[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EHMFPGNDT216YN4P360XMD":3,"skill-same:01M7EHMFPGNDT216YN4P360XMD":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},"01M7EHMFPGNDT216YN4P360XMD","inference-and-rendering",null,"Load DeTikZify models and adapters, build inference pipelines, generate TikZ, compile and rasterize documents, and troubleshoot programmatic synthesis workflows.","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\u002F04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-and-rendering\ndescription: \"Load DeTikZify models and adapters, build inference pipelines,\n  generate TikZ, compile and rasterize documents, and troubleshoot programmatic\n  synthesis workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Inference and Rendering\n\nUse this sub-skill when the task is about DeTikZify's Python inference surface: model loading, processor handling, adapter-backed text conditioning, `DetikzifyPipeline`, `DetikzifyGenerator`, `TikzDocument`, compile\u002Frasterize\u002Fsave, or MCTS-backed sampling.\n\nRoute away from this sub-skill when the main task is the browser UI, training loops, evaluation metrics, or dataset builders. Those workflows have dedicated sub-skills.\n\n## Fast Path\n\n1. Confirm the package imports and the public API surface is present:\n   ```bash\n   python scripts\u002Fapi_smoke.py\n   ```\n2. For a rendering-specific smoke, compile a tiny document through the bundled helper:\n   ```bash\n   python scripts\u002Ftikz_smoke.py\n   ```\n3. If you need search-based synthesis or tree-search behavior, run the MCTS helper:\n   ```bash\n   python scripts\u002Fmcts_smoke.py\n   ```\n\n## What This Sub-Skill Owns\n\n- `detikzify.model.load(...)` and `detikzify.model.load_adapter(...)`\n- `DetikzifyProcessor` and `AdapterProcessor`\n- `DetikzifyPipeline.sample(...)` and `DetikzifyPipeline.simulate(...)`\n- `DetikzifyGenerator` and the MCTS bridge used inside the pipeline\n- `TikzDocument.compile()`, `rasterize()`, `save()`, and error inspection\n- image loading \u002F preprocessing helpers that feed inference or rendering\n- text-conditioned generation when an adapter is loaded\n\n## Common Decisions\n\n- Use `load(model_name_or_path, ...)` for image-conditioned generation with the default processor flow.\n- Use `load_adapter(...)` or a model that already carries an adapter when the request needs text prompts.\n- Use `sample(...)` for a single best TikZ program and `simulate(...)` when the user wants search \u002F multiple candidates.\n- Treat `metric=\"model\"` as the perceptual path and `metric=\"fast\"` as the compiler-diagnostics path.\n- Set `preprocess=True` when you want the image trimmed and padded to a square before generation.\n- Check `compile_timeout` and `mcts_timeout` separately; they control different stages.\n\n## Bundled References\n\n- [references\u002Fapi-reference.md](references\u002Fapi-reference.md): signatures and object roles for the public inference surface.\n- [references\u002Fworkflows.md](references\u002Fworkflows.md): image-conditioned, text-conditioned, save\u002Frasterize, and search-based workflows.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): adapter, CUDA, image-source, and compile\u002Frasterize failure modes.\n\n## Related Helpers\n\n- [..\u002F..\u002Fscripts\u002Fapi_smoke.py](..\u002F..\u002Fscripts\u002Fapi_smoke.py): safe import and signature snapshot.\n- [..\u002F..\u002Fscripts\u002Ftikz_smoke.py](..\u002F..\u002Fscripts\u002Ftikz_smoke.py): safe TeX compile\u002Frasterize smoke.\n- [..\u002F..\u002Fscripts\u002Fmcts_smoke.py](..\u002F..\u002Fscripts\u002Fmcts_smoke.py): safe dummy-state MCTS sanity check.\n\n## Guardrails\n\n- A CPU import does not prove the GPU path works.\n- Do not assume text prompts work unless an adapter-capable load path is active.\n- Do not treat compile success as proof that the output is non-empty; check the rasterized result too.\n","# Inference and Rendering\n\nUse this sub-skill when the task is about DeTikZify's Python inference surface: model loading, processor handling, adapter-backed text conditioning, `DetikzifyPipeline`, `DetikzifyGenerator`, `TikzDocument`, compile\u002Frasterize\u002Fsave, or MCTS-backed sampling.\n\nRoute away from this sub-skill when the main task is the browser UI, training loops, evaluation metrics, or dataset builders. Those workflows have dedicated sub-skills.\n\n## Fast Path\n\n1. Confirm the package imports and the public API surface is present:\n   ```bash\n   python scripts\u002Fapi_smoke.py\n   ```\n2. For a rendering-specific smoke, compile a tiny document through the bundled helper:\n   ```bash\n   python scripts\u002Ftikz_smoke.py\n   ```\n3. If you need search-based synthesis or tree-search behavior, run the MCTS helper:\n   ```bash\n   python scripts\u002Fmcts_smoke.py\n   ```\n\n## What This Sub-Skill Owns\n\n- `detikzify.model.load(...)` and `detikzify.model.load_adapter(...)`\n- `DetikzifyProcessor` and `AdapterProcessor`\n- `DetikzifyPipeline.sample(...)` and `DetikzifyPipeline.simulate(...)`\n- `DetikzifyGenerator` and the MCTS bridge used inside the pipeline\n- `TikzDocument.compile()`, `rasterize()`, `save()`, and error inspection\n- image loading \u002F preprocessing helpers that feed inference or rendering\n- text-conditioned generation when an adapter is loaded\n\n## Common Decisions\n\n- Use `load(model_name_or_path, ...)` for image-conditioned generation with the default processor flow.\n- Use `load_adapter(...)` or a model that already carries an adapter when the request needs text prompts.\n- Use `sample(...)` for a single best TikZ program and `simulate(...)` when the user wants search \u002F multiple candidates.\n- Treat `metric=\"model\"` as the perceptual path and `metric=\"fast\"` as the compiler-diagnostics path.\n- Set `preprocess=True` when you want the image trimmed and padded to a square before generation.\n- Check `compile_timeout` and `mcts_timeout` separately; they control different stages.\n\n## Bundled References\n\n- [references\u002Fapi-reference.md](references\u002Fapi-reference.md): signatures and object roles for the public inference surface.\n- [references\u002Fworkflows.md](references\u002Fworkflows.md): image-conditioned, text-conditioned, save\u002Frasterize, and search-based workflows.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): adapter, CUDA, image-source, and compile\u002Frasterize failure modes.\n\n## Related Helpers\n\n- [..\u002F..\u002Fscripts\u002Fapi_smoke.py](..\u002F..\u002Fscripts\u002Fapi_smoke.py): safe import and signature snapshot.\n- [..\u002F..\u002Fscripts\u002Ftikz_smoke.py](..\u002F..\u002Fscripts\u002Ftikz_smoke.py): safe TeX compile\u002Frasterize smoke.\n- [..\u002F..\u002Fscripts\u002Fmcts_smoke.py](..\u002F..\u002Fscripts\u002Fmcts_smoke.py): safe dummy-state MCTS sanity check.\n\n## Guardrails\n\n- A CPU import does not prove the GPU path works.\n- Do not assume text prompts work unless an adapter-capable load path is active.\n- Do not treat compile success as proof that the output is non-empty; check the rasterized result too.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering",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 inference-and-rendering",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-and-rendering",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-and-rendering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-reference.md","REFERENCE","参考文档",2429,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering\u002Freferences\u002Fapi-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftroubleshooting.md",1278,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering\u002Freferences\u002Ftroubleshooting.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fworkflows.md",1604,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fdetikzify\u002Fsub-skills\u002Finference-and-rendering\u002Freferences\u002Fworkflows.md",[64,73,78,85,92,99],{"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":72},"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",[],[],"2026-11-16 10:05:34",{"skillNo":74,"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":75,"categories":76,"keywords":77,"publishedAt":72},"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":72},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":72},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":72},"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":72},"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",[],[]]