[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDGPZ68GREQ5PS6EAC43XD":3,"skill-same:01M7FDGPZ68GREQ5PS6EAC43XD":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},"01M7FDGPZ68GREQ5PS6EAC43XD","inference-and-export",null,"Run zi2zi checkpoint inference, style interpolation, transition GIF planning, and generator-only export from legacy TensorFlow 1.x checkpoints.","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\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: inference-and-export\ndescription: \"Run zi2zi checkpoint inference, style interpolation, transition\n  GIF planning, and generator-only export from legacy TensorFlow 1.x\n  checkpoints.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# zi2zi inference and export\n\nUse this sub-skill when a task is about generating glyphs from a trained zi2zi\ncheckpoint, interpolating between style labels, creating frame sequences or a\nGIF, or exporting generator-only variables for later reuse. It does not launch\nlong inference jobs automatically; it explains the checkpoint contract and\nprints safe command templates.\n\n## Use this sub-skill when\n\n- The user has a checkpoint directory and wants generated glyphs.\n- The task mentions `infer.py`, `export.py`, `model_dir`, `source_obj`,\n  `embedding_ids`, `interpolate`, `steps`, `output_gif`, `uroboros`, or exported\n  generator weights.\n- The user wants to know how inference chooses between single-style generation\n  and random style selection.\n- The user needs to diagnose checkpoint restore failures, output-image naming,\n  or interpolation problems.\n\n## Route elsewhere\n\n- Data rendering and `.obj` packaging go to\n  [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n- Training, fine-tuning, or label shuffling go to\n  [training-and-model](..\u002Ftraining-and-model\u002FSKILL.md).\n- Compatibility questions go to the root [compatibility](..\u002F..\u002Freferences\u002Fcompatibility.md)\n  reference.\n\n## Core inference facts\n\n- `infer.py` restores generator variables from a checkpoint and uses a source\n  object file to provide images.\n- If `embedding_ids` contains one integer, the model uses that style for every\n  source image. If it contains multiple IDs, the script picks randomly from the\n  list for each batch.\n- `interpolate=1` asks the model to linearly interpolate between style vectors.\n  With `uroboros=1`, the interpolation path closes the loop by appending the\n  first ID to the end of the chain.\n- `output_gif` triggers GIF compilation from the rendered interpolation frames.\n- `export.py` saves generator-only variables, which include the embedding table\n  and generator weights.\n\n## Output conventions\n\n- Normal inference writes files named `inferred_%04d.png` in the save directory.\n- Interpolation writes `frame_\u003Csrc>_\u003Cdst>_step_\u003Cidx>.png` files.\n- GIF compilation expects those frame PNGs in the save directory and writes the\n  named GIF beside them.\n- Export uses TensorFlow checkpoint naming with a generator model prefix.\n\n## Recommended workflow\n\n1. Verify the checkpoint directory contains a TensorFlow checkpoint state.\n2. Decide whether you want one style ID, a random mix, or interpolation between\n   two or more style IDs.\n3. Confirm the source object file contains paired glyph records and that its\n   batch size is compatible with the inference command.\n4. Use the command planner to validate flags and paths before launching any\n   long job.\n5. Inspect outputs after the first few batches, especially if the chosen style\n   labels or batch size do not match the training run.\n\nRead [inference-workflow.md](references\u002Finference-workflow.md) for command\nshapes and evaluation steps. Read [checkpoints-and-outputs.md](references\u002Fcheckpoints-and-outputs.md)\nfor restore\u002Fexport expectations and filename conventions. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor checkpoint, batch-size, GIF, and source-object failures.\n\n## Bundled helper\n\n- [scripts\u002Fplan_zi2zi_inference.py](scripts\u002Fplan_zi2zi_inference.py) validates\n  inference, interpolation, and export arguments and prints the command that a\n  future agent should run in a legacy zi2zi environment.\n\n## What not to promise automatically\n\n- Do not promise restoration of a checkpoint without checking that the concrete\n  checkpoint files exist and match the chosen hyperparameters.\n- Do not promise a successful interpolation run unless `embedding_ids` contains\n  at least two integers.\n- Do not promise export success if the model directory contains only partial or\n  mismatched checkpoint shards.\n","# zi2zi inference and export\n\nUse this sub-skill when a task is about generating glyphs from a trained zi2zi\ncheckpoint, interpolating between style labels, creating frame sequences or a\nGIF, or exporting generator-only variables for later reuse. It does not launch\nlong inference jobs automatically; it explains the checkpoint contract and\nprints safe command templates.\n\n## Use this sub-skill when\n\n- The user has a checkpoint directory and wants generated glyphs.\n- The task mentions `infer.py`, `export.py`, `model_dir`, `source_obj`,\n  `embedding_ids`, `interpolate`, `steps`, `output_gif`, `uroboros`, or exported\n  generator weights.\n- The user wants to know how inference chooses between single-style generation\n  and random style selection.\n- The user needs to diagnose checkpoint restore failures, output-image naming,\n  or interpolation problems.\n\n## Route elsewhere\n\n- Data rendering and `.obj` packaging go to\n  [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n- Training, fine-tuning, or label shuffling go to\n  [training-and-model](..\u002Ftraining-and-model\u002FSKILL.md).\n- Compatibility questions go to the root [compatibility](..\u002F..\u002Freferences\u002Fcompatibility.md)\n  reference.\n\n## Core inference facts\n\n- `infer.py` restores generator variables from a checkpoint and uses a source\n  object file to provide images.\n- If `embedding_ids` contains one integer, the model uses that style for every\n  source image. If it contains multiple IDs, the script picks randomly from the\n  list for each batch.\n- `interpolate=1` asks the model to linearly interpolate between style vectors.\n  With `uroboros=1`, the interpolation path closes the loop by appending the\n  first ID to the end of the chain.\n- `output_gif` triggers GIF compilation from the rendered interpolation frames.\n- `export.py` saves generator-only variables, which include the embedding table\n  and generator weights.\n\n## Output conventions\n\n- Normal inference writes files named `inferred_%04d.png` in the save directory.\n- Interpolation writes `frame_\u003Csrc>_\u003Cdst>_step_\u003Cidx>.png` files.\n- GIF compilation expects those frame PNGs in the save directory and writes the\n  named GIF beside them.\n- Export uses TensorFlow checkpoint naming with a generator model prefix.\n\n## Recommended workflow\n\n1. Verify the checkpoint directory contains a TensorFlow checkpoint state.\n2. Decide whether you want one style ID, a random mix, or interpolation between\n   two or more style IDs.\n3. Confirm the source object file contains paired glyph records and that its\n   batch size is compatible with the inference command.\n4. Use the command planner to validate flags and paths before launching any\n   long job.\n5. Inspect outputs after the first few batches, especially if the chosen style\n   labels or batch size do not match the training run.\n\nRead [inference-workflow.md](references\u002Finference-workflow.md) for command\nshapes and evaluation steps. Read [checkpoints-and-outputs.md](references\u002Fcheckpoints-and-outputs.md)\nfor restore\u002Fexport expectations and filename conventions. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor checkpoint, batch-size, GIF, and source-object failures.\n\n## Bundled helper\n\n- [scripts\u002Fplan_zi2zi_inference.py](scripts\u002Fplan_zi2zi_inference.py) validates\n  inference, interpolation, and export arguments and prints the command that a\n  future agent should run in a legacy zi2zi environment.\n\n## What not to promise automatically\n\n- Do not promise restoration of a checkpoint without checking that the concrete\n  checkpoint files exist and match the chosen hyperparameters.\n- Do not promise a successful interpolation run unless `embedding_ids` contains\n  at least two integers.\n- Do not promise export success if the model directory contains only partial or\n  mismatched checkpoint shards.\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\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export",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 inference-and-export",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-and-export",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-and-export","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\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcheckpoints-and-outputs.md","REFERENCE","参考文档",2084,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Freferences\u002Fcheckpoints-and-outputs.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Finference-workflow.md",2555,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Freferences\u002Finference-workflow.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",2006,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\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",[],[]]