[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SZ2DSXP69BA0QAV8V1220":3,"skill-same:01M78SZ2DSXP69BA0QAV8V1220":67},{"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},"01M78SZ2DSXP69BA0QAV8V1220","utilities",null,"Guides Autodistill image loading, visualization, model comparison, video splitting, and Roboflow utility boundaries.","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\u002Fautodistill\u002Fsub-skills\u002Futilities\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: utilities\ndescription: \"Guides Autodistill image loading, visualization, model comparison,\n  video splitting, and Roboflow utility boundaries.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Autodistill Utilities\n\nUse this sub-skill when a task asks about image loading\u002Fconversion, plotting detections, comparing model predictions, splitting video frames, understanding `split_data` side effects, or Roboflow synchronization helper boundaries.\n\nFor main auto-labeling workflows and dataset layout, use [dataset labeling](..\u002Fdataset-labeling\u002FSKILL.md). For CLI model selection, use [CLI and model registry](..\u002Fcli-and-model-registry\u002FSKILL.md). For custom model interface design, use [ontologies and model interfaces](..\u002Fontologies-and-model-interfaces\u002FSKILL.md).\n\n## Quick Route\n\n- **Image input conversion:** read [image loading and visualization](references\u002Fimage-loading-and-visualization.md) for `load_image` accepted inputs\u002Foutputs and headless plotting guidance.\n- **Utility function signatures and side effects:** read [utility reference](references\u002Futility-reference.md) for `load_image`, `split_data`, `split_video_frames`, `sync_with_roboflow`, `plot`, and `compare`.\n- **Utility failures:** read [troubleshooting](references\u002Ftroubleshooting.md) for invalid paths, unsupported return formats, URL\u002Fnetwork failures, OpenCV\u002FPillow issues, headless display, Roboflow credentials, and directory mutation.\n- **Safe local image-loading check:** run [scripts\u002Fcheck_image_loading.py](scripts\u002Fcheck_image_loading.py). It creates its own local fixture by default and does not need network.\n\n## Common Pattern\n\n```python\nfrom autodistill.helpers import load_image\n\ncv2_image = load_image(\"image.jpg\", return_format=\"cv2\")\npil_image = load_image(cv2_image, return_format=\"PIL\")\nnp_image = load_image(pil_image, return_format=\"numpy\")\n```\n\nUse `load_image` when a plugin expects a specific image object format but your workflow has a path, PIL image, or NumPy\u002FOpenCV array.\n\n## Headless Visualization Pattern\n\n```python\nfrom autodistill.utils import plot\n\nannotated = plot(image=image, detections=detections, classes=classes, raw=True)\n# Save or inspect annotated instead of relying on an interactive display.\n```\n\n`plot(..., raw=False)` uses `supervision.plot_image`, which may not be suitable for headless runs.\n\n## Safety Notes\n\n- `load_image` can fetch HTTP URLs; avoid that branch unless network use is approved.\n- `sync_with_roboflow` logs into Roboflow, downloads images, labels them, and uploads annotations; treat it as credentialed and externally mutating.\n- `split_data` mutates a dataset output directory by moving files and converting `.png`\u002F`.jpeg` to `.jpg` inside that output layout.\n","# Autodistill Utilities\n\nUse this sub-skill when a task asks about image loading\u002Fconversion, plotting detections, comparing model predictions, splitting video frames, understanding `split_data` side effects, or Roboflow synchronization helper boundaries.\n\nFor main auto-labeling workflows and dataset layout, use [dataset labeling](..\u002Fdataset-labeling\u002FSKILL.md). For CLI model selection, use [CLI and model registry](..\u002Fcli-and-model-registry\u002FSKILL.md). For custom model interface design, use [ontologies and model interfaces](..\u002Fontologies-and-model-interfaces\u002FSKILL.md).\n\n## Quick Route\n\n- **Image input conversion:** read [image loading and visualization](references\u002Fimage-loading-and-visualization.md) for `load_image` accepted inputs\u002Foutputs and headless plotting guidance.\n- **Utility function signatures and side effects:** read [utility reference](references\u002Futility-reference.md) for `load_image`, `split_data`, `split_video_frames`, `sync_with_roboflow`, `plot`, and `compare`.\n- **Utility failures:** read [troubleshooting](references\u002Ftroubleshooting.md) for invalid paths, unsupported return formats, URL\u002Fnetwork failures, OpenCV\u002FPillow issues, headless display, Roboflow credentials, and directory mutation.\n- **Safe local image-loading check:** run [scripts\u002Fcheck_image_loading.py](scripts\u002Fcheck_image_loading.py). It creates its own local fixture by default and does not need network.\n\n## Common Pattern\n\n```python\nfrom autodistill.helpers import load_image\n\ncv2_image = load_image(\"image.jpg\", return_format=\"cv2\")\npil_image = load_image(cv2_image, return_format=\"PIL\")\nnp_image = load_image(pil_image, return_format=\"numpy\")\n```\n\nUse `load_image` when a plugin expects a specific image object format but your workflow has a path, PIL image, or NumPy\u002FOpenCV array.\n\n## Headless Visualization Pattern\n\n```python\nfrom autodistill.utils import plot\n\nannotated = plot(image=image, detections=detections, classes=classes, raw=True)\n# Save or inspect annotated instead of relying on an interactive display.\n```\n\n`plot(..., raw=False)` uses `supervision.plot_image`, which may not be suitable for headless runs.\n\n## Safety Notes\n\n- `load_image` can fetch HTTP URLs; avoid that branch unless network use is approved.\n- `sync_with_roboflow` logs into Roboflow, downloads images, labels them, and uploads annotations; treat it as credentialed and externally mutating.\n- `split_data` mutates a dataset output directory by moving files and converting `.png`\u002F`.jpeg` to `.jpg` inside that output layout.\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\u002Fautodistill\u002Fsub-skills\u002Futilities",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 utilities",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill utilities",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill utilities","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautodistill\u002Fsub-skills\u002Futilities\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fimage-loading-and-visualization.md","REFERENCE","参考文档",2217,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautodistill\u002Fsub-skills\u002Futilities\u002Freferences\u002Fimage-loading-and-visualization.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2327,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautodistill\u002Fsub-skills\u002Futilities\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Futility-reference.md",3011,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautodistill\u002Fsub-skills\u002Futilities\u002Freferences\u002Futility-reference.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_image_loading.py","SCRIPT","脚本",3148,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautodistill\u002Fsub-skills\u002Futilities\u002Fscripts\u002Fcheck_image_loading.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]