[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WCA2R2JNECTAA5SB7MHPV":3,"skill-same:01M78WCA2R2JNECTAA5SB7MHPV":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78WCA2R2JNECTAA5SB7MHPV","pipeline-configuration",null,"Configure Docling's standard PDF pipeline options, OCR engines, table structure recovery, accelerators, model artifacts, remote-service gates, and option validation.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pipeline-configuration\ndescription: \"Configure Docling's standard PDF pipeline options, OCR engines,\n  table structure recovery, accelerators, model artifacts, remote-service gates,\n  and option validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Pipeline Configuration\n\nUse this sub-skill when a task needs Docling PDF pipeline tuning rather than a simple conversion call.\n\n## Route Here For\n\n- Building `PdfPipelineOptions` or `ThreadedPdfPipelineOptions` for `InputFormat.PDF`.\n- Enabling\u002Fdisabling OCR, choosing OCR engines, setting OCR language lists, or forcing full-page OCR.\n- Tuning table structure extraction, especially `do_cell_matching` and `TableFormerMode`.\n- Selecting `AcceleratorOptions` device\u002Fthread settings for CPU, CUDA, MPS, or XPU.\n- Setting `artifacts_path`, `DOCLING_ARTIFACTS_PATH`, or `docling-tools models download` for prefetched model caches.\n- Diagnosing pipeline option validation, wrong option object placement, or `OperationNotAllowed` from remote-service components.\n\n## Route Elsewhere\n\n- Basic document conversion, export formats, `DocumentConverter.convert`, or `convert_string`: use the conversion sub-skill.\n- CLI flag syntax and supported input\u002Foutput formats: use the cli-and-formats sub-skill.\n- VLM, ASR, picture enrichment, code\u002Fformula, chart extraction, or other heavy enrichment workflows: use the advanced-pipelines sub-skill.\n\n## Core Pattern\n\n```python\nfrom docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions\nfrom docling.datamodel.base_models import InputFormat\nfrom docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode\nfrom docling.document_converter import DocumentConverter, PdfFormatOption\n\npipeline_options = PdfPipelineOptions()\npipeline_options.do_ocr = True\npipeline_options.ocr_options.lang = [\"en\"]\npipeline_options.do_table_structure = True\npipeline_options.table_structure_options.do_cell_matching = False\npipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE\npipeline_options.accelerator_options = AcceleratorOptions(\n    num_threads=4,\n    device=AcceleratorDevice.AUTO,\n)\n\nconverter = DocumentConverter(\n    format_options={\n        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)\n    }\n)\nresult = converter.convert(\"input.pdf\", max_num_pages=100, max_file_size=20 * 1024 * 1024)\n```\n\n## References\n\n- `references\u002Foptions-reference.md` for field names, defaults, and validated snippets.\n- `references\u002Focr-and-tables.md` for OCR engines and table recovery choices.\n- `references\u002Ftroubleshooting.md` for common pipeline failures and fixes.\n- `scripts\u002Finspect_pipeline_options.py` to print installed option fields\u002Fdefaults without opening source files.\n","# Pipeline Configuration\n\nUse this sub-skill when a task needs Docling PDF pipeline tuning rather than a simple conversion call.\n\n## Route Here For\n\n- Building `PdfPipelineOptions` or `ThreadedPdfPipelineOptions` for `InputFormat.PDF`.\n- Enabling\u002Fdisabling OCR, choosing OCR engines, setting OCR language lists, or forcing full-page OCR.\n- Tuning table structure extraction, especially `do_cell_matching` and `TableFormerMode`.\n- Selecting `AcceleratorOptions` device\u002Fthread settings for CPU, CUDA, MPS, or XPU.\n- Setting `artifacts_path`, `DOCLING_ARTIFACTS_PATH`, or `docling-tools models download` for prefetched model caches.\n- Diagnosing pipeline option validation, wrong option object placement, or `OperationNotAllowed` from remote-service components.\n\n## Route Elsewhere\n\n- Basic document conversion, export formats, `DocumentConverter.convert`, or `convert_string`: use the conversion sub-skill.\n- CLI flag syntax and supported input\u002Foutput formats: use the cli-and-formats sub-skill.\n- VLM, ASR, picture enrichment, code\u002Fformula, chart extraction, or other heavy enrichment workflows: use the advanced-pipelines sub-skill.\n\n## Core Pattern\n\n```python\nfrom docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions\nfrom docling.datamodel.base_models import InputFormat\nfrom docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode\nfrom docling.document_converter import DocumentConverter, PdfFormatOption\n\npipeline_options = PdfPipelineOptions()\npipeline_options.do_ocr = True\npipeline_options.ocr_options.lang = [\"en\"]\npipeline_options.do_table_structure = True\npipeline_options.table_structure_options.do_cell_matching = False\npipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE\npipeline_options.accelerator_options = AcceleratorOptions(\n    num_threads=4,\n    device=AcceleratorDevice.AUTO,\n)\n\nconverter = DocumentConverter(\n    format_options={\n        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)\n    }\n)\nresult = converter.convert(\"input.pdf\", max_num_pages=100, max_file_size=20 * 1024 * 1024)\n```\n\n## References\n\n- `references\u002Foptions-reference.md` for field names, defaults, and validated snippets.\n- `references\u002Focr-and-tables.md` for OCR engines and table recovery choices.\n- `references\u002Ftroubleshooting.md` for common pipeline failures and fixes.\n- `scripts\u002Finspect_pipeline_options.py` to print installed option fields\u002Fdefaults without opening source files.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-configuration",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-configuration",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-configuration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Focr-and-tables.md","REFERENCE","参考文档",4759,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002Freferences\u002Focr-and-tables.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Foptions-reference.md",5985,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002Freferences\u002Foptions-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4668,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_pipeline_options.py","SCRIPT","脚本",4340,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocling\u002Fsub-skills\u002Fpipeline-configuration\u002Fscripts\u002Finspect_pipeline_options.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]