[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7JFB68YW74P9FS9ZMBKNY":3,"skill-same:01M7F7JFB68YW74P9FS9ZMBKNY":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},"01M7F7JFB68YW74P9FS9ZMBKNY","anomalib",null,"Use anomalib for anomaly-detection install, data\u002Fmodel selection, training and evaluation, deployment and inference, and benchmark pipelines.","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\u002Fanomalib\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: anomalib\ndescription: \"Use anomalib for anomaly-detection install, data\u002Fmodel selection,\n  training and evaluation, deployment and inference, and benchmark pipelines.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Anomalib Repo Skill\n\nUse this repo skill when the user asks about the `anomalib` Python package, anomaly-detection data modules, model selection, training and evaluation, export and inference, or benchmark pipelines.\n\nThis skill tree is self-contained. Future agents should use the bundled references and scripts inside this directory, not the original source checkout.\n\n## Repo at a glance\n\n- `src\u002Fanomalib\u002F`: public package source for data, models, engine, deploy, and pipelines.\n- `docs\u002Fsource\u002F...`: user-facing guides, API references, and troubleshooting notes distilled into bundled references.\n- `examples\u002Fapi\u002F` and `examples\u002Fcli\u002F`: runnable workflow examples that informed the bundled recipes and scripts.\n- `tests\u002F`: behavior evidence for defaults, errors, and edge cases.\n- `tools\u002F`: repo-owned helpers and advanced entry points that were copied, adapted, or referenced where safe.\n\n## Quick start\n\n- If you only need to confirm the package imports, run `scripts\u002Fcheck_import.py`.\n- If installation, optional extras, or CLI flags are the problem, start with `sub-skills\u002Finstall-and-cli\u002FSKILL.md`.\n- If the request is about data layout or choosing a model, route to `sub-skills\u002Fdata-and-models\u002FSKILL.md`.\n- If the request is about fit\u002Ftrain\u002Ftest\u002Fvalidate, metrics, callbacks, logging, preprocessing, or visualization, route to `sub-skills\u002Ftraining-and-evaluation\u002FSKILL.md`.\n- If the request is about export, `Engine.predict`, or runtime inferencers, route to `sub-skills\u002Fdeployment-and-inference\u002FSKILL.md`.\n- If the request is about benchmark configs or tiled ensemble workflows, route to `sub-skills\u002Fpipelines-and-benchmarks\u002FSKILL.md`.\n\n## Route by task\n\n| User request | Go to |\n| --- | --- |\n| \"How do I install anomalib or fix a CLI\u002Fhelp problem?\" | `sub-skills\u002Finstall-and-cli\u002F` |\n| \"Which datamodule or model should I use?\" | `sub-skills\u002Fdata-and-models\u002F` |\n| \"How do training, validation, metrics, or callbacks work?\" | `sub-skills\u002Ftraining-and-evaluation\u002F` |\n| \"How do I export or run inference from a checkpoint?\" | `sub-skills\u002Fdeployment-and-inference\u002F` |\n| \"How do I run a benchmark or tiled ensemble config?\" | `sub-skills\u002Fpipelines-and-benchmarks\u002F` |\n\n## How to choose quickly\n\n1. Start with the smallest workflow that matches the user's current step.\n2. If the user is blocked by installation or CLI syntax, resolve that first through install-and-cli.\n3. If the user already has data and a model choice, use data-and-models before any training step.\n4. If the user has a checkpoint and wants predictions or deployment artifacts, use deployment-and-inference.\n5. If the user needs benchmark-scale orchestration, use pipelines-and-benchmarks and keep execution planning separate from model or data selection.\n\n## Shared references\n\n- `references\u002Frepo-provenance.md` records the source snapshot, package version, and evidence footprint.\n- `references\u002Frepo-routing-metadata.json` feeds the managed repo-skill router during import.\n- `references\u002Ftroubleshooting.md` covers package-wide install, import, and routing failures.\n- `scripts\u002Fcheck_import.py` is a minimal package-import smoke check.\n\n## Operating notes\n\n- Prefer the most specific sub-skill instead of staying at the root.\n- Keep install and CLI issues separate from model or pipeline questions.\n- Keep deployment and inference separate from training and evaluation.\n- Keep benchmark orchestration separate from engine internals unless the user explicitly asks for both.\n- If a user asks for a broad end-to-end task, use the sub-skill that owns the current bottleneck, then cross-link to the next step.\n\n## Self-check\n\nA healthy runtime installation should at least be able to import `anomalib` and report its version. Use the bundled import check first, then move into the relevant sub-skill for deeper guidance.\n","# Anomalib Repo Skill\n\nUse this repo skill when the user asks about the `anomalib` Python package, anomaly-detection data modules, model selection, training and evaluation, export and inference, or benchmark pipelines.\n\nThis skill tree is self-contained. Future agents should use the bundled references and scripts inside this directory, not the original source checkout.\n\n## Repo at a glance\n\n- `src\u002Fanomalib\u002F`: public package source for data, models, engine, deploy, and pipelines.\n- `docs\u002Fsource\u002F...`: user-facing guides, API references, and troubleshooting notes distilled into bundled references.\n- `examples\u002Fapi\u002F` and `examples\u002Fcli\u002F`: runnable workflow examples that informed the bundled recipes and scripts.\n- `tests\u002F`: behavior evidence for defaults, errors, and edge cases.\n- `tools\u002F`: repo-owned helpers and advanced entry points that were copied, adapted, or referenced where safe.\n\n## Quick start\n\n- If you only need to confirm the package imports, run `scripts\u002Fcheck_import.py`.\n- If installation, optional extras, or CLI flags are the problem, start with `sub-skills\u002Finstall-and-cli\u002FSKILL.md`.\n- If the request is about data layout or choosing a model, route to `sub-skills\u002Fdata-and-models\u002FSKILL.md`.\n- If the request is about fit\u002Ftrain\u002Ftest\u002Fvalidate, metrics, callbacks, logging, preprocessing, or visualization, route to `sub-skills\u002Ftraining-and-evaluation\u002FSKILL.md`.\n- If the request is about export, `Engine.predict`, or runtime inferencers, route to `sub-skills\u002Fdeployment-and-inference\u002FSKILL.md`.\n- If the request is about benchmark configs or tiled ensemble workflows, route to `sub-skills\u002Fpipelines-and-benchmarks\u002FSKILL.md`.\n\n## Route by task\n\n| User request | Go to |\n| --- | --- |\n| \"How do I install anomalib or fix a CLI\u002Fhelp problem?\" | `sub-skills\u002Finstall-and-cli\u002F` |\n| \"Which datamodule or model should I use?\" | `sub-skills\u002Fdata-and-models\u002F` |\n| \"How do training, validation, metrics, or callbacks work?\" | `sub-skills\u002Ftraining-and-evaluation\u002F` |\n| \"How do I export or run inference from a checkpoint?\" | `sub-skills\u002Fdeployment-and-inference\u002F` |\n| \"How do I run a benchmark or tiled ensemble config?\" | `sub-skills\u002Fpipelines-and-benchmarks\u002F` |\n\n## How to choose quickly\n\n1. Start with the smallest workflow that matches the user's current step.\n2. If the user is blocked by installation or CLI syntax, resolve that first through install-and-cli.\n3. If the user already has data and a model choice, use data-and-models before any training step.\n4. If the user has a checkpoint and wants predictions or deployment artifacts, use deployment-and-inference.\n5. If the user needs benchmark-scale orchestration, use pipelines-and-benchmarks and keep execution planning separate from model or data selection.\n\n## Shared references\n\n- `references\u002Frepo-provenance.md` records the source snapshot, package version, and evidence footprint.\n- `references\u002Frepo-routing-metadata.json` feeds the managed repo-skill router during import.\n- `references\u002Ftroubleshooting.md` covers package-wide install, import, and routing failures.\n- `scripts\u002Fcheck_import.py` is a minimal package-import smoke check.\n\n## Operating notes\n\n- Prefer the most specific sub-skill instead of staying at the root.\n- Keep install and CLI issues separate from model or pipeline questions.\n- Keep deployment and inference separate from training and evaluation.\n- Keep benchmark orchestration separate from engine internals unless the user explicitly asks for both.\n- If a user asks for a broad end-to-end task, use the sub-skill that owns the current bottleneck, then cross-link to the next step.\n\n## Self-check\n\nA healthy runtime installation should at least be able to import `anomalib` and report its version. Use the bundled import check first, then move into the relevant sub-skill for deeper guidance.\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\u002Fanomalib",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 anomalib",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill anomalib",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill anomalib","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\u002Fanomalib\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1902,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fanomalib\u002Freferences\u002Frepo-provenance.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-routing-metadata.json",335,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fanomalib\u002Freferences\u002Frepo-routing-metadata.json",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",2792,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fanomalib\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",[],[]]