[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDF2DCVFX92KHRWZXM0YNB":3,"skill-same:01M7FDF2DCVFX92KHRWZXM0YNB":59},{"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},"01M7FDF2DCVFX92KHRWZXM0YNB","scene-generation",null,"Generate WorldGen 3D scenes from text, images, or equirectangular panoramas, choose splat or mesh output, and explore results in a local Viser viewer.","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\u002Fworldgen\u002Fsub-skills\u002Fscene-generation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: scene-generation\ndescription: \"Generate WorldGen 3D scenes from text, images, or equirectangular\n  panoramas, choose splat or mesh output, and explore results in a local Viser\n  viewer.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Scene generation\n\nUse this route when the task asks for a WorldGen scene from a text prompt,\nsource image, or 360 panorama; wants a Gaussian splat or Open3D mesh; needs\nlow-VRAM or experimental Sharp\u002Finpainting options; or wants to explore and\nexport novel views in a browser.\n\n## Choose the input path\n\n- **Text-to-scene**: construct `WorldGen(mode=\"t2s\", ...)` and call\n  `generate_world(prompt)`.\n- **Image-to-scene**: construct `WorldGen(mode=\"i2s\", ...)`, load an RGB PIL\n  image, and call `generate_world(prompt, image=image)`.\n- **Panorama-to-scene**: load a 2:1 equirectangular PIL image and call\n  `_generate_world(pano_image, return_mesh=...)` to skip panorama diffusion.\n- **Interactive viewer**: run the bundled `scripts\u002Fworldgen_demo.py`; it\n  starts Viser at `http:\u002F\u002Flocalhost:8080`, renders the scene, and exposes camera\n  path and novel-view export controls.\n\nRead [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for concrete code and\ncommand recipes. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\nfor workflow-specific failures after the package-level checks in the root\n[`references\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n\n## Select the output\n\n- Leave `return_mesh=False` for the default `SplatFile` Gaussian scene. Save it\n  with `scene.save(\"scene.ply\")`.\n- Set `return_mesh=True` for an Open3D triangle mesh and save it with\n  `open3d.io.write_triangle_mesh(\"scene.glb\", mesh)`.\n- Do not combine `return_mesh=True` and `inpaint_bg=True` in the bundled demo.\n  The inpainting implementation merges foreground\u002Fbackground splats.\n\n## Select runtime options\n\n- Use `low_vram=True` when the GPU has limited memory or when model loading\n  causes an OOM. The bundled launcher auto-enables it below 24 GB.\n- Use `use_sharp=True` only after the base pipeline works and the optional Sharp\n  package\u002Fcheckpoint is available.\n- Use `inpaint_bg=True` only for an explicitly experimental background repair;\n  it adds segmentation and LaMa model dependencies and extra downloads.\n- Use `resolution` to trade panorama detail against memory and latency. Start\n  lower when debugging an environment or an input contract.\n\n## Safe preflight\n\nBefore a long model download or generation run:\n\n```bash\npython scripts\u002Fcheck_worldgen_env.py --demo-help\n```\n\nThis confirms the installed public API and a tiny CUDA allocation without\nloading FLUX, DA-2, Sharp, or LaMa weights. For the full flag surface, run:\n\n```bash\npython scripts\u002Fworldgen_demo.py --help\n```\n\n## Boundaries\n\nThis sub-skill owns user-facing generation, output conversion, the bundled\nviewer helper, and optional generation modes. It does not own package\ninstallation diagnosis, upstream DA-2\u002FPyTorch3D development, model training,\nrelease engineering, or repository maintenance. Route those questions to the\nroot references or a more appropriate skill.\n","# Scene generation\n\nUse this route when the task asks for a WorldGen scene from a text prompt,\nsource image, or 360 panorama; wants a Gaussian splat or Open3D mesh; needs\nlow-VRAM or experimental Sharp\u002Finpainting options; or wants to explore and\nexport novel views in a browser.\n\n## Choose the input path\n\n- **Text-to-scene**: construct `WorldGen(mode=\"t2s\", ...)` and call\n  `generate_world(prompt)`.\n- **Image-to-scene**: construct `WorldGen(mode=\"i2s\", ...)`, load an RGB PIL\n  image, and call `generate_world(prompt, image=image)`.\n- **Panorama-to-scene**: load a 2:1 equirectangular PIL image and call\n  `_generate_world(pano_image, return_mesh=...)` to skip panorama diffusion.\n- **Interactive viewer**: run the bundled `scripts\u002Fworldgen_demo.py`; it\n  starts Viser at `http:\u002F\u002Flocalhost:8080`, renders the scene, and exposes camera\n  path and novel-view export controls.\n\nRead [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for concrete code and\ncommand recipes. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\nfor workflow-specific failures after the package-level checks in the root\n[`references\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n\n## Select the output\n\n- Leave `return_mesh=False` for the default `SplatFile` Gaussian scene. Save it\n  with `scene.save(\"scene.ply\")`.\n- Set `return_mesh=True` for an Open3D triangle mesh and save it with\n  `open3d.io.write_triangle_mesh(\"scene.glb\", mesh)`.\n- Do not combine `return_mesh=True` and `inpaint_bg=True` in the bundled demo.\n  The inpainting implementation merges foreground\u002Fbackground splats.\n\n## Select runtime options\n\n- Use `low_vram=True` when the GPU has limited memory or when model loading\n  causes an OOM. The bundled launcher auto-enables it below 24 GB.\n- Use `use_sharp=True` only after the base pipeline works and the optional Sharp\n  package\u002Fcheckpoint is available.\n- Use `inpaint_bg=True` only for an explicitly experimental background repair;\n  it adds segmentation and LaMa model dependencies and extra downloads.\n- Use `resolution` to trade panorama detail against memory and latency. Start\n  lower when debugging an environment or an input contract.\n\n## Safe preflight\n\nBefore a long model download or generation run:\n\n```bash\npython scripts\u002Fcheck_worldgen_env.py --demo-help\n```\n\nThis confirms the installed public API and a tiny CUDA allocation without\nloading FLUX, DA-2, Sharp, or LaMa weights. For the full flag surface, run:\n\n```bash\npython scripts\u002Fworldgen_demo.py --help\n```\n\n## Boundaries\n\nThis sub-skill owns user-facing generation, output conversion, the bundled\nviewer helper, and optional generation modes. It does not own package\ninstallation diagnosis, upstream DA-2\u002FPyTorch3D development, model training,\nrelease engineering, or repository maintenance. Route those questions to the\nroot references or a more appropriate skill.\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\u002Fworldgen\u002Fsub-skills\u002Fscene-generation",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 scene-generation",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill scene-generation",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill scene-generation","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\u002Fworldgen\u002Fsub-skills\u002Fscene-generation\u002FSKILL.md",[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",2878,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworldgen\u002Fsub-skills\u002Fscene-generation\u002Freferences\u002Ftroubleshooting.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fworkflows.md",4132,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworldgen\u002Fsub-skills\u002Fscene-generation\u002Freferences\u002Fworkflows.md",[60,68,73,80,87,94],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]