[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78W192HV13X40SWS0VCZH02":3,"skill-same:01M78W192HV13X40SWS0VCZH02":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},"01M78W192HV13X40SWS0VCZH02","inference-visualization",null,"Run Detectron2 inference, inspect model outputs, and visualize predictions safely without depending on the source demo script.","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\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-visualization\ndescription: \"Run Detectron2 inference, inspect model outputs, and visualize\n  predictions safely without depending on the source demo script.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Detectron2 Inference & Visualization\n\nUse this sub-skill when a task asks to run Detectron2 inference, call `DefaultPredictor`, call a built model directly, inspect `Instances`\u002F`Boxes`\u002Fmasks, visualize predictions, plan demo-style image\u002Fvideo\u002Fwebcam commands, or validate COCO-style prediction JSON before drawing it.\n\n## Fast Routing\n\n- For simple single-image inference, read [references\u002Finference-workflows.md](references\u002Finference-workflows.md#defaultpredictor-single-image-inference) and use `DefaultPredictor(cfg)` only when weights are local or downloads are intentional.\n- For batch\u002Fdirect model calls, read [references\u002Finference-workflows.md](references\u002Finference-workflows.md#direct-model-inference) and use `build_model(cfg)`, `DetectionCheckpointer(model).load(...)`, `model.eval()`, and `model([input_dict])[0]`.\n- For output parsing, field checks, JSON conversion, and visualization requirements, read [references\u002Fstructures-and-outputs.md](references\u002Fstructures-and-outputs.md).\n- For broken demo imports, OpenCV issues, CPU\u002FCUDA mismatches, empty predictions, metadata labels, or output side effects, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Build a safe demo-style command without executing it through [scripts\u002Fdemo_command_builder.py](scripts\u002Fdemo_command_builder.py).\n- Validate COCO-style prediction JSON without drawing or importing Detectron2 through [scripts\u002Fvisualize_json_schema_check.py](scripts\u002Fvisualize_json_schema_check.py).\n\n## Safe Defaults\n\n- Set inference device before model or predictor construction: Yacs configs use `cfg.MODEL.DEVICE = \"cpu\"` or the CLI override `MODEL.DEVICE cpu`.\n- Do not instantiate `DefaultPredictor` during no-download validation if `cfg.MODEL.WEIGHTS` points to a URL or `detectron2:\u002F\u002F` URI; it loads weights during construction.\n- Treat OpenCV images as BGR, but pass RGB images to `Visualizer`; convert with `image_rgb = image_bgr[:, :, ::-1]`.\n- Move predictions to CPU before visualization: `instances = outputs[\"instances\"].to(\"cpu\")`.\n- Check `instances.has(\"pred_boxes\")`, `instances.has(\"scores\")`, and metadata class names before assuming labels or boxes exist.\n\n## Boundaries\n\nThis sub-skill owns inference calls, model input\u002Foutput formats, `Instances`, `Boxes`, `BoxMode`, `BitMasks`, `PolygonMasks`, `ImageList`, `Visualizer`, `ColorMode`, demo-style flags, confidence thresholds, CPU overrides, and prediction JSON sanity checks.\n\nRoute model-zoo config\u002Fcheckpoint selection to `..\u002Fconfiguration-model-zoo\u002F`. Route dataset registration, catalog metadata, and dataset dict validation to `..\u002Fdata-datasets\u002F`. Route training, evaluation loops, evaluators, and metrics to `..\u002Ftraining-evaluation\u002F`. Route TorchScript, tracing, Caffe2, and deployment packaging to `..\u002Fdeployment-export\u002F`.\n","# Detectron2 Inference & Visualization\n\nUse this sub-skill when a task asks to run Detectron2 inference, call `DefaultPredictor`, call a built model directly, inspect `Instances`\u002F`Boxes`\u002Fmasks, visualize predictions, plan demo-style image\u002Fvideo\u002Fwebcam commands, or validate COCO-style prediction JSON before drawing it.\n\n## Fast Routing\n\n- For simple single-image inference, read [references\u002Finference-workflows.md](references\u002Finference-workflows.md#defaultpredictor-single-image-inference) and use `DefaultPredictor(cfg)` only when weights are local or downloads are intentional.\n- For batch\u002Fdirect model calls, read [references\u002Finference-workflows.md](references\u002Finference-workflows.md#direct-model-inference) and use `build_model(cfg)`, `DetectionCheckpointer(model).load(...)`, `model.eval()`, and `model([input_dict])[0]`.\n- For output parsing, field checks, JSON conversion, and visualization requirements, read [references\u002Fstructures-and-outputs.md](references\u002Fstructures-and-outputs.md).\n- For broken demo imports, OpenCV issues, CPU\u002FCUDA mismatches, empty predictions, metadata labels, or output side effects, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Build a safe demo-style command without executing it through [scripts\u002Fdemo_command_builder.py](scripts\u002Fdemo_command_builder.py).\n- Validate COCO-style prediction JSON without drawing or importing Detectron2 through [scripts\u002Fvisualize_json_schema_check.py](scripts\u002Fvisualize_json_schema_check.py).\n\n## Safe Defaults\n\n- Set inference device before model or predictor construction: Yacs configs use `cfg.MODEL.DEVICE = \"cpu\"` or the CLI override `MODEL.DEVICE cpu`.\n- Do not instantiate `DefaultPredictor` during no-download validation if `cfg.MODEL.WEIGHTS` points to a URL or `detectron2:\u002F\u002F` URI; it loads weights during construction.\n- Treat OpenCV images as BGR, but pass RGB images to `Visualizer`; convert with `image_rgb = image_bgr[:, :, ::-1]`.\n- Move predictions to CPU before visualization: `instances = outputs[\"instances\"].to(\"cpu\")`.\n- Check `instances.has(\"pred_boxes\")`, `instances.has(\"scores\")`, and metadata class names before assuming labels or boxes exist.\n\n## Boundaries\n\nThis sub-skill owns inference calls, model input\u002Foutput formats, `Instances`, `Boxes`, `BoxMode`, `BitMasks`, `PolygonMasks`, `ImageList`, `Visualizer`, `ColorMode`, demo-style flags, confidence thresholds, CPU overrides, and prediction JSON sanity checks.\n\nRoute model-zoo config\u002Fcheckpoint selection to `..\u002Fconfiguration-model-zoo\u002F`. Route dataset registration, catalog metadata, and dataset dict validation to `..\u002Fdata-datasets\u002F`. Route training, evaluation loops, evaluators, and metrics to `..\u002Ftraining-evaluation\u002F`. Route TorchScript, tracing, Caffe2, and deployment packaging to `..\u002Fdeployment-export\u002F`.\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\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization",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 inference-visualization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-visualization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finference-workflows.md","REFERENCE","参考文档",6238,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002Freferences\u002Finference-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fstructures-and-outputs.md",6714,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002Freferences\u002Fstructures-and-outputs.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5834,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fdemo_command_builder.py","SCRIPT","脚本",5903,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002Fscripts\u002Fdemo_command_builder.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fvisualize_json_schema_check.py",10333,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdetectron2\u002Fsub-skills\u002Finference-visualization\u002Fscripts\u002Fvisualize_json_schema_check.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",[],[]]