[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WDCYS3RF6CD7PC33Q6XGS":3,"skill-same:01M78WDCYS3RF6CD7PC33Q6XGS":63},{"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},"01M78WDCYS3RF6CD7PC33Q6XGS","core-ocr-and-kie",null,"Run docTR end-to-end OCR and KIE inference with predictor APIs, rotation\u002Flayout\u002Ftable options, batching, devices, and output checks.","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\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: core-ocr-and-kie\ndescription: \"Run docTR end-to-end OCR and KIE inference with predictor APIs,\n  rotation\u002Flayout\u002Ftable options, batching, devices, and output checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# core-ocr-and-kie\n\nUse this sub-skill when the task is to run or debug docTR's Python end-to-end inference pipelines:\n\n- `doctr.io.DocumentFile` or a list of RGB NumPy pages -> `doctr.models.ocr_predictor(...)` -> `Document`.\n- `doctr.io.DocumentFile` or a list of RGB NumPy pages -> `doctr.models.kie_predictor(...)` -> `KIEDocument`.\n- Predictor-level flags for rotated\u002Fskewed pages, orientation\u002Flanguage detection, layout detection, table detection, ignored layout regions, batching, and device movement.\n- Sanity-checking output object shapes, page counts, geometry conventions, and the no-download\u002Frandom-weight caveat.\n\nDo **not** use this sub-skill for raw file loading\u002Fexport format details, model zoo catalogs\u002Fcustom weights\u002FONNX export, CLI wrappers, training, datasets, or evaluation scripts. Route those tasks to sibling sub-skills:\n\n- Document loading and result export\u002Frender details: [document-io-and-exports](..\u002Fdocument-io-and-exports\u002FSKILL.md)\n- Architecture catalogs, custom models, optimization, export, vocab whitelisting: [models-and-customization](..\u002Fmodels-and-customization\u002FSKILL.md)\n- `doctr-cli` and bundled command-line helpers: [cli-and-scripts](..\u002Fcli-and-scripts\u002FSKILL.md)\n- Datasets, training, metrics, and evaluation: [datasets-training-and-evaluation](..\u002Fdatasets-training-and-evaluation\u002FSKILL.md)\n\n## Read first\n\n1. For API recipes and option interactions, read [references\u002Focr-kie-workflows.md](references\u002Focr-kie-workflows.md).\n2. For failure diagnosis, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n3. For a safe import\u002Ffactory\u002Foptional-forward smoke check, run or adapt [scripts\u002Focr_api_smoke.py](scripts\u002Focr_api_smoke.py).\n\n## Operating rules\n\n- Prefer explicit `det_arch`, `reco_arch`, `pretrained`, `pretrained_backbone`, `assume_straight_pages`, and batch-size choices when reproducibility matters.\n- Treat `pretrained=False` as an API\u002Fshape smoke mode only; randomly initialized detection and recognition models do not produce useful OCR.\n- Be explicit about network\u002Fcache behavior: pretrained model weights and some orientation helpers may download on first use unless already cached or disabled.\n- Validate outputs before downstream use: `Document.pages` for OCR, `KIEDocument.pages[*].predictions` for KIE, optional `page.layout`, optional `page.tables`, and relative geometries.\n","# core-ocr-and-kie\n\nUse this sub-skill when the task is to run or debug docTR's Python end-to-end inference pipelines:\n\n- `doctr.io.DocumentFile` or a list of RGB NumPy pages -> `doctr.models.ocr_predictor(...)` -> `Document`.\n- `doctr.io.DocumentFile` or a list of RGB NumPy pages -> `doctr.models.kie_predictor(...)` -> `KIEDocument`.\n- Predictor-level flags for rotated\u002Fskewed pages, orientation\u002Flanguage detection, layout detection, table detection, ignored layout regions, batching, and device movement.\n- Sanity-checking output object shapes, page counts, geometry conventions, and the no-download\u002Frandom-weight caveat.\n\nDo **not** use this sub-skill for raw file loading\u002Fexport format details, model zoo catalogs\u002Fcustom weights\u002FONNX export, CLI wrappers, training, datasets, or evaluation scripts. Route those tasks to sibling sub-skills:\n\n- Document loading and result export\u002Frender details: [document-io-and-exports](..\u002Fdocument-io-and-exports\u002FSKILL.md)\n- Architecture catalogs, custom models, optimization, export, vocab whitelisting: [models-and-customization](..\u002Fmodels-and-customization\u002FSKILL.md)\n- `doctr-cli` and bundled command-line helpers: [cli-and-scripts](..\u002Fcli-and-scripts\u002FSKILL.md)\n- Datasets, training, metrics, and evaluation: [datasets-training-and-evaluation](..\u002Fdatasets-training-and-evaluation\u002FSKILL.md)\n\n## Read first\n\n1. For API recipes and option interactions, read [references\u002Focr-kie-workflows.md](references\u002Focr-kie-workflows.md).\n2. For failure diagnosis, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n3. For a safe import\u002Ffactory\u002Foptional-forward smoke check, run or adapt [scripts\u002Focr_api_smoke.py](scripts\u002Focr_api_smoke.py).\n\n## Operating rules\n\n- Prefer explicit `det_arch`, `reco_arch`, `pretrained`, `pretrained_backbone`, `assume_straight_pages`, and batch-size choices when reproducibility matters.\n- Treat `pretrained=False` as an API\u002Fshape smoke mode only; randomly initialized detection and recognition models do not produce useful OCR.\n- Be explicit about network\u002Fcache behavior: pretrained model weights and some orientation helpers may download on first use unless already cached or disabled.\n- Validate outputs before downstream use: `Document.pages` for OCR, `KIEDocument.pages[*].predictions` for KIE, optional `page.layout`, optional `page.tables`, and relative geometries.\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\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie",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 core-ocr-and-kie",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill core-ocr-and-kie",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill core-ocr-and-kie","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Focr-kie-workflows.md","REFERENCE","参考文档",12973,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie\u002Freferences\u002Focr-kie-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",9372,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Focr_api_smoke.py","SCRIPT","脚本",9083,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fcore-ocr-and-kie\u002Fscripts\u002Focr_api_smoke.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]