to combine\nnearby candidates. Render the video and generate the report from the same final,\nsorted, non-overlapping removal list.\n\n## Parameters Tuning\n\n| Parameter | Lower Value | Higher Value |\n|-----------|-------------|--------------|\n| `threshold_ratio` | Lower cutoff; fewer low-energy candidates | Higher cutoff; more low-energy candidates |\n| `min_duration` | Shorter pauses | Longer pauses only |\n| `window_size` | Local context | Broader context |\n\n## Notes\n\n- Requires energy data from energy-calculator skill\n- Use --start-time to skip detected opening\n- Local threshold adapts to varying speaker volume\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FHumanAnnotated-CrossModel-10Tasks-20261008\u002Fgemini31\u002Ftasks\u002Fvideo-silence-remover\u002Frepaired_skill\u002Fpause-detector",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill pause-detector",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill pause-detector",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill pause-detector","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FHumanAnnotated-CrossModel-10Tasks-20261008\u002Fgemini31\u002Ftasks\u002Fvideo-silence-remover\u002Frepaired_skill\u002Fpause-detector\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fdetect_pauses.py","SCRIPT","脚本",6213,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FHumanAnnotated-CrossModel-10Tasks-20261008\u002Fgemini31\u002Ftasks\u002Fvideo-silence-remover\u002Frepaired_skill\u002Fpause-detector\u002Fscripts\u002Fdetect_pauses.py",[52,59,66,73,78,83],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":74,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":79,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":84,"name":68,"nameZh":6,"description":69,"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},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]