[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z287YAWC2SY3F1TM04BK7":3,"skill-same:01M78Z287YAWC2SY3F1TM04BK7":53},{"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},"01M78Z287YAWC2SY3F1TM04BK7","layout-objects",null,"Routes LayoutParser coordinate primitives, layout containers, shape operations, and layout-analysis helpers.","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\u002Fsub-skills\u002Flayout-objects\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: layout-objects\ndescription: \"Routes LayoutParser coordinate primitives, layout containers,\n  shape operations, and layout-analysis helpers.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Layout Objects\n\nUse this sub-skill for geometry-heavy LayoutParser tasks: coordinate\nconversion, padding, containment, serialization, sorting, and lightweight line\nor category grouping.\n\n## What belongs here\n\n- `Interval`, `Rectangle`, `Quadrilateral`, `TextBlock`, and `Layout`\n- relative\u002Fabsolute coordinate transforms\n- `pad`, `shift`, `scale`, `crop_image`\n- `union`, `intersect`, `is_in`, `condition_on`, `relative_to`\n- `to_dict`, `from_dict`, `to_dataframe`, `get_homogeneous_blocks`\n- `generalized_connected_component_analysis_1d`\n- `simple_line_detection`\n- `group_textblocks_based_on_category`\n\n## What does not belong here\n\n- JSON\u002FCSV\u002FPDF loading and export: use `layout-io`\n- `draw_box` \u002F `draw_text`: use `visualization`\n- OCR response parsing: use `ocr`\n- `lp:\u002F\u002F` model catalogs or model inference: use `layout-models`\n\n## Read these files\n\n- `references\u002Fguide.md` for the class, operation overview, and troubleshooting notes\n- `..\u002Flayout-io\u002FSKILL.md` when the task starts with files or PDFs\n- `..\u002Fvisualization\u002FSKILL.md` when the task ends with rendering\n\n## Fast path\n\n1. Identify the shape type on each block.\n2. Use the most specific conversion first (`Interval` ↔ `Rectangle` ↔\n   `Quadrilateral`).\n3. Use `Layout` batch methods for page-wide transforms.\n4. Keep `TextBlock` wrappers when the block also carries text or ids.\n5. Only approximate quadrilateral shape operations with `strict=False` when a\n   bounding-box approximation is acceptable.\n\n## Common user requests\n\n- \"Filter the left column\"\n- \"Convert boxes to rectangles\"\n- \"Union the regions\"\n- \"Check whether a token is inside a page block\"\n- \"Sort blocks by reading order\"\n- \"Group the text blocks by line or category\"\n- \"Round-trip a layout to dict or dataframe\"\n\n## Minimal smoke\n\nUse the bundled root smoke script when you only need to confirm the geometry\nlayer and serialization basics:\n\n```bash\npython ..\u002F..\u002Fscripts\u002Fsmoke_layoutparser_core.py\n```\n\n## Failure clues\n\n- `InvalidShapeError`: the chosen union\u002Fintersection is geometrically invalid.\n- `NotSupportedShapeError`: the operation would create a polygonal result that\n  LayoutParser cannot represent directly.\n- `ValueError` from `Layout(...)`: the input is not an iterable of blocks or is\n  already a `Layout` wrapper.\n- `ValueError` from `TextBlock.to_interval()`: the axis is missing.\n\n## Output discipline\n\nWhen answering, give the exact class names and coordinate assumptions that the\nfuture agent should use. If a block should be re-encoded as another shape,\nstate the destination shape explicitly so the user can follow the conversion.\n","# Layout Objects\n\nUse this sub-skill for geometry-heavy LayoutParser tasks: coordinate\nconversion, padding, containment, serialization, sorting, and lightweight line\nor category grouping.\n\n## What belongs here\n\n- `Interval`, `Rectangle`, `Quadrilateral`, `TextBlock`, and `Layout`\n- relative\u002Fabsolute coordinate transforms\n- `pad`, `shift`, `scale`, `crop_image`\n- `union`, `intersect`, `is_in`, `condition_on`, `relative_to`\n- `to_dict`, `from_dict`, `to_dataframe`, `get_homogeneous_blocks`\n- `generalized_connected_component_analysis_1d`\n- `simple_line_detection`\n- `group_textblocks_based_on_category`\n\n## What does not belong here\n\n- JSON\u002FCSV\u002FPDF loading and export: use `layout-io`\n- `draw_box` \u002F `draw_text`: use `visualization`\n- OCR response parsing: use `ocr`\n- `lp:\u002F\u002F` model catalogs or model inference: use `layout-models`\n\n## Read these files\n\n- `references\u002Fguide.md` for the class, operation overview, and troubleshooting notes\n- `..\u002Flayout-io\u002FSKILL.md` when the task starts with files or PDFs\n- `..\u002Fvisualization\u002FSKILL.md` when the task ends with rendering\n\n## Fast path\n\n1. Identify the shape type on each block.\n2. Use the most specific conversion first (`Interval` ↔ `Rectangle` ↔\n   `Quadrilateral`).\n3. Use `Layout` batch methods for page-wide transforms.\n4. Keep `TextBlock` wrappers when the block also carries text or ids.\n5. Only approximate quadrilateral shape operations with `strict=False` when a\n   bounding-box approximation is acceptable.\n\n## Common user requests\n\n- \"Filter the left column\"\n- \"Convert boxes to rectangles\"\n- \"Union the regions\"\n- \"Check whether a token is inside a page block\"\n- \"Sort blocks by reading order\"\n- \"Group the text blocks by line or category\"\n- \"Round-trip a layout to dict or dataframe\"\n\n## Minimal smoke\n\nUse the bundled root smoke script when you only need to confirm the geometry\nlayer and serialization basics:\n\n```bash\npython ..\u002F..\u002Fscripts\u002Fsmoke_layoutparser_core.py\n```\n\n## Failure clues\n\n- `InvalidShapeError`: the chosen union\u002Fintersection is geometrically invalid.\n- `NotSupportedShapeError`: the operation would create a polygonal result that\n  LayoutParser cannot represent directly.\n- `ValueError` from `Layout(...)`: the input is not an iterable of blocks or is\n  already a `Layout` wrapper.\n- `ValueError` from `TextBlock.to_interval()`: the axis is missing.\n\n## Output discipline\n\nWhen answering, give the exact class names and coordinate assumptions that the\nfuture agent should use. If a block should be re-encoded as another shape,\nstate the destination shape explicitly so the user can follow the conversion.\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\u002Fsub-skills\u002Flayout-objects",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-objects",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill layout-objects",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill layout-objects","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Fsub-skills\u002Flayout-objects\u002FSKILL.md",[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fguide.md","REFERENCE","参考文档",4013,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flayout-parser\u002Fsub-skills\u002Flayout-objects\u002Freferences\u002Fguide.md",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":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},"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":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},"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":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},"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":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},"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",[],[]]