[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7973VBK4D6PXM0Z2B5658ZT":3,"skill-same:01M7973VBK4D6PXM0Z2B5658ZT":75},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7973VBK4D6PXM0Z2B5658ZT","video-subtitle-extractor",null,"Use Video-subtitle-extractor (VSE) to extract hard-coded video subtitles into SRT\u002FTXT, configure OCR\u002Fbackends, batch GUI runs, clean subtitle output, and synchronize subtitle timelines.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video-subtitle-extractor\ndescription: \"Use Video-subtitle-extractor (VSE) to extract hard-coded video\n  subtitles into SRT\u002FTXT, configure OCR\u002Fbackends, batch GUI runs, clean subtitle\n  output, and synchronize subtitle timelines.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Video-subtitle-extractor (VSE)\n\nUse this repo skill when the task involves VSE \u002F Video-subtitle-extractor,\nhard-subtitle OCR from videos, VideoSubFinder frame detection, PaddleOCR model\nselection, GUI batch extraction, subtitle post-processing, or the bundled Sushi\nsubtitle timeline synchronizer.\n\nThis is an operating guide, not the VSE application itself. If the user has no\nVSE installation or source checkout yet, first follow\n[installation and runtime](references\u002Finstallation-and-runtime.md) to choose a\nrelease, source run, or backend-specific environment.\n\n## Route by task\n\n| User intent | Read |\n| --- | --- |\n| Extract hard-coded text from video into `.srt`\u002F`.txt`; plan CLI\u002Fsource runs; choose fast\u002Fauto\u002Faccurate; reason about VideoSubFinder and cache\u002Foutput paths | [extraction-workflows](sub-skills\u002Fextraction-workflows\u002FSKILL.md) |\n| Configure PaddleOCR\u002FPaddlePaddle, language codes, bundled V5 models, CPU\u002FCUDA\u002FDirectML\u002FONNX acceleration, OCR batches, thresholds, backend probes | [ocr-backends](sub-skills\u002Focr-backends\u002FSKILL.md) |\n| Edit typo replacement rules, clean OCR text, keep\u002Fdelete empty timestamps, generate TXT, debug missing OCR lines, tune confidence\u002Farea filters | [postprocessing-config](sub-skills\u002Fpostprocessing-config\u002FSKILL.md) |\n| Operate the PySide6 GUI, batch videos, draw subtitle areas, bind areas to AB sections, choose output folders, stop\u002Fretry tasks | [gui-batch-operations](sub-skills\u002Fgui-batch-operations\u002FSKILL.md) |\n| Synchronize an existing SRT\u002FASS subtitle track to another video with the bundled Sushi CLI\u002FAPI or GUI Sync Timeline page | [subtitle-sync](sub-skills\u002Fsubtitle-sync\u002FSKILL.md) |\n\n## Minimal runtime shape\n\nVSE is distributed primarily as an application\u002Fsource tree rather than a\npip-installable library with package metadata. Common public entry points are:\n\n- GUI: `python gui.py` from a VSE source checkout with GUI dependencies.\n- Interactive extraction CLI: `python -m backend.main` from a VSE source\n  checkout; it prompts for video path and subtitle area.\n- Sushi timeline synchronization: `python -m backend.sushi --src SOURCE --dst DEST --script SUBTITLE -o OUTPUT`.\n\nFor a non-interactive or automation task, do not guess missing coordinates or\nbackends. Use the bundled planning\u002Fprobe helpers:\n\n- [scripts\u002Fvse_environment_probe.py](scripts\u002Fvse_environment_probe.py) checks\n  dependencies, backend visibility, and VSE source-layout readiness.\n- [extraction-workflows\u002Fscripts\u002Fvse_cli_plan.py](sub-skills\u002Fextraction-workflows\u002Fscripts\u002Fvse_cli_plan.py)\n  prints a safe extraction plan without running OCR.\n- [ocr-backends\u002Fscripts\u002Fmodel_config_probe.py](sub-skills\u002Focr-backends\u002Fscripts\u002Fmodel_config_probe.py)\n  reports bundled V5 language\u002Fmodel mapping from a VSE source tree.\n\n## Default decisions\n\n- Prefer **Fast** or **Auto** mode first. Use **Accurate** only when Fast\u002FAuto\n  misses many subtitle intervals and the user accepts much slower processing.\n- Treat CPU as the portable baseline. CUDA, DirectML, ONNX providers, ROCm,\n  CoreML, and other accelerators are optional speed\u002Faccuracy paths and require\n  backend-specific verification.\n- Ask for or derive a concrete subtitle area before running extraction. If the\n  user only knows normalized GUI coordinates, route to\n  [gui-batch-operations](sub-skills\u002Fgui-batch-operations\u002FSKILL.md) for coordinate conversion.\n- Avoid paths with spaces or non-ASCII characters when troubleshooting VSE runs;\n  the upstream README warns these can cause unknown failures.\n\n## Cross-cutting references\n\n- Read [installation and runtime](references\u002Finstallation-and-runtime.md) for\n  Python version, dependency variants, backend install commands, and launch\n  expectations.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport,\n  model, video, path, backend, GUI, and process-management failures.\n- Read [development notes](references\u002Fdevelopment-notes.md) only for maintainer\n  packaging\u002Fbuild context; release build scripts are not normal user workflows.\n- Read [repo provenance](references\u002Frepo-provenance.md) before relying on this\n  skill for a newer VSE checkout.\n\n## Avoid this skill when\n\n- The user wants audio speech recognition \u002F ASR for videos without visible\n  hard-coded text. Use a speech\u002FASR workflow instead.\n- The user wants generic subtitle editing unrelated to VSE extraction or Sushi\n  synchronization.\n- The task is only about a different OCR library without VSE, VideoSubFinder,\n  or VSE's bundled model\u002Flayout assumptions.\n","# Video-subtitle-extractor (VSE)\n\nUse this repo skill when the task involves VSE \u002F Video-subtitle-extractor,\nhard-subtitle OCR from videos, VideoSubFinder frame detection, PaddleOCR model\nselection, GUI batch extraction, subtitle post-processing, or the bundled Sushi\nsubtitle timeline synchronizer.\n\nThis is an operating guide, not the VSE application itself. If the user has no\nVSE installation or source checkout yet, first follow\n[installation and runtime](references\u002Finstallation-and-runtime.md) to choose a\nrelease, source run, or backend-specific environment.\n\n## Route by task\n\n| User intent | Read |\n| --- | --- |\n| Extract hard-coded text from video into `.srt`\u002F`.txt`; plan CLI\u002Fsource runs; choose fast\u002Fauto\u002Faccurate; reason about VideoSubFinder and cache\u002Foutput paths | [extraction-workflows](sub-skills\u002Fextraction-workflows\u002FSKILL.md) |\n| Configure PaddleOCR\u002FPaddlePaddle, language codes, bundled V5 models, CPU\u002FCUDA\u002FDirectML\u002FONNX acceleration, OCR batches, thresholds, backend probes | [ocr-backends](sub-skills\u002Focr-backends\u002FSKILL.md) |\n| Edit typo replacement rules, clean OCR text, keep\u002Fdelete empty timestamps, generate TXT, debug missing OCR lines, tune confidence\u002Farea filters | [postprocessing-config](sub-skills\u002Fpostprocessing-config\u002FSKILL.md) |\n| Operate the PySide6 GUI, batch videos, draw subtitle areas, bind areas to AB sections, choose output folders, stop\u002Fretry tasks | [gui-batch-operations](sub-skills\u002Fgui-batch-operations\u002FSKILL.md) |\n| Synchronize an existing SRT\u002FASS subtitle track to another video with the bundled Sushi CLI\u002FAPI or GUI Sync Timeline page | [subtitle-sync](sub-skills\u002Fsubtitle-sync\u002FSKILL.md) |\n\n## Minimal runtime shape\n\nVSE is distributed primarily as an application\u002Fsource tree rather than a\npip-installable library with package metadata. Common public entry points are:\n\n- GUI: `python gui.py` from a VSE source checkout with GUI dependencies.\n- Interactive extraction CLI: `python -m backend.main` from a VSE source\n  checkout; it prompts for video path and subtitle area.\n- Sushi timeline synchronization: `python -m backend.sushi --src SOURCE --dst DEST --script SUBTITLE -o OUTPUT`.\n\nFor a non-interactive or automation task, do not guess missing coordinates or\nbackends. Use the bundled planning\u002Fprobe helpers:\n\n- [scripts\u002Fvse_environment_probe.py](scripts\u002Fvse_environment_probe.py) checks\n  dependencies, backend visibility, and VSE source-layout readiness.\n- [extraction-workflows\u002Fscripts\u002Fvse_cli_plan.py](sub-skills\u002Fextraction-workflows\u002Fscripts\u002Fvse_cli_plan.py)\n  prints a safe extraction plan without running OCR.\n- [ocr-backends\u002Fscripts\u002Fmodel_config_probe.py](sub-skills\u002Focr-backends\u002Fscripts\u002Fmodel_config_probe.py)\n  reports bundled V5 language\u002Fmodel mapping from a VSE source tree.\n\n## Default decisions\n\n- Prefer **Fast** or **Auto** mode first. Use **Accurate** only when Fast\u002FAuto\n  misses many subtitle intervals and the user accepts much slower processing.\n- Treat CPU as the portable baseline. CUDA, DirectML, ONNX providers, ROCm,\n  CoreML, and other accelerators are optional speed\u002Faccuracy paths and require\n  backend-specific verification.\n- Ask for or derive a concrete subtitle area before running extraction. If the\n  user only knows normalized GUI coordinates, route to\n  [gui-batch-operations](sub-skills\u002Fgui-batch-operations\u002FSKILL.md) for coordinate conversion.\n- Avoid paths with spaces or non-ASCII characters when troubleshooting VSE runs;\n  the upstream README warns these can cause unknown failures.\n\n## Cross-cutting references\n\n- Read [installation and runtime](references\u002Finstallation-and-runtime.md) for\n  Python version, dependency variants, backend install commands, and launch\n  expectations.\n- Read [troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport,\n  model, video, path, backend, GUI, and process-management failures.\n- Read [development notes](references\u002Fdevelopment-notes.md) only for maintainer\n  packaging\u002Fbuild context; release build scripts are not normal user workflows.\n- Read [repo provenance](references\u002Frepo-provenance.md) before relying on this\n  skill for a newer VSE checkout.\n\n## Avoid this skill when\n\n- The user wants audio speech recognition \u002F ASR for videos without visible\n  hard-coded text. Use a speech\u002FASR workflow instead.\n- The user wants generic subtitle editing unrelated to VSE extraction or Sushi\n  synchronization.\n- The task is only about a different OCR library without VSE, VideoSubFinder,\n  or VSE's bundled model\u002Flayout assumptions.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill video-subtitle-extractor",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill video-subtitle-extractor",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill video-subtitle-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdevelopment-notes.md","REFERENCE","参考文档",1622,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Freferences\u002Fdevelopment-notes.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finstallation-and-runtime.md",3265,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Freferences\u002Finstallation-and-runtime.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",1832,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",349,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",2590,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fvse_environment_probe.py","SCRIPT","脚本",3004,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvideo-subtitle-extractor\u002Fscripts\u002Fvse_environment_probe.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"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":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]