[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WDKEE5WSFYWFSZ8Q2BDVC":3,"skill-same:01M78WDKEE5WSFYWFSZ8Q2BDVC":61},{"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},"01M78WDKEE5WSFYWFSZ8Q2BDVC","deployment-and-contrib",null,"Use docTR deployment templates, demo surfaces, contrib utilities, Docker images, optional extras, and Hugging Face Hub workflows safely.","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\u002Fdeployment-and-contrib\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deployment-and-contrib\ndescription: \"Use docTR deployment templates, demo surfaces, contrib utilities,\n  Docker images, optional extras, and Hugging Face Hub workflows safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# deployment-and-contrib\n\nUse this sub-skill when a docTR task is about an optional surface around the core OCR package rather than a plain `DocumentFile -> predictor -> result` workflow:\n\n- exposing OCR\u002FKIE through a FastAPI service;\n- adapting the Streamlit demo flow;\n- choosing Docker images or Docker GPU settings;\n- installing or debugging optional `html`, `viz`, or `contrib` extras;\n- using `doctr.contrib.ArtefactDetector`;\n- loading from or sharing to the Hugging Face Hub.\n\nStart by deciding whether the user actually needs a service\u002Fdemo. For scripts, notebooks, batch jobs, or one-off research experiments, route them to the package API sub-skills instead of starting a long-lived service.\n\n## Read order\n\n1. For API, demo, and Docker deployment shape, read [references\u002Fapi-and-demo.md](references\u002Fapi-and-demo.md).\n2. For optional extras, `ArtefactDetector`, and Hugging Face Hub loading\u002Fpushing, read [references\u002Fcontrib-and-hub.md](references\u002Fcontrib-and-hub.md).\n3. For missing extras, MIME\u002Froute errors, GPU\u002FDocker issues, and Hub authentication failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Route away\n\n- Use the core OCR\u002FKIE sub-skill for normal `ocr_predictor`\u002F`kie_predictor` Python API work, predictor parameters, batching, and result interpretation.\n- Use the document IO\u002Fexport sub-skill for `DocumentFile`, HTML input, visualization\u002Fexport methods, and output object semantics.\n- Use the models\u002Fcustomization sub-skill for architecture selection, model factories, ONNX export, precision\u002Fcompile\u002Fdevice optimization, and custom weights outside Hub packaging.\n- Use the CLI\u002Fscripts sub-skill for installed `doctr-cli` and bundled batch helpers.\n- Use the datasets\u002Ftraining sub-skill before Hub publishing when the model still needs training, evaluation, or artifact validation.\n\n## Safety boundaries\n\n- Do not start a web server, Streamlit app, Docker container, browser session, interactive Hub login, or Hub push unless the user explicitly asks for that side effect.\n- Do not ask for, echo, save, or invent credentials. If a Hub operation needs authentication, stop and ask the user to provide an already-configured token\u002Fsession or to approve an interactive login.\n- Do not claim full service, Docker, GPU, or Hub verification from static inspection alone. Treat the recipes here as deployment guidance until the requested runtime check is actually run.\n- Keep service ports, file-size limits, authentication, concurrency, and model cache behavior explicit when moving from a demo\u002Ftemplate to production.\n","# deployment-and-contrib\n\nUse this sub-skill when a docTR task is about an optional surface around the core OCR package rather than a plain `DocumentFile -> predictor -> result` workflow:\n\n- exposing OCR\u002FKIE through a FastAPI service;\n- adapting the Streamlit demo flow;\n- choosing Docker images or Docker GPU settings;\n- installing or debugging optional `html`, `viz`, or `contrib` extras;\n- using `doctr.contrib.ArtefactDetector`;\n- loading from or sharing to the Hugging Face Hub.\n\nStart by deciding whether the user actually needs a service\u002Fdemo. For scripts, notebooks, batch jobs, or one-off research experiments, route them to the package API sub-skills instead of starting a long-lived service.\n\n## Read order\n\n1. For API, demo, and Docker deployment shape, read [references\u002Fapi-and-demo.md](references\u002Fapi-and-demo.md).\n2. For optional extras, `ArtefactDetector`, and Hugging Face Hub loading\u002Fpushing, read [references\u002Fcontrib-and-hub.md](references\u002Fcontrib-and-hub.md).\n3. For missing extras, MIME\u002Froute errors, GPU\u002FDocker issues, and Hub authentication failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Route away\n\n- Use the core OCR\u002FKIE sub-skill for normal `ocr_predictor`\u002F`kie_predictor` Python API work, predictor parameters, batching, and result interpretation.\n- Use the document IO\u002Fexport sub-skill for `DocumentFile`, HTML input, visualization\u002Fexport methods, and output object semantics.\n- Use the models\u002Fcustomization sub-skill for architecture selection, model factories, ONNX export, precision\u002Fcompile\u002Fdevice optimization, and custom weights outside Hub packaging.\n- Use the CLI\u002Fscripts sub-skill for installed `doctr-cli` and bundled batch helpers.\n- Use the datasets\u002Ftraining sub-skill before Hub publishing when the model still needs training, evaluation, or artifact validation.\n\n## Safety boundaries\n\n- Do not start a web server, Streamlit app, Docker container, browser session, interactive Hub login, or Hub push unless the user explicitly asks for that side effect.\n- Do not ask for, echo, save, or invent credentials. If a Hub operation needs authentication, stop and ask the user to provide an already-configured token\u002Fsession or to approve an interactive login.\n- Do not claim full service, Docker, GPU, or Hub verification from static inspection alone. Treat the recipes here as deployment guidance until the requested runtime check is actually run.\n- Keep service ports, file-size limits, authentication, concurrency, and model cache behavior explicit when moving from a demo\u002Ftemplate to production.\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\u002Fdeployment-and-contrib",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 deployment-and-contrib",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-and-contrib",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-and-contrib","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fdeployment-and-contrib\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-and-demo.md","REFERENCE","参考文档",7926,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fdeployment-and-contrib\u002Freferences\u002Fapi-and-demo.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcontrib-and-hub.md",7569,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fdeployment-and-contrib\u002Freferences\u002Fcontrib-and-hub.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7863,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdoctr\u002Fsub-skills\u002Fdeployment-and-contrib\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]