[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792DCK021AS7XRDJ5XDJT39":3,"skill-same:01M792DCK021AS7XRDJ5XDJT39":82},{"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},"01M792DCK021AS7XRDJ5XDJT39","paddlex",null,"Operate PaddleX 3.7.2 for low-code AI pipelines, module custom development, deployment, installation, and troubleshooting.","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\u002Fpaddlex\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: paddlex\ndescription: \"Operate PaddleX 3.7.2 for low-code AI pipelines, module custom\n  development, deployment, installation, and troubleshooting.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# PaddleX operating skill\n\nUse this skill when a task involves **PaddleX**, the PaddlePaddle low-code toolkit for pre-trained pipelines, model\u002Fmodule development, and deployment.\n\nThis skill is self-contained. Do not rely on the original PaddleX repository checkout while using it; use the bundled references and scripts here.\n\n## Route by user intent\n\n| User intent | Read |\n| --- | --- |\n| install PaddleX, verify imports, choose extras, or fix package setup | `references\u002Finstallation.md`, `references\u002Ftroubleshooting.md`, `scripts\u002Fcheck_paddlex_install.py` |\n| run a ready-made AI pipeline through Python or CLI | `sub-skills\u002Fpipelines\u002F` |\n| export\u002Fget\u002Fedit a pipeline config, set devices\u002Fengines, save pipeline outputs | `sub-skills\u002Fpipelines\u002F` |\n| use `create_model`, validate a dataset, train, evaluate, export, predict, or convert module weights | `sub-skills\u002Fmodules\u002F` |\n| deploy or accelerate a pipeline\u002Fmodel with HPI, serving, Paddle2ONNX, GenAI client\u002Fserver, or hardware-specific runtimes | `sub-skills\u002Fdeployment\u002F` |\n| decide whether this skill is stale for a new checkout | `references\u002Frepo-provenance.md` |\n\n## Core public entry points\n\nInstalled PaddleX 3.7.2 exports these high-value APIs:\n\n```python\nfrom paddlex import create_pipeline, create_predictor, create_model\nfrom paddlex import build_dataset_checker, build_trainer, build_evaluator\n```\n\nVerified signatures during construction:\n\n```text\ncreate_pipeline(pipeline=None, *, config=None, device=None, engine=None,\n                engine_config=None, pp_option=None, use_hpip=None,\n                hpi_config=None, **kwargs)\ncreate_predictor(model_name, *, model_dir=None, device=None, engine=None,\n                 engine_config=None, batch_size=1, pp_option=None,\n                 use_hpip=False, hpi_config=None, genai_config=None, **kwargs)\ncreate_model(model_name, model_dir=None, *args, **kwargs)\n```\n\nInstalled CLI entry points:\n\n```bash\npaddlex --help\npaddlex --pipeline image_classification --input demo.jpg --save_path output --device cpu\npaddlex --get_pipeline_config image_classification\npaddlex --serve --pipeline image_classification --host 0.0.0.0 --port 8080\npaddlex --paddle2onnx --paddle_model_dir .\u002Finference_model --onnx_model_dir .\u002Fonnx\npaddlex_genai_server --help\n```\n\n## Baseline install check\n\nAfter installing PaddlePaddle and PaddleX, run:\n\n```bash\npython scripts\u002Fcheck_paddlex_install.py\n```\n\nA healthy baseline shows PaddleX importable, a PaddlePaddle version, CLI entry points, and whether Paddle is CPU-only or GPU-enabled.\n\n## Common decision rules\n\n- Use **pipelines** for pre-trained pipeline inference and pipeline YAML orchestration.\n- Use **modules** for custom datasets, model configs, training\u002Fevaluation\u002Fexport, and `create_model`.\n- Use **deployment** only after the user asks for serving, acceleration, conversion, GenAI hosting, or hardware packaging.\n- CPU import success is not proof of GPU\u002FHPI\u002Faccelerator readiness. Verify the specific PaddlePaddle wheel, plugin, and backend.\n- Avoid full training, model downloads, server starts, or plugin installs until the user supplies data, runtime budget, and backend constraints.\n\n## Bundled references\n\n- `references\u002Finstallation.md` — install order, extras, PaddlePaddle wheel choice, plugins.\n- `references\u002Ftroubleshooting.md` — cross-cutting package\u002FCLI\u002Fdata\u002Fbackend problems.\n- `references\u002Fpipeline-catalog.md` — root summary of pipeline capabilities.\n- `references\u002Fmodule-overview.md` — root summary of module capabilities.\n- `references\u002Fdeployment-overview.md` — root summary of deployment capabilities.\n- `references\u002Frepo-provenance.md` — source commit\u002Fevidence\u002Fstaleness information.\n- `references\u002Frepo-routing-metadata.json` — router metadata for managed import.\n","# PaddleX operating skill\n\nUse this skill when a task involves **PaddleX**, the PaddlePaddle low-code toolkit for pre-trained pipelines, model\u002Fmodule development, and deployment.\n\nThis skill is self-contained. Do not rely on the original PaddleX repository checkout while using it; use the bundled references and scripts here.\n\n## Route by user intent\n\n| User intent | Read |\n| --- | --- |\n| install PaddleX, verify imports, choose extras, or fix package setup | `references\u002Finstallation.md`, `references\u002Ftroubleshooting.md`, `scripts\u002Fcheck_paddlex_install.py` |\n| run a ready-made AI pipeline through Python or CLI | `sub-skills\u002Fpipelines\u002F` |\n| export\u002Fget\u002Fedit a pipeline config, set devices\u002Fengines, save pipeline outputs | `sub-skills\u002Fpipelines\u002F` |\n| use `create_model`, validate a dataset, train, evaluate, export, predict, or convert module weights | `sub-skills\u002Fmodules\u002F` |\n| deploy or accelerate a pipeline\u002Fmodel with HPI, serving, Paddle2ONNX, GenAI client\u002Fserver, or hardware-specific runtimes | `sub-skills\u002Fdeployment\u002F` |\n| decide whether this skill is stale for a new checkout | `references\u002Frepo-provenance.md` |\n\n## Core public entry points\n\nInstalled PaddleX 3.7.2 exports these high-value APIs:\n\n```python\nfrom paddlex import create_pipeline, create_predictor, create_model\nfrom paddlex import build_dataset_checker, build_trainer, build_evaluator\n```\n\nVerified signatures during construction:\n\n```text\ncreate_pipeline(pipeline=None, *, config=None, device=None, engine=None,\n                engine_config=None, pp_option=None, use_hpip=None,\n                hpi_config=None, **kwargs)\ncreate_predictor(model_name, *, model_dir=None, device=None, engine=None,\n                 engine_config=None, batch_size=1, pp_option=None,\n                 use_hpip=False, hpi_config=None, genai_config=None, **kwargs)\ncreate_model(model_name, model_dir=None, *args, **kwargs)\n```\n\nInstalled CLI entry points:\n\n```bash\npaddlex --help\npaddlex --pipeline image_classification --input demo.jpg --save_path output --device cpu\npaddlex --get_pipeline_config image_classification\npaddlex --serve --pipeline image_classification --host 0.0.0.0 --port 8080\npaddlex --paddle2onnx --paddle_model_dir .\u002Finference_model --onnx_model_dir .\u002Fonnx\npaddlex_genai_server --help\n```\n\n## Baseline install check\n\nAfter installing PaddlePaddle and PaddleX, run:\n\n```bash\npython scripts\u002Fcheck_paddlex_install.py\n```\n\nA healthy baseline shows PaddleX importable, a PaddlePaddle version, CLI entry points, and whether Paddle is CPU-only or GPU-enabled.\n\n## Common decision rules\n\n- Use **pipelines** for pre-trained pipeline inference and pipeline YAML orchestration.\n- Use **modules** for custom datasets, model configs, training\u002Fevaluation\u002Fexport, and `create_model`.\n- Use **deployment** only after the user asks for serving, acceleration, conversion, GenAI hosting, or hardware packaging.\n- CPU import success is not proof of GPU\u002FHPI\u002Faccelerator readiness. Verify the specific PaddlePaddle wheel, plugin, and backend.\n- Avoid full training, model downloads, server starts, or plugin installs until the user supplies data, runtime budget, and backend constraints.\n\n## Bundled references\n\n- `references\u002Finstallation.md` — install order, extras, PaddlePaddle wheel choice, plugins.\n- `references\u002Ftroubleshooting.md` — cross-cutting package\u002FCLI\u002Fdata\u002Fbackend problems.\n- `references\u002Fpipeline-catalog.md` — root summary of pipeline capabilities.\n- `references\u002Fmodule-overview.md` — root summary of module capabilities.\n- `references\u002Fdeployment-overview.md` — root summary of deployment capabilities.\n- `references\u002Frepo-provenance.md` — source commit\u002Fevidence\u002Fstaleness information.\n- `references\u002Frepo-routing-metadata.json` — router metadata for managed import.\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\u002Fpaddlex",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 paddlex",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill paddlex",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill paddlex","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002FSKILL.md",[47,53,57,61,65,69,73,77],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdeployment-overview.md","REFERENCE","参考文档",874,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Fdeployment-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finstallation.md",3000,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Finstallation.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fmodule-overview.md",939,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Fmodule-overview.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fpipeline-catalog.md",854,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Fpipeline-catalog.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frepo-provenance.md",2336,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Frepo-provenance.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Frepo-routing-metadata.json",509,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Frepo-routing-metadata.json",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Ftroubleshooting.md",2905,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Freferences\u002Ftroubleshooting.md",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":75,"sourceHtmlUrl":81},"scripts\u002Fcheck_paddlex_install.py","SCRIPT","脚本","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlex\u002Fscripts\u002Fcheck_paddlex_install.py",[83,90,97,104,111,118],{"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},"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":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},"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":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},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"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",[],[]]