[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FC5FSJNPVQPY404JKS69TY":3,"skill-same:01M7FC5FSJNPVQPY404JKS69TY":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},"01M7FC5FSJNPVQPY404JKS69TY","modeling-and-layers",null,"Understand Scenic model registry contracts, BaseModel task bases, Flax module construction, layers, attention, matchers, and tiny smoke checks.","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\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: modeling-and-layers\ndescription: \"Understand Scenic model registry contracts, BaseModel task bases,\n  Flax module construction, layers, attention, matchers, and tiny smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Modeling and Layers\n\nUse this sub-skill when the task is about Scenic model selection, BaseModel contracts, task-specific model bases, Flax module construction, layer\u002Fattention\u002Fmatcher APIs, or tiny smoke checks.\n\n## Start here\n\n- Read [`references\u002Fmodeling-api.md`](references\u002Fmodeling-api.md) for the registry, model-class contracts, loss\u002Fmetric conventions, and model-init\u002Fapply patterns.\n- Read [`references\u002Flayers-and-matchers.md`](references\u002Flayers-and-matchers.md) for attention\u002Flayer\u002Fmatcher APIs, optional dependencies, and tiny validation patterns.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a model name is missing, a Flax\u002FJAX shape or RNG issue appears, metrics aggregate incorrectly, or a checkpoint does not load cleanly.\n- Run [`scripts\u002Fmodel_registry_probe.py`](scripts\u002Fmodel_registry_probe.py) to list registered model names or resolve a single model class without instantiating it.\n\n## Scope and routing\n\n- In scope: model registry lookups, BaseModel and task-base contracts, loss\u002Fmetric normalization, Flax module construction, layer\u002Fattention\u002Fmatcher APIs, and smoke-test patterns for tiny inputs.\n- Out of scope: training orchestration, launch commands, schedules, checkpoint lifecycle, dataset builders, project selection, and paper\u002Fbaseline choice.\n- Route training\u002Fruntime execution to `running-and-training`.\n- Route dataset builders and input-pipeline work to `data-pipelines`.\n- Route project-level or paper-level model selection to `baselines-and-projects`.\n\n## Operating rules\n\n1. Begin with the registry; an unrecognized model name is usually a registry or config problem, not a training problem.\n2. Treat `build_flax_model()` as the construction boundary. Build the Flax module, then use tiny `init`\u002F`apply` checks instead of a full run.\n3. Keep loss functions local and scalar; keep metrics cross-device safe by returning sum\u002Fnormalizer pairs.\n4. Use tiny dummy inputs for smoke checks and shape assertions. Prefer `init_with_output`, `init`, and `apply` on minimal batches.\n5. Keep optional matcher dependencies explicit. Do not promise `scipy` or `ott-jax` behavior unless the target matcher requires it.\n\n## When to read what\n\n| Need | Read |\n| --- | --- |\n| Registry, BaseModel, task bases, loss\u002Fmetric rules, smoke-init pattern | [`references\u002Fmodeling-api.md`](references\u002Fmodeling-api.md) |\n| Attention, layer, masked-layer, and matcher APIs plus tiny validation patterns | [`references\u002Flayers-and-matchers.md`](references\u002Flayers-and-matchers.md) |\n| Common failure modes and recovery | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n| List registered models or resolve one class | [`scripts\u002Fmodel_registry_probe.py`](scripts\u002Fmodel_registry_probe.py) |\n","# Modeling and Layers\n\nUse this sub-skill when the task is about Scenic model selection, BaseModel contracts, task-specific model bases, Flax module construction, layer\u002Fattention\u002Fmatcher APIs, or tiny smoke checks.\n\n## Start here\n\n- Read [`references\u002Fmodeling-api.md`](references\u002Fmodeling-api.md) for the registry, model-class contracts, loss\u002Fmetric conventions, and model-init\u002Fapply patterns.\n- Read [`references\u002Flayers-and-matchers.md`](references\u002Flayers-and-matchers.md) for attention\u002Flayer\u002Fmatcher APIs, optional dependencies, and tiny validation patterns.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a model name is missing, a Flax\u002FJAX shape or RNG issue appears, metrics aggregate incorrectly, or a checkpoint does not load cleanly.\n- Run [`scripts\u002Fmodel_registry_probe.py`](scripts\u002Fmodel_registry_probe.py) to list registered model names or resolve a single model class without instantiating it.\n\n## Scope and routing\n\n- In scope: model registry lookups, BaseModel and task-base contracts, loss\u002Fmetric normalization, Flax module construction, layer\u002Fattention\u002Fmatcher APIs, and smoke-test patterns for tiny inputs.\n- Out of scope: training orchestration, launch commands, schedules, checkpoint lifecycle, dataset builders, project selection, and paper\u002Fbaseline choice.\n- Route training\u002Fruntime execution to `running-and-training`.\n- Route dataset builders and input-pipeline work to `data-pipelines`.\n- Route project-level or paper-level model selection to `baselines-and-projects`.\n\n## Operating rules\n\n1. Begin with the registry; an unrecognized model name is usually a registry or config problem, not a training problem.\n2. Treat `build_flax_model()` as the construction boundary. Build the Flax module, then use tiny `init`\u002F`apply` checks instead of a full run.\n3. Keep loss functions local and scalar; keep metrics cross-device safe by returning sum\u002Fnormalizer pairs.\n4. Use tiny dummy inputs for smoke checks and shape assertions. Prefer `init_with_output`, `init`, and `apply` on minimal batches.\n5. Keep optional matcher dependencies explicit. Do not promise `scipy` or `ott-jax` behavior unless the target matcher requires it.\n\n## When to read what\n\n| Need | Read |\n| --- | --- |\n| Registry, BaseModel, task bases, loss\u002Fmetric rules, smoke-init pattern | [`references\u002Fmodeling-api.md`](references\u002Fmodeling-api.md) |\n| Attention, layer, masked-layer, and matcher APIs plus tiny validation patterns | [`references\u002Flayers-and-matchers.md`](references\u002Flayers-and-matchers.md) |\n| Common failure modes and recovery | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n| List registered models or resolve one class | [`scripts\u002Fmodel_registry_probe.py`](scripts\u002Fmodel_registry_probe.py) |\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\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers",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 modeling-and-layers",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill modeling-and-layers",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill modeling-and-layers","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\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Flayers-and-matchers.md","REFERENCE","参考文档",6125,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers\u002Freferences\u002Flayers-and-matchers.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fmodeling-api.md",6598,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers\u002Freferences\u002Fmodeling-api.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",3933,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fscenic\u002Fsub-skills\u002Fmodeling-and-layers\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",[],[]]