[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YM39TWHE72KC63HVTH5WN":3,"skill-same:01M78YM39TWHE72KC63HVTH5WN":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78YM39TWHE72KC63HVTH5WN","video-restoration",null,"KAIR VRT and RVRT video restoration testing and training guidance for video super-resolution, deblurring, denoising, frame interpolation, and space-time SR.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video-restoration\ndescription: \"KAIR VRT and RVRT video restoration testing and training guidance\n  for video super-resolution, deblurring, denoising, frame interpolation, and\n  space-time SR.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# KAIR video restoration router\n\nUse this sub-skill when the task is about KAIR VRT or RVRT video workflows:\nvideo super-resolution, video deblurring, video denoising, video frame\ninterpolation, space-time video SR, VRT\u002FRVRT task IDs, video tiling\u002FOOM, VRT or\nRVRT training configs, or RVRT custom CUDA extension failures.\n\nBefore giving commands, assume the user is in their own KAIR checkout and has\ninstalled PyTorch plus KAIR's `requirement.txt` dependencies. Treat VRT\u002FRVRT\nfull inference and training as CUDA-first workflows; RVRT's guided deformable\nattention path requires a working CUDA-capable PyTorch build, `nvcc`, and\n`ninja` for the custom extension.\n\n## Read these bundled references\n\n- `references\u002Fvrt-rvrt-task-reference.md` for the VRT `001`-`009` and RVRT\n  `001`-`006` task namespaces, checkpoint names, default test folders, and\n  training config paths.\n- `references\u002Fvideo-restoration-workflows.md` for quick testing, custom-folder\n  commands, training command patterns, data layout expectations, tile semantics,\n  auto-download caveats, and metric\u002Foutput behavior.\n- `references\u002Ftroubleshooting.md` when CUDA extension builds, missing weights,\n  missing data, Vimeo preparation, DDP checkpoint\u002Fstatic-graph resumes,\n  `num_workers`, or OOM are involved.\n- `scripts\u002Fbuild_video_restoration_command.py` to print safe KAIR VRT\u002FRVRT test\n  commands without importing KAIR, downloading files, or launching inference.\n\n## Route to siblings for non-owned work\n\n- Route video dataset regrouping, LMDB creation, meta-info validation, and\n  destructive preparation scripts to `..\u002Fdata-preparation\u002FSKILL.md`.\n- Route generic image restoration testing to `..\u002Fimage-testing\u002FSKILL.md`.\n- Route generic image training and non-video KAIR configs to\n  `..\u002Fimage-training\u002FSKILL.md`.\n- Route shared checkpoint acquisition policy to the root model-zoo\u002Fdownload\n  guidance when available; VRT\u002FRVRT test scripts can auto-download missing\n  weights and some testsets, so call that out before running them.\n\nDo not ask future agents to inspect the original KAIR source or docs for these\nworkflows. The operational task tables, command patterns, caveats, and failure\nmodes are distilled into this sub-skill's bundled references.\n","# KAIR video restoration router\n\nUse this sub-skill when the task is about KAIR VRT or RVRT video workflows:\nvideo super-resolution, video deblurring, video denoising, video frame\ninterpolation, space-time video SR, VRT\u002FRVRT task IDs, video tiling\u002FOOM, VRT or\nRVRT training configs, or RVRT custom CUDA extension failures.\n\nBefore giving commands, assume the user is in their own KAIR checkout and has\ninstalled PyTorch plus KAIR's `requirement.txt` dependencies. Treat VRT\u002FRVRT\nfull inference and training as CUDA-first workflows; RVRT's guided deformable\nattention path requires a working CUDA-capable PyTorch build, `nvcc`, and\n`ninja` for the custom extension.\n\n## Read these bundled references\n\n- `references\u002Fvrt-rvrt-task-reference.md` for the VRT `001`-`009` and RVRT\n  `001`-`006` task namespaces, checkpoint names, default test folders, and\n  training config paths.\n- `references\u002Fvideo-restoration-workflows.md` for quick testing, custom-folder\n  commands, training command patterns, data layout expectations, tile semantics,\n  auto-download caveats, and metric\u002Foutput behavior.\n- `references\u002Ftroubleshooting.md` when CUDA extension builds, missing weights,\n  missing data, Vimeo preparation, DDP checkpoint\u002Fstatic-graph resumes,\n  `num_workers`, or OOM are involved.\n- `scripts\u002Fbuild_video_restoration_command.py` to print safe KAIR VRT\u002FRVRT test\n  commands without importing KAIR, downloading files, or launching inference.\n\n## Route to siblings for non-owned work\n\n- Route video dataset regrouping, LMDB creation, meta-info validation, and\n  destructive preparation scripts to `..\u002Fdata-preparation\u002FSKILL.md`.\n- Route generic image restoration testing to `..\u002Fimage-testing\u002FSKILL.md`.\n- Route generic image training and non-video KAIR configs to\n  `..\u002Fimage-training\u002FSKILL.md`.\n- Route shared checkpoint acquisition policy to the root model-zoo\u002Fdownload\n  guidance when available; VRT\u002FRVRT test scripts can auto-download missing\n  weights and some testsets, so call that out before running them.\n\nDo not ask future agents to inspect the original KAIR source or docs for these\nworkflows. The operational task tables, command patterns, caveats, and failure\nmodes are distilled into this sub-skill's bundled references.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill video-restoration",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill video-restoration",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill video-restoration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",9104,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002Freferences\u002Ftroubleshooting.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fvideo-restoration-workflows.md",9939,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002Freferences\u002Fvideo-restoration-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fvrt-rvrt-task-reference.md",8739,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002Freferences\u002Fvrt-rvrt-task-reference.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_video_restoration_command.py","SCRIPT","脚本",6583,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkair\u002Fsub-skills\u002Fvideo-restoration\u002Fscripts\u002Fbuild_video_restoration_command.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]