[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ENE4YFPC2DT5Q1MCKJT8WB":3,"skill-same:01M7ENE4YFPC2DT5Q1MCKJT8WB":62},{"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},"01M7ENE4YFPC2DT5Q1MCKJT8WB","llamagen",null,"Router for LlamaGen autoregressive image-generation workflows, including tokenizers, data preparation, class-conditional generation, and text-conditional generation.","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\u002Fllamagen\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: llamagen\ndescription: \"Router for LlamaGen autoregressive image-generation workflows,\n  including tokenizers, data preparation, class-conditional generation, and\n  text-conditional generation.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# LlamaGen\n\nUse this skill when the user asks about the LlamaGen repository, its released checkpoints, or its image-generation workflows.\n\n## What this skill owns\n- Tokenizer family workflows: VQ, VQGAN, Stable Diffusion VAE, and Consistency Decoder training or reconstruction.\n- Preprocessing workflows: discrete-code extraction, T5 feature extraction, OpenImages manifests, and dataset cache layout.\n- Class-conditional image generation: c2i training, sampling, serving, and c2i evaluation.\n- Text-conditional image generation: t2i stage-1 \u002F stage-2 training, prompt sampling, and t2i evaluation.\n\n## When to route where\n- Tokenizer training, finetuning, reconstruction, or code\u002Fimage round-trip checks -> `sub-skills\u002Ftokenizers\u002F`\n- Code\u002FT5 cache generation, OpenImages manifests, or dataset-layout questions -> `sub-skills\u002Fdata-preparation\u002F`\n- ImageNet class-conditional generation, serving, packaging, or c2i evaluation -> `sub-skills\u002Fclass-conditional\u002F`\n- Caption-conditioned training, sampling, or t2i evaluation -> `sub-skills\u002Ftext-conditional\u002F`\n\n## Before you start\n- Read `references\u002Frepo-provenance.md` to confirm the checkout snapshot.\n- Read `references\u002Ftroubleshooting.md` when the request mentions installs, imports, CUDA, checkpoints, caches, or evaluation dependencies.\n- Run `scripts\u002Fcheck_env.py` when you need a quick import and backend smoke before a larger workflow.\n\n## Setup and smoke\n- Install the repo baseline with `python -m pip install -r requirements.txt`.\n- Install any workflow-specific extras called out by the nearest sub-skill references before sampling, serving, or evaluation.\n- Minimal import smoke: `python scripts\u002Fcheck_env.py --repo-root . --skip-cuda`.\n- CUDA smoke on a GPU host: `python scripts\u002Fcheck_env.py --repo-root . --with-serving --with-eval --with-gradio`.\n\n## Root guidance\nThis root skill is a router, not a manual. Read the nearest sub-skill for concrete commands, argument conventions, cache layouts, and troubleshooting.\n\n### Typical selection cues\n- VQ \u002F VQGAN \u002F VAE \u002F Consistency Decoder -> tokenizer sub-skill.\n- ImageNet code caches or FLAN-T5 features -> data-preparation sub-skill.\n- `train_c2i`, `sample_c2i`, `serve_c2i`, `eval c2i` -> class-conditional sub-skill.\n- `train_t2i`, `sample_t2i`, `evaluate t2i` -> text-conditional sub-skill.\n\n## Cross-cutting runtime notes\n- The repo is source-driven; future agents should rely on the bundled references and scripts rather than the original checkout layout.\n- Core workflows are CUDA-oriented. If `torch.cuda.is_available()` is false, the training \u002F generation routes are not ready.\n- Evaluation paths depend on extra packages such as TensorFlow, CLIP, and clean-fid; use the bundled troubleshooting notes before assuming a workflow is broken.\n- `app.py` is reference-only and should not be treated as a safe import-time runtime helper.\n\n## Useful bundled entry points\n- `scripts\u002Fcheck_env.py` for a quick import \u002F CUDA smoke.\n- `references\u002Frepo-routing-metadata.json` for router placement metadata.\n- `references\u002Ftroubleshooting.md` for cross-cutting install and runtime failures.\n\n## How to think about requests\n1. Identify whether the user is asking about tokenizers, preprocessing, c2i, or t2i.\n2. Route to the matching sub-skill.\n3. Use the sub-skill references for exact flags, layouts, and failure modes.\n4. Fall back to the root troubleshooting notes only for cross-cutting issues.\n","# LlamaGen\n\nUse this skill when the user asks about the LlamaGen repository, its released checkpoints, or its image-generation workflows.\n\n## What this skill owns\n- Tokenizer family workflows: VQ, VQGAN, Stable Diffusion VAE, and Consistency Decoder training or reconstruction.\n- Preprocessing workflows: discrete-code extraction, T5 feature extraction, OpenImages manifests, and dataset cache layout.\n- Class-conditional image generation: c2i training, sampling, serving, and c2i evaluation.\n- Text-conditional image generation: t2i stage-1 \u002F stage-2 training, prompt sampling, and t2i evaluation.\n\n## When to route where\n- Tokenizer training, finetuning, reconstruction, or code\u002Fimage round-trip checks -> `sub-skills\u002Ftokenizers\u002F`\n- Code\u002FT5 cache generation, OpenImages manifests, or dataset-layout questions -> `sub-skills\u002Fdata-preparation\u002F`\n- ImageNet class-conditional generation, serving, packaging, or c2i evaluation -> `sub-skills\u002Fclass-conditional\u002F`\n- Caption-conditioned training, sampling, or t2i evaluation -> `sub-skills\u002Ftext-conditional\u002F`\n\n## Before you start\n- Read `references\u002Frepo-provenance.md` to confirm the checkout snapshot.\n- Read `references\u002Ftroubleshooting.md` when the request mentions installs, imports, CUDA, checkpoints, caches, or evaluation dependencies.\n- Run `scripts\u002Fcheck_env.py` when you need a quick import and backend smoke before a larger workflow.\n\n## Setup and smoke\n- Install the repo baseline with `python -m pip install -r requirements.txt`.\n- Install any workflow-specific extras called out by the nearest sub-skill references before sampling, serving, or evaluation.\n- Minimal import smoke: `python scripts\u002Fcheck_env.py --repo-root . --skip-cuda`.\n- CUDA smoke on a GPU host: `python scripts\u002Fcheck_env.py --repo-root . --with-serving --with-eval --with-gradio`.\n\n## Root guidance\nThis root skill is a router, not a manual. Read the nearest sub-skill for concrete commands, argument conventions, cache layouts, and troubleshooting.\n\n### Typical selection cues\n- VQ \u002F VQGAN \u002F VAE \u002F Consistency Decoder -> tokenizer sub-skill.\n- ImageNet code caches or FLAN-T5 features -> data-preparation sub-skill.\n- `train_c2i`, `sample_c2i`, `serve_c2i`, `eval c2i` -> class-conditional sub-skill.\n- `train_t2i`, `sample_t2i`, `evaluate t2i` -> text-conditional sub-skill.\n\n## Cross-cutting runtime notes\n- The repo is source-driven; future agents should rely on the bundled references and scripts rather than the original checkout layout.\n- Core workflows are CUDA-oriented. If `torch.cuda.is_available()` is false, the training \u002F generation routes are not ready.\n- Evaluation paths depend on extra packages such as TensorFlow, CLIP, and clean-fid; use the bundled troubleshooting notes before assuming a workflow is broken.\n- `app.py` is reference-only and should not be treated as a safe import-time runtime helper.\n\n## Useful bundled entry points\n- `scripts\u002Fcheck_env.py` for a quick import \u002F CUDA smoke.\n- `references\u002Frepo-routing-metadata.json` for router placement metadata.\n- `references\u002Ftroubleshooting.md` for cross-cutting install and runtime failures.\n\n## How to think about requests\n1. Identify whether the user is asking about tokenizers, preprocessing, c2i, or t2i.\n2. Route to the matching sub-skill.\n3. Use the sub-skill references for exact flags, layouts, and failure modes.\n4. Fall back to the root troubleshooting notes only for cross-cutting issues.\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\u002Fllamagen",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 llamagen",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill llamagen",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill llamagen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fllamagen\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Frepo-provenance.md","REFERENCE","参考文档",820,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fllamagen\u002Freferences\u002Frepo-provenance.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-routing-metadata.json",418,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fllamagen\u002Freferences\u002Frepo-routing-metadata.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",4080,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fllamagen\u002Freferences\u002Ftroubleshooting.md",[63,71,76,83,90,97],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"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":72,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":70},"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":70},"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":70},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":70},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":70},"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",[],[]]