[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2034AG46FDPF83HRFBGG":3,"skill-same:01M78Z2034AG46FDPF83HRFBGG":79},{"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},"01M78Z2034AG46FDPF83HRFBGG","layout-parser",null,"Routes LayoutParser workflows for document layout objects, document I\u002FO, visualization, OCR, and layout-detection model wrappers.","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\u002Flayout-parser\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: layout-parser\ndescription: \"Routes LayoutParser workflows for document layout objects,\n  document I\u002FO, visualization, OCR, and layout-detection model wrappers.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# LayoutParser\n\nLayoutParser is a document-image analysis toolkit for layout objects,\npage\u002Ftoken loading, OCR parsing, visualization, and layout-detection model\nwrappers.\n\nUse this root skill as a router. Read the owning sub-skill for detailed API\nnotes, workflow steps, and troubleshooting.\n\n## Install and first checks\n\nBase install:\n\n```bash\npip install layoutparser\n```\n\nOCR support:\n\n```bash\npip install \"layoutparser[ocr]\"\n```\n\nLayout-model support:\n\n```bash\npip install \"layoutparser[layoutmodels]\"\npip install \"layoutparser[effdet]\"\npip install \"layoutparser[paddledetection]\"\n```\n\nDetectron2 still uses its own backend install path:\n\n```bash\npip install layoutparser torchvision\npip install \"detectron2@git+https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdetectron2.git@v0.5#egg=detectron2\"\n```\n\nFor local inspection from a checkout, prefer an isolated environment and an\neditable install in that private environment rather than mutating the source\nrepository.\n\nMinimal import checks:\n\n```bash\npython -c \"import layoutparser as lp; print(lp.__version__)\"\npython -c \"from layoutparser import Layout, Rectangle; print(Layout([Rectangle(0, 0, 10, 10)]))\"\n```\n\nIf backend availability is uncertain, run the bundled inspector:\n\n```bash\npython scripts\u002Finspect_backends.py\n```\n\nFor a local smoke check that stays inside synthetic data, use:\n\n```bash\npython scripts\u002Fsmoke_layoutparser_core.py\n```\n\n## Route map\n\n### `layout-objects`\nRead this for:\n\n- `Interval`, `Rectangle`, `Quadrilateral`, `TextBlock`, and `Layout`\n- coordinate transforms, padding, shifting, scaling, cropping\n- `union`, `intersect`, `relative_to`, `condition_on`, `is_in`\n- `Layout` sorting, filtering, serialization, and line\u002Fcategory grouping\n\n### `layout-io`\nRead this for:\n\n- `load_json`, `load_dict`, `load_csv`, `load_dataframe`, `load_pdf`\n- JSON\u002FCSV\u002FDataFrame round-trips and PDF token extraction\n- page metadata, `block_type`, and layout export\u002Fimport issues\n- COCO-style annotation conversion patterns\n\n### `visualization`\nRead this for:\n\n- `draw_box` and `draw_text`\n- color maps, alpha handling, font settings, vertical text, and layout overlays\n- turning detected or loaded layouts into readable page visuals\n\n### `layout-models`\nRead this for:\n\n- `AutoLayoutModel`\n- `Detectron2LayoutModel`, `EfficientDetLayoutModel`, and `PaddleDetectionLayoutModel`\n- `lp:\u002F\u002F` config parsing, model catalogs, label maps, and backend selection\n- model download, cache, and device-selection behavior\n\n### `ocr`\nRead this for:\n\n- `TesseractAgent`, `TesseractFeatureType`\n- `GCVAgent`, `GCVFeatureType`\n- OCR response parsing, saved-response loading, and text aggregation\n- credential and binary requirements for live OCR\n\n## Root references\n\n- Read `references\u002Fapi-reference.md` for the top-level public API map.\n- Read `references\u002Fworkflows.md` for cross-sub-skill document workflows.\n- Read `references\u002Frepo-provenance.md` before checking staleness or refreshing.\n- Read `references\u002Frepo-routing-metadata.json` only when verifying managed\n  repo-skills-router placement.\n\n## When to jump to troubleshooting\n\nRead `references\u002Ftroubleshooting.md` when you see any of these:\n\n- missing optional backend imports\n- `pkg_resources` \u002F setuptools issues around `google-cloud-vision==1`\n- `tesseract` or credential problems\n- `pdf2image` \u002F `poppler` problems\n- `InvalidShapeError`, `NotSupportedShapeError`, or layout validation errors\n- model download, cache, or `lp:\u002F\u002F` parsing failures\n\n## Notes for future agents\n\n- This skill is public runtime guidance; do not rely on the original checkout\n  remaining available.\n- Runtime links should stay inside this generated skill tree.\n- Use the sub-skill that matches the user’s primary workflow first, then cross-\n  reference the others when a task spans multiple layers.\n","# LayoutParser\n\nLayoutParser is a document-image analysis toolkit for layout objects,\npage\u002Ftoken loading, OCR parsing, visualization, and layout-detection model\nwrappers.\n\nUse this root skill as a router. Read the owning sub-skill for detailed API\nnotes, workflow steps, and troubleshooting.\n\n## Install and first checks\n\nBase install:\n\n```bash\npip install layoutparser\n```\n\nOCR support:\n\n```bash\npip install \"layoutparser[ocr]\"\n```\n\nLayout-model support:\n\n```bash\npip install \"layoutparser[layoutmodels]\"\npip install \"layoutparser[effdet]\"\npip install \"layoutparser[paddledetection]\"\n```\n\nDetectron2 still uses its own backend install path:\n\n```bash\npip install layoutparser torchvision\npip install \"detectron2@git+https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdetectron2.git@v0.5#egg=detectron2\"\n```\n\nFor local inspection from a checkout, prefer an isolated environment and an\neditable install in that private environment rather than mutating the source\nrepository.\n\nMinimal import checks:\n\n```bash\npython -c \"import layoutparser as lp; print(lp.__version__)\"\npython -c \"from layoutparser import Layout, Rectangle; print(Layout([Rectangle(0, 0, 10, 10)]))\"\n```\n\nIf backend availability is uncertain, run the bundled inspector:\n\n```bash\npython scripts\u002Finspect_backends.py\n```\n\nFor a local smoke check that stays inside synthetic data, use:\n\n```bash\npython scripts\u002Fsmoke_layoutparser_core.py\n```\n\n## Route map\n\n### `layout-objects`\nRead this for:\n\n- `Interval`, `Rectangle`, `Quadrilateral`, `TextBlock`, and `Layout`\n- coordinate transforms, padding, shifting, scaling, cropping\n- `union`, `intersect`, `relative_to`, `condition_on`, `is_in`\n- `Layout` sorting, filtering, serialization, and line\u002Fcategory grouping\n\n### `layout-io`\nRead this for:\n\n- `load_json`, `load_dict`, `load_csv`, `load_dataframe`, `load_pdf`\n- JSON\u002FCSV\u002FDataFrame round-trips and PDF token extraction\n- page metadata, `block_type`, and layout export\u002Fimport issues\n- COCO-style annotation conversion patterns\n\n### `visualization`\nRead this for:\n\n- `draw_box` and `draw_text`\n- color maps, alpha handling, font settings, vertical text, and layout overlays\n- turning detected or loaded layouts into readable page visuals\n\n### `layout-models`\nRead this for:\n\n- `AutoLayoutModel`\n- `Detectron2LayoutModel`, `EfficientDetLayoutModel`, and `PaddleDetectionLayoutModel`\n- `lp:\u002F\u002F` config parsing, model catalogs, label maps, and backend selection\n- model download, cache, and device-selection behavior\n\n### `ocr`\nRead this for:\n\n- `TesseractAgent`, `TesseractFeatureType`\n- `GCVAgent`, `GCVFeatureType`\n- OCR response parsing, saved-response loading, and text aggregation\n- credential and binary requirements for live OCR\n\n## Root references\n\n- Read `references\u002Fapi-reference.md` for the top-level public API map.\n- Read `references\u002Fworkflows.md` for cross-sub-skill document workflows.\n- Read `references\u002Frepo-provenance.md` before checking staleness or refreshing.\n- Read `references\u002Frepo-routing-metadata.json` only when verifying managed\n  repo-skills-router placement.\n\n## When to jump to troubleshooting\n\nRead `references\u002Ftroubleshooting.md` when you see any of these:\n\n- missing optional backend imports\n- `pkg_resources` \u002F setuptools issues around `google-cloud-vision==1`\n- `tesseract` or credential problems\n- `pdf2image` \u002F `poppler` problems\n- `InvalidShapeError`, `NotSupportedShapeError`, or layout validation errors\n- model download, cache, or `lp:\u002F\u002F` parsing failures\n\n## Notes for future agents\n\n- This skill is public runtime guidance; do not rely on the original checkout\n  remaining available.\n- Runtime links should stay inside this generated skill tree.\n- Use the sub-skill that matches the user’s primary workflow first, then cross-\n  reference the others when a task spans multiple layers.\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\u002Flayout-parser",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 layout-parser",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill layout-parser",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill layout-parser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002FSKILL.md",[47,53,57,61,65,69,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",2412,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1444,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",331,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5284,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fworkflows.md",2174,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Freferences\u002Fworkflows.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Finspect_backends.py","SCRIPT","脚本",3392,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Fscripts\u002Finspect_backends.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fsmoke_layoutparser_core.py",2632,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Fscripts\u002Fsmoke_layoutparser_core.py",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]