[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKDWVC5XSXZ0BT4C4CE2WF":3,"skill-same:01M7BKDWVC5XSXZ0BT4C4CE2WF":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},"01M7BKDWVC5XSXZ0BT4C4CE2WF","segment-combiner",null,"Combine multiple detector outputs into a single removal list, then merge intervals to reduce fragmentation and avoid precision loss from over-segmentation.","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\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Fsingle-video-silence-remover-all\u002Fround-5\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: segment-combiner\ndescription: Combine multiple detector outputs into a single removal list, then merge\n  intervals to reduce fragmentation and avoid precision loss from over-segmentation.\n---\n\n## Steps\n1. Combine detector outputs (this script **concatenates + sorts**; it does not “union-merge” by itself):\n   ```bash\n   python3 \u002Froot\u002F.claude\u002Fskills\u002Fsegment-combiner\u002Fscripts\u002Fcombine_segments.py \\\n     --segments \u002Froot\u002Fsilence.json \u002Froot\u002Fpauses.json \\\n     --output \u002Froot\u002Fall_segments_raw.json\n   ```\n2. Merge intervals using the project convention:\n   - Treat segments as **half-open** intervals: `[start, end)` in seconds.\n   - Merge when `next.start \u003C= current.end` (overlap\u002Ftouch).\n   - To reduce fragmentation from 1-second energy quantization (improves benchmark **precision**), optionally also merge across tiny gaps by using a `gap_tolerance` (commonly `1` second): merge when `next.start \u003C= current.end + gap_tolerance`.\n   - After merging, always recompute `duration = end - start`.\n   Example merge post-process (edit `GAP` as needed):\n   ```bash\n   python3 - \u003C\u003C'PY'\n   import json\n   INP=\"\u002Froot\u002Fall_segments_raw.json\"\n   OUT=\"\u002Froot\u002Fall_segments.json\"\n   GAP=1  # 0 = only overlap\u002Ftouch; 1 = also merge 1s gaps to reduce fragmentation\n\n   data=json.load(open(INP))\n   segs=sorted(data.get(\"segments\", []), key=lambda s: s[\"start\"])\n\n   merged=[]\n   for s in segs:\n       a=float(s[\"start\"]); b=float(s[\"end\"])\n       if b \u003C= a:\n           continue\n       if (not merged) or (a > merged[-1][\"end\"] + GAP):\n           merged.append({\"start\": a, \"end\": b})\n       else:\n           merged[-1][\"end\"] = max(merged[-1][\"end\"], b)\n\n   def norm(x):\n       r=round(x)\n       return int(r) if abs(x-r) \u003C 1e-6 else float(x)\n\n   for m in merged:\n       m[\"start\"]=norm(m[\"start\"])\n       m[\"end\"]=norm(m[\"end\"])\n       m[\"duration\"]=m[\"end\"]-m[\"start\"]\n\n   out={\n       \"segments\": merged,\n       \"total_segments\": len(merged),\n       \"total_duration_seconds\": sum(m[\"duration\"] for m in merged),\n   }\n   json.dump(out, open(OUT, \"w\"), indent=2)\n   print(f\"Wrote {OUT}: {len(merged)} merged segments\")\n   PY\n   ```\n3. Quick validity check before video processing:\n   - sorted by `start`\n   - non-overlapping after merge\n   - each has numeric `start \u003C end` and `duration == end - start`\n\n## Expected Result\nA single `all_segments.json` containing a de-fragmented, merged removal list that is more likely to match ground truth segment granularity (higher precision).\n","## Steps\n1. Combine detector outputs (this script **concatenates + sorts**; it does not “union-merge” by itself):\n   ```bash\n   python3 \u002Froot\u002F.claude\u002Fskills\u002Fsegment-combiner\u002Fscripts\u002Fcombine_segments.py \\\n     --segments \u002Froot\u002Fsilence.json \u002Froot\u002Fpauses.json \\\n     --output \u002Froot\u002Fall_segments_raw.json\n   ```\n2. Merge intervals using the project convention:\n   - Treat segments as **half-open** intervals: `[start, end)` in seconds.\n   - Merge when `next.start \u003C= current.end` (overlap\u002Ftouch).\n   - To reduce fragmentation from 1-second energy quantization (improves benchmark **precision**), optionally also merge across tiny gaps by using a `gap_tolerance` (commonly `1` second): merge when `next.start \u003C= current.end + gap_tolerance`.\n   - After merging, always recompute `duration = end - start`.\n   Example merge post-process (edit `GAP` as needed):\n   ```bash\n   python3 - \u003C\u003C'PY'\n   import json\n   INP=\"\u002Froot\u002Fall_segments_raw.json\"\n   OUT=\"\u002Froot\u002Fall_segments.json\"\n   GAP=1  # 0 = only overlap\u002Ftouch; 1 = also merge 1s gaps to reduce fragmentation\n\n   data=json.load(open(INP))\n   segs=sorted(data.get(\"segments\", []), key=lambda s: s[\"start\"])\n\n   merged=[]\n   for s in segs:\n       a=float(s[\"start\"]); b=float(s[\"end\"])\n       if b \u003C= a:\n           continue\n       if (not merged) or (a > merged[-1][\"end\"] + GAP):\n           merged.append({\"start\": a, \"end\": b})\n       else:\n           merged[-1][\"end\"] = max(merged[-1][\"end\"], b)\n\n   def norm(x):\n       r=round(x)\n       return int(r) if abs(x-r) \u003C 1e-6 else float(x)\n\n   for m in merged:\n       m[\"start\"]=norm(m[\"start\"])\n       m[\"end\"]=norm(m[\"end\"])\n       m[\"duration\"]=m[\"end\"]-m[\"start\"]\n\n   out={\n       \"segments\": merged,\n       \"total_segments\": len(merged),\n       \"total_duration_seconds\": sum(m[\"duration\"] for m in merged),\n   }\n   json.dump(out, open(OUT, \"w\"), indent=2)\n   print(f\"Wrote {OUT}: {len(merged)} merged segments\")\n   PY\n   ```\n3. Quick validity check before video processing:\n   - sorted by `start`\n   - non-overlapping after merge\n   - each has numeric `start \u003C end` and `duration == end - start`\n\n## Expected Result\nA single `all_segments.json` containing a de-fragmented, merged removal list that is more likely to match ground truth segment granularity (higher precision).\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","controlled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Fsingle-video-silence-remover-all\u002Fround-5\u002Fskills\u002Fsegment-combiner",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 segment-combiner",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill segment-combiner",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill segment-combiner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Fsingle-video-silence-remover-all\u002Fround-5\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fcombine_segments.py","SCRIPT","脚本",1566,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Fsingle-video-silence-remover-all\u002Fround-5\u002Fskills\u002Fsegment-combiner\u002Fscripts\u002Fcombine_segments.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",[],[]]