[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794V9A73C5Z8BCZP7QDRFV4":3,"skill-same:01M794V9A73C5Z8BCZP7QDRFV4":71},{"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},"01M794V9A73C5Z8BCZP7QDRFV4","automatic-mask-generation",null,"Generate masks for all objects in images or folders with Segment Anything's SamAutomaticMaskGenerator and the bundled AMG CLI. Use for batch automatic masks, PNG\u002FCSV outputs, COCO RLE JSON, threshold tuning, crop settings, and memory-aware AMG runs.","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\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automatic-mask-generation\ndescription: \"Generate masks for all objects in images or folders with Segment\n  Anything's SamAutomaticMaskGenerator and the bundled AMG CLI. Use for batch\n  automatic masks, PNG\u002FCSV outputs, COCO RLE JSON, threshold tuning, crop\n  settings, and memory-aware AMG runs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Automatic Mask Generation\n\nUse this sub-skill when the user wants SAM to segment all visible objects in an image or folder without point or box prompts. It covers `SamAutomaticMaskGenerator`, the bundled `scripts\u002Famg_cli.py`, binary mask PNG folders, `metadata.csv`, COCO RLE JSON, threshold tuning, crop expansion, batching, and memory tradeoffs.\n\nDo not use this sub-skill for prompted point\u002Fbox\u002Fmask refinement; route those requests to `..\u002Fprompted-segmentation\u002F`. Do not use it for ONNX export, browser inference, or the web demo; route those requests to `..\u002Fonnx-and-browser\u002F`.\n\n## Quick Start\n\n```bash\npython sub-skills\u002Fautomatic-mask-generation\u002Fscripts\u002Famg_cli.py \\\n  --checkpoint sam_vit_b_01ec64.pth \\\n  --model-type vit_b \\\n  --input images\u002F \\\n  --output masks\u002F \\\n  --device cpu\n```\n\nFor COCO-style RLE JSON instead of per-mask PNG folders:\n\n```bash\npython sub-skills\u002Fautomatic-mask-generation\u002Fscripts\u002Famg_cli.py \\\n  --checkpoint sam_vit_h_4b8939.pth \\\n  --model-type vit_h \\\n  --input image.jpg \\\n  --output masks-rle\u002F \\\n  --convert-to-rle \\\n  --device cuda\n```\n\n## Routing\n\n- Use `references\u002Fapi-reference.md` for direct Python use of `SamAutomaticMaskGenerator` and returned annotation records.\n- Use `references\u002Fcli-reference.md` for exact bundled CLI flags, output layout, and optional dependency checks.\n- Use `references\u002Fworkflows.md` for folder runs, COCO RLE conversion, threshold tuning, and avoiding GPU out-of-memory failures.\n- Use `references\u002Ftroubleshooting.md` for missing `cv2`, missing `pycocotools`, checkpoint\u002Fmodel mismatch, CPU fallback, unreadable images, empty output, and memory blowups.\n\n## Key Defaults\n\n- Registry keys are `default`, `vit_h`, `vit_l`, and `vit_b`; `default` is equivalent to the ViT-H builder.\n- `SamAutomaticMaskGenerator(model)` defaults to `points_per_side=32`, `points_per_batch=64`, `pred_iou_thresh=0.88`, `stability_score_thresh=0.95`, `crop_n_layers=0`, `min_mask_region_area=0`, and `output_mode=\"binary_mask\"`.\n- `output_mode=\"coco_rle\"` requires `pycocotools`; `min_mask_region_area > 0` requires OpenCV.\n- Large images, high `points_per_side`, large `points_per_batch`, crop layers, and binary mask output all increase memory use.\n","# Automatic Mask Generation\n\nUse this sub-skill when the user wants SAM to segment all visible objects in an image or folder without point or box prompts. It covers `SamAutomaticMaskGenerator`, the bundled `scripts\u002Famg_cli.py`, binary mask PNG folders, `metadata.csv`, COCO RLE JSON, threshold tuning, crop expansion, batching, and memory tradeoffs.\n\nDo not use this sub-skill for prompted point\u002Fbox\u002Fmask refinement; route those requests to `..\u002Fprompted-segmentation\u002F`. Do not use it for ONNX export, browser inference, or the web demo; route those requests to `..\u002Fonnx-and-browser\u002F`.\n\n## Quick Start\n\n```bash\npython sub-skills\u002Fautomatic-mask-generation\u002Fscripts\u002Famg_cli.py \\\n  --checkpoint sam_vit_b_01ec64.pth \\\n  --model-type vit_b \\\n  --input images\u002F \\\n  --output masks\u002F \\\n  --device cpu\n```\n\nFor COCO-style RLE JSON instead of per-mask PNG folders:\n\n```bash\npython sub-skills\u002Fautomatic-mask-generation\u002Fscripts\u002Famg_cli.py \\\n  --checkpoint sam_vit_h_4b8939.pth \\\n  --model-type vit_h \\\n  --input image.jpg \\\n  --output masks-rle\u002F \\\n  --convert-to-rle \\\n  --device cuda\n```\n\n## Routing\n\n- Use `references\u002Fapi-reference.md` for direct Python use of `SamAutomaticMaskGenerator` and returned annotation records.\n- Use `references\u002Fcli-reference.md` for exact bundled CLI flags, output layout, and optional dependency checks.\n- Use `references\u002Fworkflows.md` for folder runs, COCO RLE conversion, threshold tuning, and avoiding GPU out-of-memory failures.\n- Use `references\u002Ftroubleshooting.md` for missing `cv2`, missing `pycocotools`, checkpoint\u002Fmodel mismatch, CPU fallback, unreadable images, empty output, and memory blowups.\n\n## Key Defaults\n\n- Registry keys are `default`, `vit_h`, `vit_l`, and `vit_b`; `default` is equivalent to the ViT-H builder.\n- `SamAutomaticMaskGenerator(model)` defaults to `points_per_side=32`, `points_per_batch=64`, `pred_iou_thresh=0.88`, `stability_score_thresh=0.95`, `crop_n_layers=0`, `min_mask_region_area=0`, and `output_mode=\"binary_mask\"`.\n- `output_mode=\"coco_rle\"` requires `pycocotools`; `min_mask_region_area > 0` requires OpenCV.\n- Large images, high `points_per_side`, large `points_per_batch`, crop layers, and binary mask output all increase memory use.\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\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation",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 automatic-mask-generation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill automatic-mask-generation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill automatic-mask-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",3573,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcli-reference.md",3706,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002Freferences\u002Fcli-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2988,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",3843,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Famg_cli.py","SCRIPT","脚本",8529,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fautomatic-mask-generation\u002Fscripts\u002Famg_cli.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]