[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FACWASJRAXPDBV7BHJQWFH":3,"skill-same:01M7FACWASJRAXPDBV7BHJQWFH":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},"01M7FACWASJRAXPDBV7BHJQWFH","lightly",null,"Use LightlySSL for self-supervised computer-vision training, model components, CLIs, embeddings, data layout, evaluation, and repository maintenance.","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\u002Flightly\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: lightly\ndescription: \"Use LightlySSL for self-supervised computer-vision training, model\n  components, CLIs, embeddings, data layout, evaluation, and repository\n  maintenance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LightlySSL Repo Skill\n\nUse this skill when a task names `lightly`, LightlySSL, self-supervised computer vision, Lightly's CLI commands, SSL transforms\u002Flosses\u002Fheads, image-folder embeddings, YOLO crop helpers, or maintenance of the LightlySSL repository.\n\n## Quick setup\n\n- Public install: `pip install lightly`\n- Optional TIMM\u002FViT modules: `pip install \"lightly[timm]\"`\n- Optional direct video support: `pip install \"lightly[video]\"`\n- Minimal import check:\n\n```bash\npython - \u003C\u003C'PY'\nimport lightly\nfrom lightly.loss import NTXentLoss\nfrom lightly.transforms import SimCLRTransform\nprint(lightly.__version__, NTXentLoss, SimCLRTransform)\nPY\n```\n\nFor a richer environment smoke, run the bundled [environment checker](scripts\u002Fcheck_lightly_environment.py). It imports core modules, reports optional TIMM\u002Fvideo availability, and can do a tiny tensor check without downloads.\n\n## Route map\n\n| Need | Read |\n|---|---|\n| Assemble datasets, collates, transforms, losses, projection heads, memory banks, or method-to-component mappings. | [ssl-building-blocks](sub-skills\u002Fssl-building-blocks\u002FSKILL.md) |\n| Adapt a bare PyTorch, PyTorch Lightning, or distributed Lightly SSL training recipe without downloading repo examples. | [training-workflows](sub-skills\u002Ftraining-workflows\u002FSKILL.md) |\n| Build or validate `lightly-version`, `lightly-ssl-train`, `lightly-embed`, `lightly-magic`, `lightly-crop`, Hydra overrides, input folders, embeddings CSVs, or YOLO crop labels. | [cli-data-embedding](sub-skills\u002Fcli-data-embedding\u002FSKILL.md) |\n| Use KNN\u002Flinear evaluation utilities or choose repository checks for changes to losses, transforms, examples, docs, notebooks, or distributed tests. | [evaluation-maintenance](sub-skills\u002Fevaluation-maintenance\u002FSKILL.md) |\n\n## Shared references\n\n- [Package overview](references\u002Fpackage-overview.md) — public surfaces, optional extras, and workflow boundaries.\n- [Troubleshooting](references\u002Ftroubleshooting.md) — cross-cutting install\u002Fimport\u002Fbackend\u002Fdata\u002Fconfig problems before routing deeper.\n- [Repository provenance](references\u002Frepo-provenance.md) — source snapshot and refresh triggers.\n- [Router metadata](references\u002Frepo-routing-metadata.json) — structured scenario placement used by the managed repo-skills router.\n\n## Operating rules\n\n1. Do not run training, embedding, crop, notebook, benchmark, or distributed commands until the user provides data paths, output policy, and runtime budget.\n2. Prefer bundled scripts for safe preflight: environment checks, component smoke checks, CLI command construction, folder validation, tiny YOLO fixtures, and synthetic SimCLR steps.\n3. Treat GPU, distributed, TIMM, and video support as optional unless the user explicitly asks for them; verify the relevant backend\u002Fextra before claiming it works.\n4. Keep source-code maintenance guidance separate from package-use guidance. When editing the repository, use the maintenance sub-skill to select focused checks before broad `make all-checks`.\n","# LightlySSL Repo Skill\n\nUse this skill when a task names `lightly`, LightlySSL, self-supervised computer vision, Lightly's CLI commands, SSL transforms\u002Flosses\u002Fheads, image-folder embeddings, YOLO crop helpers, or maintenance of the LightlySSL repository.\n\n## Quick setup\n\n- Public install: `pip install lightly`\n- Optional TIMM\u002FViT modules: `pip install \"lightly[timm]\"`\n- Optional direct video support: `pip install \"lightly[video]\"`\n- Minimal import check:\n\n```bash\npython - \u003C\u003C'PY'\nimport lightly\nfrom lightly.loss import NTXentLoss\nfrom lightly.transforms import SimCLRTransform\nprint(lightly.__version__, NTXentLoss, SimCLRTransform)\nPY\n```\n\nFor a richer environment smoke, run the bundled [environment checker](scripts\u002Fcheck_lightly_environment.py). It imports core modules, reports optional TIMM\u002Fvideo availability, and can do a tiny tensor check without downloads.\n\n## Route map\n\n| Need | Read |\n|---|---|\n| Assemble datasets, collates, transforms, losses, projection heads, memory banks, or method-to-component mappings. | [ssl-building-blocks](sub-skills\u002Fssl-building-blocks\u002FSKILL.md) |\n| Adapt a bare PyTorch, PyTorch Lightning, or distributed Lightly SSL training recipe without downloading repo examples. | [training-workflows](sub-skills\u002Ftraining-workflows\u002FSKILL.md) |\n| Build or validate `lightly-version`, `lightly-ssl-train`, `lightly-embed`, `lightly-magic`, `lightly-crop`, Hydra overrides, input folders, embeddings CSVs, or YOLO crop labels. | [cli-data-embedding](sub-skills\u002Fcli-data-embedding\u002FSKILL.md) |\n| Use KNN\u002Flinear evaluation utilities or choose repository checks for changes to losses, transforms, examples, docs, notebooks, or distributed tests. | [evaluation-maintenance](sub-skills\u002Fevaluation-maintenance\u002FSKILL.md) |\n\n## Shared references\n\n- [Package overview](references\u002Fpackage-overview.md) — public surfaces, optional extras, and workflow boundaries.\n- [Troubleshooting](references\u002Ftroubleshooting.md) — cross-cutting install\u002Fimport\u002Fbackend\u002Fdata\u002Fconfig problems before routing deeper.\n- [Repository provenance](references\u002Frepo-provenance.md) — source snapshot and refresh triggers.\n- [Router metadata](references\u002Frepo-routing-metadata.json) — structured scenario placement used by the managed repo-skills router.\n\n## Operating rules\n\n1. Do not run training, embedding, crop, notebook, benchmark, or distributed commands until the user provides data paths, output policy, and runtime budget.\n2. Prefer bundled scripts for safe preflight: environment checks, component smoke checks, CLI command construction, folder validation, tiny YOLO fixtures, and synthetic SimCLR steps.\n3. Treat GPU, distributed, TIMM, and video support as optional unless the user explicitly asks for them; verify the relevant backend\u002Fextra before claiming it works.\n4. Keep source-code maintenance guidance separate from package-use guidance. When editing the repository, use the maintenance sub-skill to select focused checks before broad `make all-checks`.\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\u002Flightly",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 lightly",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill lightly",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill lightly","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\u002Flightly\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fpackage-overview.md","REFERENCE","参考文档",2572,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Flightly\u002Freferences\u002Fpackage-overview.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",1719,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Flightly\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",514,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Flightly\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",2821,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Flightly\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",[],[]]