[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EGYVW3JS0PPMWRRB8NW4J3":3,"skill-same:01M7EGYVW3JS0PPMWRRB8NW4J3":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},"01M7EGYVW3JS0PPMWRRB8NW4J3","deep-danbooru",null,"Use DeepDanbooru for anime-style image tag estimation, project and Danbooru-style dataset preparation, TensorFlow training, image evaluation, TFLite conversion, and experimental Grad-CAM workflows.","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\u002F04-安全渗透\u002Fdeep-danbooru\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deep-danbooru\ndescription: \"Use DeepDanbooru for anime-style image tag estimation, project and\n  Danbooru-style dataset preparation, TensorFlow training, image evaluation,\n  TFLite conversion, and experimental Grad-CAM workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# DeepDanbooru\n\nUse this repo skill when a task names DeepDanbooru or `deepdanbooru`, asks for\nanime-style multi-label image tagging, or needs the package's project, dataset,\ntraining, evaluation, TensorFlow Lite, or Grad-CAM workflows. This skill covers\nthe 1.0.0 source contract represented by the provenance snapshot; read it before\nrefreshing against a changed checkout.\n\n## Route by task\n\n- **Project, tags, or dataset layout**: read\n  [`project-data-setup`](sub-skills\u002Fproject-data-setup\u002FSKILL.md). It owns\n  `create-project`, `download-tags`, `make-training-database`, `project.json`,\n  `tags.txt`, SQLite `posts`, and `images\u002F\u003Cprefix>\u002F` validation.\n- **Training or checkpoint recovery**: read\n  [`model-training`](sub-skills\u002Fmodel-training\u002FSKILL.md). It owns config\n  validation, supported ResNet\u002Foptimizer\u002Floss values, data preflight,\n  `train-project`, checkpoints, and `.keras` exports.\n- **Tag inference or evaluation**: read\n  [`inference-evaluation`](sub-skills\u002Finference-evaluation\u002FSKILL.md). It owns\n  `evaluate`, `evaluate-project`, Python inference APIs, preprocessing,\n  thresholds, recursive folders, and `.txt` sidecars.\n- **Export or attribution artifacts**: read\n  [`post-training-tools`](sub-skills\u002Fpost-training-tools\u002FSKILL.md). It owns\n  `conv2tflite`, TFLite checks, and experimental `grad-cam` output.\n\nUse the owning sub-skill rather than trying to make the root a full API manual.\nThe root references below contain cross-cutting install, CLI, and failure\ninformation.\n\n## Install and verify\n\nThe source package declares a base install plus a TensorFlow extra. For the\nrepository's documented full workflow, install the TensorFlow requirements in a\nfresh compatible Python environment:\n\n```console\npython -m pip install \"deepdanbooru[tensorflow]\"\n# Or, when the distribution's published requirements file is available:\npython -m pip install -r requirements.txt\n```\n\nThe package imports TensorFlow and TensorFlow I\u002FO through its public module and\nCLI paths. Do not call a CPU import proof of CUDA readiness. Start with the\nbundled no-download diagnostic:\n\n```console\npython scripts\u002Fenvironment_smoke.py\npython -m deepdanbooru --help\npython -m deepdanbooru evaluate --help\n```\n\nThe console entry point is `deepdanbooru`. CPU TensorFlow is the verified\ncorrectness backend for this skill. `evaluate` is CPU-first unless\n`--allow-gpu` is explicitly supplied; this source snapshot did not verify GPU\nlibraries or GPU performance.\n\n## Operating boundaries\n\n- Do not download Danbooru tags, model weights, or datasets without explicit\n  network\u002Fcredential approval. The bundled scripts are offline and safe by\n  default.\n- Do not launch full training as a smoke test. Validate the project, tags,\n  SQLite schema, image paths, and package imports first; training is expensive\n  and writes checkpoints\u002Fexports.\n- Treat the known 1.0.0 `evaluate-project` loader defect as real: its native\n  route calls the absent `dd.data.load_tags_from_project` symbol. For production\n  folder inference, use `evaluate --project-path ... --allow-folder`, which uses\n  the available project tag loader. The bundled project smoke helper exercises\n  that fallback and does not claim an unverified native run.\n- The native `evaluate --save-txt` path can fail for an empty selected-tag list\n  and overwrites an existing sibling sidecar with `w`. Use the skill helper\n  `sub-skills\u002Finference-evaluation\u002Fscripts\u002Fsave_txt_guard.py` when sidecar output\n  needs a local safety boundary: it rejects empty selections and sibling\n  directories, and requires an explicit flag to overwrite a regular file.\n- Read [`repo-provenance.md`](references\u002Frepo-provenance.md) before deciding\n  whether this graph is stale; package\u002Fsource version drift remains possible.\n- Read [`install-and-cli.md`](references\u002Finstall-and-cli.md) for the full command\n  map and dependency\u002Fversion caveat.\n- Read [`troubleshooting.md`](references\u002Ftroubleshooting.md) for package-wide\n  recovery.\n","# DeepDanbooru\n\nUse this repo skill when a task names DeepDanbooru or `deepdanbooru`, asks for\nanime-style multi-label image tagging, or needs the package's project, dataset,\ntraining, evaluation, TensorFlow Lite, or Grad-CAM workflows. This skill covers\nthe 1.0.0 source contract represented by the provenance snapshot; read it before\nrefreshing against a changed checkout.\n\n## Route by task\n\n- **Project, tags, or dataset layout**: read\n  [`project-data-setup`](sub-skills\u002Fproject-data-setup\u002FSKILL.md). It owns\n  `create-project`, `download-tags`, `make-training-database`, `project.json`,\n  `tags.txt`, SQLite `posts`, and `images\u002F\u003Cprefix>\u002F` validation.\n- **Training or checkpoint recovery**: read\n  [`model-training`](sub-skills\u002Fmodel-training\u002FSKILL.md). It owns config\n  validation, supported ResNet\u002Foptimizer\u002Floss values, data preflight,\n  `train-project`, checkpoints, and `.keras` exports.\n- **Tag inference or evaluation**: read\n  [`inference-evaluation`](sub-skills\u002Finference-evaluation\u002FSKILL.md). It owns\n  `evaluate`, `evaluate-project`, Python inference APIs, preprocessing,\n  thresholds, recursive folders, and `.txt` sidecars.\n- **Export or attribution artifacts**: read\n  [`post-training-tools`](sub-skills\u002Fpost-training-tools\u002FSKILL.md). It owns\n  `conv2tflite`, TFLite checks, and experimental `grad-cam` output.\n\nUse the owning sub-skill rather than trying to make the root a full API manual.\nThe root references below contain cross-cutting install, CLI, and failure\ninformation.\n\n## Install and verify\n\nThe source package declares a base install plus a TensorFlow extra. For the\nrepository's documented full workflow, install the TensorFlow requirements in a\nfresh compatible Python environment:\n\n```console\npython -m pip install \"deepdanbooru[tensorflow]\"\n# Or, when the distribution's published requirements file is available:\npython -m pip install -r requirements.txt\n```\n\nThe package imports TensorFlow and TensorFlow I\u002FO through its public module and\nCLI paths. Do not call a CPU import proof of CUDA readiness. Start with the\nbundled no-download diagnostic:\n\n```console\npython scripts\u002Fenvironment_smoke.py\npython -m deepdanbooru --help\npython -m deepdanbooru evaluate --help\n```\n\nThe console entry point is `deepdanbooru`. CPU TensorFlow is the verified\ncorrectness backend for this skill. `evaluate` is CPU-first unless\n`--allow-gpu` is explicitly supplied; this source snapshot did not verify GPU\nlibraries or GPU performance.\n\n## Operating boundaries\n\n- Do not download Danbooru tags, model weights, or datasets without explicit\n  network\u002Fcredential approval. The bundled scripts are offline and safe by\n  default.\n- Do not launch full training as a smoke test. Validate the project, tags,\n  SQLite schema, image paths, and package imports first; training is expensive\n  and writes checkpoints\u002Fexports.\n- Treat the known 1.0.0 `evaluate-project` loader defect as real: its native\n  route calls the absent `dd.data.load_tags_from_project` symbol. For production\n  folder inference, use `evaluate --project-path ... --allow-folder`, which uses\n  the available project tag loader. The bundled project smoke helper exercises\n  that fallback and does not claim an unverified native run.\n- The native `evaluate --save-txt` path can fail for an empty selected-tag list\n  and overwrites an existing sibling sidecar with `w`. Use the skill helper\n  `sub-skills\u002Finference-evaluation\u002Fscripts\u002Fsave_txt_guard.py` when sidecar output\n  needs a local safety boundary: it rejects empty selections and sibling\n  directories, and requires an explicit flag to overwrite a regular file.\n- Read [`repo-provenance.md`](references\u002Frepo-provenance.md) before deciding\n  whether this graph is stale; package\u002Fsource version drift remains possible.\n- Read [`install-and-cli.md`](references\u002Finstall-and-cli.md) for the full command\n  map and dependency\u002Fversion caveat.\n- Read [`troubleshooting.md`](references\u002Ftroubleshooting.md) for package-wide\n  recovery.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fdeep-danbooru",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 deep-danbooru",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill deep-danbooru",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill deep-danbooru","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdeep-danbooru\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Finstall-and-cli.md","REFERENCE","参考文档",2851,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdeep-danbooru\u002Freferences\u002Finstall-and-cli.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",1603,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdeep-danbooru\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",332,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdeep-danbooru\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",3697,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdeep-danbooru\u002Freferences\u002Ftroubleshooting.md",[67,75,80,87,94,101],{"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":74},"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",[],[],"2026-11-16 10:05:34",{"skillNo":76,"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":77,"categories":78,"keywords":79,"publishedAt":74},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":74},"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":74},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":74},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":74},"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",[],[]]