[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDCY0NGWPCGPZGYASFSBBA":3,"skill-same:01M7FDCY0NGWPCGPZGYASFSBBA":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7FDCY0NGWPCGPZGYASFSBBA","wenet",null,"Use WeNet for ASR package transcription, data preparation, training and decoding recipes, model export, and production runtime deployment.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fwenet\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: wenet\ndescription: \"Use WeNet for ASR package transcription, data preparation,\n  training and decoding recipes, model export, and production runtime\n  deployment.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# WeNet Repo Skill\n\nUse this skill when the task involves WeNet, an end-to-end speech recognition\n(ASR) toolkit with package transcription, staged training recipes, model export,\nand production runtime deployment.\n\n## Quick install\u002Fimport check\n\nFor package transcription or API inspection, install WeNet in the target Python\nenvironment and verify imports:\n\n```bash\npython - \u003C\u003C'PY'\nimport wenet\nfrom wenet import load_model, load_feature, load_tokenizer\nprint(\"WeNet import OK\")\nPY\n```\n\nFor broader workflow checks, run the bundled environment checker:\n\n```bash\npython scripts\u002Fcheck_wenet_environment.py --device cpu\n```\n\nPrefer `device=cpu` for safe diagnostics. CUDA, NPU, OpenVINO, IPEX, BPU, XPU,\nmobile, and Triton\u002FTensorRT paths require target-specific dependencies and\nhardware.\n\n## Route by task\n\n| User task | Read |\n|---|---|\n| Transcribe one audio file with the installed `wenet` CLI\u002FAPI; load a built-in or local model; validate a model directory; debug package import\u002Fbackend selection. | [sub-skills\u002Fpackage-transcription\u002FSKILL.md](sub-skills\u002Fpackage-transcription\u002FSKILL.md) |\n| Build or validate `wav.scp`, `text`, raw\u002Fshard `data.list`, dictionaries, tokenizer resources, CMVN inputs, or custom ASR data layout. | [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md) |\n| Adapt staged recipes; train\u002Ffine-tune; resume checkpoints; average models; run offline recognition; compare decoding modes; compute WER\u002FCER; use LM\u002Fk2\u002Fcontext\u002FLoRA paths. | [sub-skills\u002Ftraining-and-decoding\u002FSKILL.md](sub-skills\u002Ftraining-and-decoding\u002FSKILL.md) |\n| Export a trained checkpoint\u002Fconfig to TorchScript\u002FJIT, quantized JIT, ONNX CPU\u002FGPU, IPEX, or Horizon BPU artifacts. | [sub-skills\u002Fmodel-export\u002FSKILL.md](sub-skills\u002Fmodel-export\u002FSKILL.md) |\n| Choose and prepare production runtime deployment for libtorch, ONNX Runtime, OpenVINO, Android\u002FiOS, web, Raspberry Pi, Triton\u002FTensorRT, IPEX, BPU, or XPU. | [sub-skills\u002Fruntime-deployment\u002FSKILL.md](sub-skills\u002Fruntime-deployment\u002FSKILL.md) |\n\n## Shared references and scripts\n\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n  cross-cutting installation, optional backend, artifact mismatch, network, and\n  long-job issues.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is current for a WeNet checkout.\n- `references\u002Frepo-routing-metadata.json` contains structured router metadata\n  for managed repo-skill importers.\n- Run [scripts\u002Fcheck_wenet_environment.py](scripts\u002Fcheck_wenet_environment.py)\n  to safely inspect package import and CPU\u002FCUDA\u002FNPU visibility.\n\n## Operating rules\n\n- Do not launch downloads, full training, shard packaging, CMVN over large\n  corpora, runtime builds, or services until the user approves network,\n  storage, hardware, port, and runtime cost.\n- Keep model artifacts together: `train.yaml`, checkpoint, `units.txt`,\n  tokenizer resources, optional `global_cmvn`, and export metadata must match.\n- Use the bundled scripts for safe validation; use WeNet's installed package or\n  module entry points for real workflows in the user's environment.\n- When a workflow spans multiple stages, validate data first, then train\u002Fdecode,\n  then export, then deploy.\n","# WeNet Repo Skill\n\nUse this skill when the task involves WeNet, an end-to-end speech recognition\n(ASR) toolkit with package transcription, staged training recipes, model export,\nand production runtime deployment.\n\n## Quick install\u002Fimport check\n\nFor package transcription or API inspection, install WeNet in the target Python\nenvironment and verify imports:\n\n```bash\npython - \u003C\u003C'PY'\nimport wenet\nfrom wenet import load_model, load_feature, load_tokenizer\nprint(\"WeNet import OK\")\nPY\n```\n\nFor broader workflow checks, run the bundled environment checker:\n\n```bash\npython scripts\u002Fcheck_wenet_environment.py --device cpu\n```\n\nPrefer `device=cpu` for safe diagnostics. CUDA, NPU, OpenVINO, IPEX, BPU, XPU,\nmobile, and Triton\u002FTensorRT paths require target-specific dependencies and\nhardware.\n\n## Route by task\n\n| User task | Read |\n|---|---|\n| Transcribe one audio file with the installed `wenet` CLI\u002FAPI; load a built-in or local model; validate a model directory; debug package import\u002Fbackend selection. | [sub-skills\u002Fpackage-transcription\u002FSKILL.md](sub-skills\u002Fpackage-transcription\u002FSKILL.md) |\n| Build or validate `wav.scp`, `text`, raw\u002Fshard `data.list`, dictionaries, tokenizer resources, CMVN inputs, or custom ASR data layout. | [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md) |\n| Adapt staged recipes; train\u002Ffine-tune; resume checkpoints; average models; run offline recognition; compare decoding modes; compute WER\u002FCER; use LM\u002Fk2\u002Fcontext\u002FLoRA paths. | [sub-skills\u002Ftraining-and-decoding\u002FSKILL.md](sub-skills\u002Ftraining-and-decoding\u002FSKILL.md) |\n| Export a trained checkpoint\u002Fconfig to TorchScript\u002FJIT, quantized JIT, ONNX CPU\u002FGPU, IPEX, or Horizon BPU artifacts. | [sub-skills\u002Fmodel-export\u002FSKILL.md](sub-skills\u002Fmodel-export\u002FSKILL.md) |\n| Choose and prepare production runtime deployment for libtorch, ONNX Runtime, OpenVINO, Android\u002FiOS, web, Raspberry Pi, Triton\u002FTensorRT, IPEX, BPU, or XPU. | [sub-skills\u002Fruntime-deployment\u002FSKILL.md](sub-skills\u002Fruntime-deployment\u002FSKILL.md) |\n\n## Shared references and scripts\n\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n  cross-cutting installation, optional backend, artifact mismatch, network, and\n  long-job issues.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is current for a WeNet checkout.\n- `references\u002Frepo-routing-metadata.json` contains structured router metadata\n  for managed repo-skill importers.\n- Run [scripts\u002Fcheck_wenet_environment.py](scripts\u002Fcheck_wenet_environment.py)\n  to safely inspect package import and CPU\u002FCUDA\u002FNPU visibility.\n\n## Operating rules\n\n- Do not launch downloads, full training, shard packaging, CMVN over large\n  corpora, runtime builds, or services until the user approves network,\n  storage, hardware, port, and runtime cost.\n- Keep model artifacts together: `train.yaml`, checkpoint, `units.txt`,\n  tokenizer resources, optional `global_cmvn`, and export metadata must match.\n- Use the bundled scripts for safe validation; use WeNet's installed package or\n  module entry points for real workflows in the user's environment.\n- When a workflow spans multiple stages, validate data first, then train\u002Fdecode,\n  then export, then deploy.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fwenet",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill wenet",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill wenet",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill wenet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fwenet\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2150,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fwenet\u002Freferences\u002Frepo-provenance.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-routing-metadata.json",506,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fwenet\u002Freferences\u002Frepo-routing-metadata.json",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",2306,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fwenet\u002Freferences\u002Ftroubleshooting.md",[64,72,77,84,91,98],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]