[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SZPZD8ED33ATQ5E8GVR9K":3,"skill-same:01M78SZPZD8ED33ATQ5E8GVR9K":83},{"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},"01M78SZPZD8ED33ATQ5E8GVR9K","multimodal-automl",null,"Use AutoGluon MultiModalPredictor for text, image, tabular+text\u002Fimage, document, NER, semantic matching, object detection, semantic segmentation, feature extraction, zero-shot, and deployment workflows.","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\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: multimodal-automl\ndescription: \"Use AutoGluon MultiModalPredictor for text, image,\n  tabular+text\u002Fimage, document, NER, semantic matching, object detection,\n  semantic segmentation, feature extraction, zero-shot, and deployment\n  workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# MultiModal AutoML\n\nUse this sub-skill when the user needs AutoGluon AutoMM or `MultiModalPredictor` for text, image, mixed tabular+text\u002Fimage, document, NER, semantic matching, object detection, semantic segmentation, feature extraction, zero-shot inference, or multimodal deployment\u002Fexport tasks.\n\nRoute structured-only supervised learning to `..\u002Ftabular-ml\u002F` and forecasting to `..\u002Ftime-series-forecasting\u002F`. Do not treat external dataset downloads, competition submissions, or raw repository CI examples as runtime requirements; distill the needed data\u002FAPI pattern and work with the user's local files.\n\n## Start Here\n\n- For constructor and method signatures, problem types, metrics, and model config knobs, read `references\u002Fapi-reference.md`.\n- For end-to-end task recipes, including semantic matching and save\u002Fload, read `references\u002Fworkflows.md`.\n- For DataFrame, image, document, NER, matching, segmentation, and local path expectations, read `references\u002Fdata-formats.md`.\n- For COCO\u002FVOC\u002FDataFrame object detection handling, read `references\u002Fobject-detection.md`.\n- For ONNX, TensorRT, embedding extraction, and offline packaging, read `references\u002Fdeployment.md`.\n- For dependency, backend, schema, and checkpoint failure modes, read `references\u002Ftroubleshooting.md`.\n\n## Safe Bundled Helpers\n\n- Use `scripts\u002Finspect_multimodal_inputs.py --help` to validate local CSV\u002FJSON data, image\u002Fdocument paths, matching identifiers, COCO metadata, or VOC-style annotations without training or downloading.\n- Use `scripts\u002Fmultimodal_smoke.py --help` to check installed AutoGluon multimodal imports, API signatures, problem types, and optional backend versions without training by default.\n\n## Routing Guide\n\n| User request | Read first | Key API |\n| --- | --- | --- |\n| Text\u002Fimage\u002Fmixed classification or regression | `references\u002Fworkflows.md` | `MultiModalPredictor(label=..., problem_type=...)` |\n| Document image\u002FPDF classification | `references\u002Fdata-formats.md` | `column_types={...: \"document\"}` or inferred document columns |\n| NER\u002Fentity extraction | `references\u002Fdata-formats.md` | `problem_type=\"ner\"`, `column_types={text_col: \"text_ner\"}` |\n| Text\u002Fimage\u002Fimage-text similarity or retrieval | `references\u002Fworkflows.md` | `query=...`, `response=...`, `match_label=...`, `candidate_data`, `id_mappings` |\n| Object detection | `references\u002Fobject-detection.md` | `problem_type=\"object_detection\"`, COCO\u002FVOC\u002FDataFrame data |\n| Semantic segmentation | `references\u002Fdata-formats.md` | `problem_type=\"semantic_segmentation\"`, image and mask columns |\n| Feature extraction or zero-shot image classification | `references\u002Fworkflows.md` | `problem_type=\"feature_extraction\"` or `\"zero_shot_image_classification\"` |\n| ONNX\u002FTensorRT\u002Fexport\u002Foffline deployment | `references\u002Fdeployment.md` | `save`, `load`, `export_onnx`, `optimize_for_inference` |\n\n## Default Agent Approach\n\n1. Identify the task family and route away if it is structured-only tabular or time-series.\n2. Confirm data shape before code: label\u002Fquery\u002Fresponse columns, local image\u002Fdocument paths, object-detection annotation format, segmentation mask availability, and optional backend constraints.\n3. Prefer CPU-safe, no-download validation first with the bundled scripts; only propose training\u002Fexport after local data and dependencies are plausible.\n4. Keep `path`\u002F`save_path` explicit for real training, use short `time_limit` only for smoke examples, and set backend hyperparameters intentionally for CPU\u002FGPU.\n5. For matching\u002Fretrieval, distinguish row-pair prediction from candidate search: `predict(data, candidate_data=...)`, `evaluate(query_data=..., response_data=...)`, or embedding-based search.\n6. For deployment, call out pickle trust for `load`, optional `standalone=True` packaging, and ONNXRuntime\u002FTensorRT dependency requirements.\n","# MultiModal AutoML\n\nUse this sub-skill when the user needs AutoGluon AutoMM or `MultiModalPredictor` for text, image, mixed tabular+text\u002Fimage, document, NER, semantic matching, object detection, semantic segmentation, feature extraction, zero-shot inference, or multimodal deployment\u002Fexport tasks.\n\nRoute structured-only supervised learning to `..\u002Ftabular-ml\u002F` and forecasting to `..\u002Ftime-series-forecasting\u002F`. Do not treat external dataset downloads, competition submissions, or raw repository CI examples as runtime requirements; distill the needed data\u002FAPI pattern and work with the user's local files.\n\n## Start Here\n\n- For constructor and method signatures, problem types, metrics, and model config knobs, read `references\u002Fapi-reference.md`.\n- For end-to-end task recipes, including semantic matching and save\u002Fload, read `references\u002Fworkflows.md`.\n- For DataFrame, image, document, NER, matching, segmentation, and local path expectations, read `references\u002Fdata-formats.md`.\n- For COCO\u002FVOC\u002FDataFrame object detection handling, read `references\u002Fobject-detection.md`.\n- For ONNX, TensorRT, embedding extraction, and offline packaging, read `references\u002Fdeployment.md`.\n- For dependency, backend, schema, and checkpoint failure modes, read `references\u002Ftroubleshooting.md`.\n\n## Safe Bundled Helpers\n\n- Use `scripts\u002Finspect_multimodal_inputs.py --help` to validate local CSV\u002FJSON data, image\u002Fdocument paths, matching identifiers, COCO metadata, or VOC-style annotations without training or downloading.\n- Use `scripts\u002Fmultimodal_smoke.py --help` to check installed AutoGluon multimodal imports, API signatures, problem types, and optional backend versions without training by default.\n\n## Routing Guide\n\n| User request | Read first | Key API |\n| --- | --- | --- |\n| Text\u002Fimage\u002Fmixed classification or regression | `references\u002Fworkflows.md` | `MultiModalPredictor(label=..., problem_type=...)` |\n| Document image\u002FPDF classification | `references\u002Fdata-formats.md` | `column_types={...: \"document\"}` or inferred document columns |\n| NER\u002Fentity extraction | `references\u002Fdata-formats.md` | `problem_type=\"ner\"`, `column_types={text_col: \"text_ner\"}` |\n| Text\u002Fimage\u002Fimage-text similarity or retrieval | `references\u002Fworkflows.md` | `query=...`, `response=...`, `match_label=...`, `candidate_data`, `id_mappings` |\n| Object detection | `references\u002Fobject-detection.md` | `problem_type=\"object_detection\"`, COCO\u002FVOC\u002FDataFrame data |\n| Semantic segmentation | `references\u002Fdata-formats.md` | `problem_type=\"semantic_segmentation\"`, image and mask columns |\n| Feature extraction or zero-shot image classification | `references\u002Fworkflows.md` | `problem_type=\"feature_extraction\"` or `\"zero_shot_image_classification\"` |\n| ONNX\u002FTensorRT\u002Fexport\u002Foffline deployment | `references\u002Fdeployment.md` | `save`, `load`, `export_onnx`, `optimize_for_inference` |\n\n## Default Agent Approach\n\n1. Identify the task family and route away if it is structured-only tabular or time-series.\n2. Confirm data shape before code: label\u002Fquery\u002Fresponse columns, local image\u002Fdocument paths, object-detection annotation format, segmentation mask availability, and optional backend constraints.\n3. Prefer CPU-safe, no-download validation first with the bundled scripts; only propose training\u002Fexport after local data and dependencies are plausible.\n4. Keep `path`\u002F`save_path` explicit for real training, use short `time_limit` only for smoke examples, and set backend hyperparameters intentionally for CPU\u002FGPU.\n5. For matching\u002Fretrieval, distinguish row-pair prediction from candidate search: `predict(data, candidate_data=...)`, `evaluate(query_data=..., response_data=...)`, or embedding-based search.\n6. For deployment, call out pickle trust for `load`, optional `standalone=True` packaging, and ONNXRuntime\u002FTensorRT dependency requirements.\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\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl",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 multimodal-automl",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-automl",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-automl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002FSKILL.md",[47,53,57,61,65,69,73,79],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8983,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdata-formats.md",7073,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Fdata-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fdeployment.md",5083,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Fdeployment.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fobject-detection.md",5624,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Fobject-detection.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",6672,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fworkflows.md",8665,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Freferences\u002Fworkflows.md",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Finspect_multimodal_inputs.py","SCRIPT","脚本",20045,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Fscripts\u002Finspect_multimodal_inputs.py",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fmultimodal_smoke.py",8177,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautogluon\u002Fsub-skills\u002Fmultimodal-automl\u002Fscripts\u002Fmultimodal_smoke.py",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]