[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FCJA9YM9BXWHX6DGS2Q2MF":3,"skill-same:01M7FCJA9YM9BXWHX6DGS2Q2MF":66},{"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},"01M7FCJA9YM9BXWHX6DGS2Q2MF","tacotron",null,"Guides the legacy TensorFlow 1.x Tacotron repository for text normalization, speech-data preprocessing, Tacotron graph inspection, training, checkpoint synthesis, evaluation, and the Falcon demo server.","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\u002Ftacotron\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: tacotron\ndescription: \"Guides the legacy TensorFlow 1.x Tacotron repository for text\n  normalization, speech-data preprocessing, Tacotron graph inspection, training,\n  checkpoint synthesis, evaluation, and the Falcon demo server.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Tacotron\n\nUse this skill for the original `keithito\u002Ftacotron`-style implementation of\nTacotron speech synthesis in TensorFlow 1.x. It is a repository workflow skill,\nnot a modern TensorFlow 2 or Tacotron 2 guide. Keep the original model's\ncheckpoint, hyperparameters, text cleaners, and spectrogram conventions\nconsistent across preprocessing, training, and synthesis.\n\n## First route\n\n- **Text cleaning, number expansion, symbols, ARPAbet, or CMUDict:** read\n  [`text-normalization`](sub-skills\u002Ftext-normalization\u002FSKILL.md).\n- **LJ Speech\u002FBlizzard layout, preprocessing, or custom data conversion:** read\n  [`data-preparation`](sub-skills\u002Fdata-preparation\u002FSKILL.md).\n- **Graph shapes, CBHG\u002Fprenet\u002Fattention internals, or audio dimensions:** read\n  [`model-architecture`](sub-skills\u002Fmodel-architecture\u002FSKILL.md).\n- **Training commands, hparams, checkpoints, TensorBoard, or loss recovery:**\n  read [`training`](sub-skills\u002Ftraining\u002FSKILL.md).\n- **Checkpoint WAV synthesis, batch evaluation, or HTTP serving:** read\n  [`synthesis-serving`](sub-skills\u002Fsynthesis-serving\u002FSKILL.md).\n\nFor a request spanning routes, use data-preparation → training →\nsynthesis-serving, and use text-normalization whenever the cleaner or symbol\ncontract changes.\n\n## Runtime contract\n\nThe repository is not packaged with `setup.py`, `setup.cfg`, or `pyproject.toml`.\nUse an isolated legacy Python environment and run repository entry points from a\nTacotron checkout. The documented requirements omit TensorFlow; install a\nTensorFlow 1.x build compatible with the platform. TensorFlow 1.15.5 with\nPython 3.6 was verified for inspection, together with the pinned audio\u002Ftext\ndependencies, but newer Python\u002FTensorFlow combinations are not automatically\ncompatible with `tf.contrib`.\n\nUse explicit roots in command examples; replace these two assignments only when\nthe checkout is stored elsewhere:\n\n```bash\nSKILL_ROOT=\u002Fpath\u002Fto\u002Ftacotron-skill\nCHECKOUT_ROOT=\u002Fpath\u002Fto\u002Ftacotron-checkout\n```\n\nBundled command builders run from `SKILL_ROOT` and print a command prefixed by\n`cd \"$CHECKOUT_ROOT\"`. Native preprocessing, training, evaluation, and serving\nmust therefore run with the checkout as their cwd; a skill directory is not a\nsource checkout. The skill's audio path uses the repository's `librosa`\u002FSciPy\nhelpers and built-in Griffin-Lim reconstruction. It does not bundle or require\na neural vocoder, but real WAV input is required for preprocessing and a real\ncheckpoint is required for synthesis.\n\n```bash\ncd \"$CHECKOUT_ROOT\"\npython -m pip install -r requirements.txt\n# Select a platform-compatible TensorFlow 1.x package; do not use TensorFlow 2.x.\npython -c \"import tensorflow as tf; print(tf.__version__); print(hasattr(tf, 'contrib'))\"\n```\n\nThe repository's requirements pin old versions. If modern package resolution\nbreaks `scipy`, `librosa`, or `numba`, follow the compatibility notes in\n[`references\u002Finstallation.md`](references\u002Finstallation.md) rather than\nblindly upgrading all dependencies.\n\n## Verification boundary\n\nThe bundled text, metadata, fixture, environment, shape, and command helpers\nare offline or dry-run checks. They do not prove real audio decoding,\nspectrogram quality, checkpoint compatibility, generated WAV quality, GPU\nperformance, full preprocessing, training convergence, or server security.\nFull training and checkpoint synthesis need external data\u002Fcheckpoints and can\nbe expensive. Use the bundled builders and validators before starting them.\n\n## Shared invariants\n\n- The default sample rate is 20 kHz; audio uses 80 mel channels, 1025 linear\n  frequency bins, 50 ms windows, and 12.5 ms frame shifts.\n- `outputs_per_step=5` and `max_iters=200` affect both training and synthesis;\n  use the same relevant hparams at both times.\n- Preprocessing writes time-major `.npy` spectrogram arrays and `train.txt`\n  rows with two filenames, frame count, and text. Validate this before training.\n- Text conversion appends the `~` EOS symbol. Cleaner names and ARPAbet syntax\n  must be available in both training and inference environments.\n- Full training and checkpoint synthesis need real datasets\u002Fcheckpoints and can\n  be expensive. Use the bundled builders and validators before starting them.\n\nRead [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\ncross-cutting TensorFlow-version, dependency, path, checkpoint, and audio\nfailure handling. Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md)\nbefore deciding whether this skill is stale for a changed checkout.\n","# Tacotron\n\nUse this skill for the original `keithito\u002Ftacotron`-style implementation of\nTacotron speech synthesis in TensorFlow 1.x. It is a repository workflow skill,\nnot a modern TensorFlow 2 or Tacotron 2 guide. Keep the original model's\ncheckpoint, hyperparameters, text cleaners, and spectrogram conventions\nconsistent across preprocessing, training, and synthesis.\n\n## First route\n\n- **Text cleaning, number expansion, symbols, ARPAbet, or CMUDict:** read\n  [`text-normalization`](sub-skills\u002Ftext-normalization\u002FSKILL.md).\n- **LJ Speech\u002FBlizzard layout, preprocessing, or custom data conversion:** read\n  [`data-preparation`](sub-skills\u002Fdata-preparation\u002FSKILL.md).\n- **Graph shapes, CBHG\u002Fprenet\u002Fattention internals, or audio dimensions:** read\n  [`model-architecture`](sub-skills\u002Fmodel-architecture\u002FSKILL.md).\n- **Training commands, hparams, checkpoints, TensorBoard, or loss recovery:**\n  read [`training`](sub-skills\u002Ftraining\u002FSKILL.md).\n- **Checkpoint WAV synthesis, batch evaluation, or HTTP serving:** read\n  [`synthesis-serving`](sub-skills\u002Fsynthesis-serving\u002FSKILL.md).\n\nFor a request spanning routes, use data-preparation → training →\nsynthesis-serving, and use text-normalization whenever the cleaner or symbol\ncontract changes.\n\n## Runtime contract\n\nThe repository is not packaged with `setup.py`, `setup.cfg`, or `pyproject.toml`.\nUse an isolated legacy Python environment and run repository entry points from a\nTacotron checkout. The documented requirements omit TensorFlow; install a\nTensorFlow 1.x build compatible with the platform. TensorFlow 1.15.5 with\nPython 3.6 was verified for inspection, together with the pinned audio\u002Ftext\ndependencies, but newer Python\u002FTensorFlow combinations are not automatically\ncompatible with `tf.contrib`.\n\nUse explicit roots in command examples; replace these two assignments only when\nthe checkout is stored elsewhere:\n\n```bash\nSKILL_ROOT=\u002Fpath\u002Fto\u002Ftacotron-skill\nCHECKOUT_ROOT=\u002Fpath\u002Fto\u002Ftacotron-checkout\n```\n\nBundled command builders run from `SKILL_ROOT` and print a command prefixed by\n`cd \"$CHECKOUT_ROOT\"`. Native preprocessing, training, evaluation, and serving\nmust therefore run with the checkout as their cwd; a skill directory is not a\nsource checkout. The skill's audio path uses the repository's `librosa`\u002FSciPy\nhelpers and built-in Griffin-Lim reconstruction. It does not bundle or require\na neural vocoder, but real WAV input is required for preprocessing and a real\ncheckpoint is required for synthesis.\n\n```bash\ncd \"$CHECKOUT_ROOT\"\npython -m pip install -r requirements.txt\n# Select a platform-compatible TensorFlow 1.x package; do not use TensorFlow 2.x.\npython -c \"import tensorflow as tf; print(tf.__version__); print(hasattr(tf, 'contrib'))\"\n```\n\nThe repository's requirements pin old versions. If modern package resolution\nbreaks `scipy`, `librosa`, or `numba`, follow the compatibility notes in\n[`references\u002Finstallation.md`](references\u002Finstallation.md) rather than\nblindly upgrading all dependencies.\n\n## Verification boundary\n\nThe bundled text, metadata, fixture, environment, shape, and command helpers\nare offline or dry-run checks. They do not prove real audio decoding,\nspectrogram quality, checkpoint compatibility, generated WAV quality, GPU\nperformance, full preprocessing, training convergence, or server security.\nFull training and checkpoint synthesis need external data\u002Fcheckpoints and can\nbe expensive. Use the bundled builders and validators before starting them.\n\n## Shared invariants\n\n- The default sample rate is 20 kHz; audio uses 80 mel channels, 1025 linear\n  frequency bins, 50 ms windows, and 12.5 ms frame shifts.\n- `outputs_per_step=5` and `max_iters=200` affect both training and synthesis;\n  use the same relevant hparams at both times.\n- Preprocessing writes time-major `.npy` spectrogram arrays and `train.txt`\n  rows with two filenames, frame count, and text. Validate this before training.\n- Text conversion appends the `~` EOS symbol. Cleaner names and ARPAbet syntax\n  must be available in both training and inference environments.\n- Full training and checkpoint synthesis need real datasets\u002Fcheckpoints and can\n  be expensive. Use the bundled builders and validators before starting them.\n\nRead [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\ncross-cutting TensorFlow-version, dependency, path, checkpoint, and audio\nfailure handling. Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md)\nbefore deciding whether this skill is stale for a changed checkout.\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\u002Ftacotron",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 tacotron",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill tacotron",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill tacotron","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\u002Ftacotron\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Finstallation.md","REFERENCE","参考文档",2220,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftacotron\u002Freferences\u002Finstallation.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",1729,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftacotron\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",318,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftacotron\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",2412,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftacotron\u002Freferences\u002Ftroubleshooting.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]