[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F9RYK4278GPEQPMKAMMPFA":3,"skill-same:01M7F9RYK4278GPEQPMKAMMPFA":62},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F9RYK4278GPEQPMKAMMPFA","inference",null,"Routes HiFi-GAN wav-to-wav and mel-to-wav inference, checkpoint\u002Fconfig pairing, output naming, and smoke checks.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhifi-gan\u002Fsub-skills\u002Finference\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: \"inference\"\ndescription: \"Routes HiFi-GAN wav-to-wav and mel-to-wav inference,\n  checkpoint\u002Fconfig pairing, output naming, and smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# HiFi-GAN Inference\n\nUse this sub-skill when you need to synthesize waveforms with a trained HiFi-GAN generator.\n\n## Use this route for\n\n- Self-contained `scripts\u002Finfer_hifigan.py --mode wav` synthesis from a directory of input wavs.\n- Self-contained `scripts\u002Finfer_hifigan.py --mode mel` synthesis from a directory of mel `.npy` files.\n- Loading a generator checkpoint that sits beside its matching `config.json`.\n- Choosing input and output directories and understanding generated filename suffixes.\n- CPU\u002FGPU selection, checkpoint\u002Fconfig mismatch recovery, and synthetic smoke checks.\n\n## Do not use this route for\n\n- Training, fine-tuning, or checkpoint creation\u002Fresume. Use the training sub-skill instead.\n- Upstream text-to-mel generation. Prepare those mel files first, then return here.\n\n## Read first\n\n- [references\u002Froot-material.md](references\u002Froot-material.md)\n- [references\u002Fworkflows.md](references\u002Fworkflows.md)\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n\n## Bundled helpers\n\n- [scripts\u002Finfer_hifigan.py](scripts\u002Finfer_hifigan.py) — self-contained wav\u002Fmel inference entrypoint using bundled HiFi-GAN runtime source.\n- [scripts\u002Fmake_dummy_checkpoint.py](scripts\u002Fmake_dummy_checkpoint.py) — create a synthetic generator checkpoint from bundled source and copy or intentionally mismatch the paired `config.json`.\n- [scripts\u002Fmake_tiny_inference_fixtures.py](scripts\u002Fmake_tiny_inference_fixtures.py) — create tiny wav and mel fixtures for smoke tests and negative cases.\n- [scripts\u002Frun_inference_smoke.py](scripts\u002Frun_inference_smoke.py) — build the synthetic inputs and run both inference modes end to end.\n\n## Key contracts\n\n- `scripts\u002Finfer_hifigan.py` wraps the bundled `inference.py` and `inference_e2e.py`; both underlying paths read `config.json` from the checkpoint directory and do not accept a separate config flag.\n- The checkpoint must be a generator checkpoint dict with a `generator` entry. Training checkpoints named `do_########` are not valid inference inputs.\n- `scripts\u002Finfer_hifigan.py --mode wav` expects mono wav files, computes mels with the loaded config, and writes `\u003Cstem>_generated.wav`.\n- `scripts\u002Finfer_hifigan.py --mode mel` expects mel `.npy` files and writes `\u003Cstem>_generated_e2e.wav`.\n- Both scripts auto-select CUDA when `torch.cuda.is_available()` is true and fall back to CPU otherwise.\n- The bundled inference entrypoint ultimately runs code that iterates `os.listdir(...)` directly, so keep the input directory clean and populated only with the intended files.\n- Use the matching config family for the checkpoint. The skill bundles `config_v1.json`, `config_v2.json`, and `config_v3.json` under `..\u002F..\u002Fscripts\u002Fhifigan_runtime\u002Fconfigs\u002F`.\n\n## Known-good inspection environment\n\n- Verified inspection facts: `torch 2.3.1+cu121` imported on an NVIDIA A100-SXM4-40GB host; `torch.cuda.is_available()` returned true; `torch.cuda.get_device_name(0)` worked; `torch.utils.tensorboard` imported; `librosa.util.normalize` was present in `librosa 0.10.2.post1`.\n","# HiFi-GAN Inference\n\nUse this sub-skill when you need to synthesize waveforms with a trained HiFi-GAN generator.\n\n## Use this route for\n\n- Self-contained `scripts\u002Finfer_hifigan.py --mode wav` synthesis from a directory of input wavs.\n- Self-contained `scripts\u002Finfer_hifigan.py --mode mel` synthesis from a directory of mel `.npy` files.\n- Loading a generator checkpoint that sits beside its matching `config.json`.\n- Choosing input and output directories and understanding generated filename suffixes.\n- CPU\u002FGPU selection, checkpoint\u002Fconfig mismatch recovery, and synthetic smoke checks.\n\n## Do not use this route for\n\n- Training, fine-tuning, or checkpoint creation\u002Fresume. Use the training sub-skill instead.\n- Upstream text-to-mel generation. Prepare those mel files first, then return here.\n\n## Read first\n\n- [references\u002Froot-material.md](references\u002Froot-material.md)\n- [references\u002Fworkflows.md](references\u002Fworkflows.md)\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n\n## Bundled helpers\n\n- [scripts\u002Finfer_hifigan.py](scripts\u002Finfer_hifigan.py) — self-contained wav\u002Fmel inference entrypoint using bundled HiFi-GAN runtime source.\n- [scripts\u002Fmake_dummy_checkpoint.py](scripts\u002Fmake_dummy_checkpoint.py) — create a synthetic generator checkpoint from bundled source and copy or intentionally mismatch the paired `config.json`.\n- [scripts\u002Fmake_tiny_inference_fixtures.py](scripts\u002Fmake_tiny_inference_fixtures.py) — create tiny wav and mel fixtures for smoke tests and negative cases.\n- [scripts\u002Frun_inference_smoke.py](scripts\u002Frun_inference_smoke.py) — build the synthetic inputs and run both inference modes end to end.\n\n## Key contracts\n\n- `scripts\u002Finfer_hifigan.py` wraps the bundled `inference.py` and `inference_e2e.py`; both underlying paths read `config.json` from the checkpoint directory and do not accept a separate config flag.\n- The checkpoint must be a generator checkpoint dict with a `generator` entry. Training checkpoints named `do_########` are not valid inference inputs.\n- `scripts\u002Finfer_hifigan.py --mode wav` expects mono wav files, computes mels with the loaded config, and writes `\u003Cstem>_generated.wav`.\n- `scripts\u002Finfer_hifigan.py --mode mel` expects mel `.npy` files and writes `\u003Cstem>_generated_e2e.wav`.\n- Both scripts auto-select CUDA when `torch.cuda.is_available()` is true and fall back to CPU otherwise.\n- The bundled inference entrypoint ultimately runs code that iterates `os.listdir(...)` directly, so keep the input directory clean and populated only with the intended files.\n- Use the matching config family for the checkpoint. The skill bundles `config_v1.json`, `config_v2.json`, and `config_v3.json` under `..\u002F..\u002Fscripts\u002Fhifigan_runtime\u002Fconfigs\u002F`.\n\n## Known-good inspection environment\n\n- Verified inspection facts: `torch 2.3.1+cu121` imported on an NVIDIA A100-SXM4-40GB host; `torch.cuda.is_available()` returned true; `torch.cuda.get_device_name(0)` worked; `torch.utils.tensorboard` imported; `librosa.util.normalize` was present in `librosa 0.10.2.post1`.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fhifi-gan\u002Fsub-skills\u002Finference",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":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill inference",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill inference",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill inference","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\u002Fhifi-gan\u002Fsub-skills\u002Finference\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Froot-material.md","REFERENCE","参考文档",1827,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhifi-gan\u002Fsub-skills\u002Finference\u002Freferences\u002Froot-material.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Ftroubleshooting.md",3386,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhifi-gan\u002Fsub-skills\u002Finference\u002Freferences\u002Ftroubleshooting.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fworkflows.md",3048,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhifi-gan\u002Fsub-skills\u002Finference\u002Freferences\u002Fworkflows.md",[63,70,75,82,89,96],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":71,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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",[],[]]