[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z1SP09JFMAZ2VSF369YXN":3,"skill-same:01M78Z1SP09JFMAZ2VSF369YXN":74},{"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},"01M78Z1SP09JFMAZ2VSF369YXN","ocr-inference",null,"Guides pix2tex CLI and Python OCR inference from equation images to LaTeX, including images, checkpoints, CPU\u002FCUDA choices, and prediction troubleshooting.","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\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ocr-inference\ndescription: \"Guides pix2tex CLI and Python OCR inference from equation images\n  to LaTeX, including images, checkpoints, CPU\u002FCUDA choices, and prediction\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# OCR Inference\n\nUse this sub-skill when the user wants LaTeX code from an equation image, wants\nto call `pix2tex` or `LatexOCR`, or needs to debug inference quality, model\ncheckpoints, image preprocessing, or CLI flags.\n\n## Quick Route\n\n1. For the Python class and helper signatures, read\n   [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n2. For CLI commands and flags, read\n   [references\u002Fcli-reference.md](references\u002Fcli-reference.md).\n3. For image size\u002Fmode\u002Fpreprocessing decisions, read\n   [references\u002Fimage-preprocessing.md](references\u002Fimage-preprocessing.md).\n4. For common failures, read\n   [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. Before loading model weights, run\n   [scripts\u002Fcheck_pix2tex_cli.py](scripts\u002Fcheck_pix2tex_cli.py) and, for a\n   local image, [scripts\u002Finspect_pix2tex_image.py](scripts\u002Finspect_pix2tex_image.py).\n\n## Standard CLI Workflow\n\n```bash\npix2tex --no-cuda path\u002Fto\u002Fequation.png\n```\n\nUse `--no-cuda` for CPU-only environments or deterministic smoke tests. Omit it\nonly after verifying CUDA PyTorch in the target environment. Add `--no-resize`\nwhen you do not want the auxiliary image-resizer model to adjust image width.\nUse `-t\u002F--temperature` to control sampling; lower values make repeated\npredictions less variable.\n\n## Standard Python Workflow\n\n```python\nfrom PIL import Image\nfrom pix2tex.cli import LatexOCR\n\nmodel = LatexOCR()  # may download checkpoints if missing\nlatex = model(Image.open(\"equation.png\"))\nprint(latex)\n```\n\nInstantiate `LatexOCR()` only when checkpoint downloads and compute are allowed.\nFor CPU-only use, pass an argparse-like object or CLI route with `no_cuda=True`.\n\n## Boundaries\n\n- For GUI screenshot workflows or API serving, use\n  [..\u002Finteractive-apps-and-api\u002FSKILL.md](..\u002Finteractive-apps-and-api\u002FSKILL.md).\n- For dataset creation, formula rendering, or scraping, use\n  [..\u002Fdata-preparation\u002FSKILL.md](..\u002Fdata-preparation\u002FSKILL.md).\n- For training\u002Fevaluation or model architecture details, use\n  [..\u002Ftraining-and-evaluation\u002FSKILL.md](..\u002Ftraining-and-evaluation\u002FSKILL.md).\n","# OCR Inference\n\nUse this sub-skill when the user wants LaTeX code from an equation image, wants\nto call `pix2tex` or `LatexOCR`, or needs to debug inference quality, model\ncheckpoints, image preprocessing, or CLI flags.\n\n## Quick Route\n\n1. For the Python class and helper signatures, read\n   [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n2. For CLI commands and flags, read\n   [references\u002Fcli-reference.md](references\u002Fcli-reference.md).\n3. For image size\u002Fmode\u002Fpreprocessing decisions, read\n   [references\u002Fimage-preprocessing.md](references\u002Fimage-preprocessing.md).\n4. For common failures, read\n   [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. Before loading model weights, run\n   [scripts\u002Fcheck_pix2tex_cli.py](scripts\u002Fcheck_pix2tex_cli.py) and, for a\n   local image, [scripts\u002Finspect_pix2tex_image.py](scripts\u002Finspect_pix2tex_image.py).\n\n## Standard CLI Workflow\n\n```bash\npix2tex --no-cuda path\u002Fto\u002Fequation.png\n```\n\nUse `--no-cuda` for CPU-only environments or deterministic smoke tests. Omit it\nonly after verifying CUDA PyTorch in the target environment. Add `--no-resize`\nwhen you do not want the auxiliary image-resizer model to adjust image width.\nUse `-t\u002F--temperature` to control sampling; lower values make repeated\npredictions less variable.\n\n## Standard Python Workflow\n\n```python\nfrom PIL import Image\nfrom pix2tex.cli import LatexOCR\n\nmodel = LatexOCR()  # may download checkpoints if missing\nlatex = model(Image.open(\"equation.png\"))\nprint(latex)\n```\n\nInstantiate `LatexOCR()` only when checkpoint downloads and compute are allowed.\nFor CPU-only use, pass an argparse-like object or CLI route with `no_cuda=True`.\n\n## Boundaries\n\n- For GUI screenshot workflows or API serving, use\n  [..\u002Finteractive-apps-and-api\u002FSKILL.md](..\u002Finteractive-apps-and-api\u002FSKILL.md).\n- For dataset creation, formula rendering, or scraping, use\n  [..\u002Fdata-preparation\u002FSKILL.md](..\u002Fdata-preparation\u002FSKILL.md).\n- For training\u002Fevaluation or model architecture details, use\n  [..\u002Ftraining-and-evaluation\u002FSKILL.md](..\u002Ftraining-and-evaluation\u002FSKILL.md).\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference",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 ocr-inference",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill ocr-inference",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill ocr-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",2164,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcli-reference.md",1379,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Freferences\u002Fcli-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fimage-preprocessing.md",1423,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Freferences\u002Fimage-preprocessing.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",1414,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_pix2tex_cli.py","SCRIPT","脚本",2063,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Fscripts\u002Fcheck_pix2tex_cli.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Finspect_pix2tex_image.py",2510,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flatex-ocr\u002Fsub-skills\u002Focr-inference\u002Fscripts\u002Finspect_pix2tex_image.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]