[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FC3KMCAYHSAC7GAWSPS7JW":3,"skill-same:01M7FC3KMCAYHSAC7GAWSPS7JW":67},{"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},"01M7FC3KMCAYHSAC7GAWSPS7JW","video-world-streaming",null,"Plan and troubleshoot Sana video-generation, long-video, world-model, and streaming V2V 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\u002F06-前端与设计\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: video-world-streaming\ndescription: \"Plan and troubleshoot Sana video-generation, long-video,\n  world-model, and streaming V2V workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# video-world-streaming\n\nUse this sub-skill when a future agent needs to plan, compare, or debug Sana video workflows that share the same video-generation stack but differ in prompt surface, camera control, long-context rollouts, or streaming editing.\n\n## Owns\n\n- SANA-Video text-to-video and image-to-video command planning at 480p and 720p.\n- The SANA-Video + LTX-2 refiner two-stage path for higher-fidelity 720p outputs.\n- LongSANA minute-scale rollout planning and frame-budget checks.\n- SANA-WM bidirectional, chunk-causal, and streaming world-model command planning.\n- SANA-Streaming `bidirectional_short` and `long_streaming` video-to-video editing.\n\n## Route elsewhere\n\n- Image-only generation -> `image-generation`.\n- Training recipes, dataset prep, or data-layout construction -> `training-data-configs`.\n- Metrics, conversion, export, or deployment -> `evaluation-conversion-deployment`.\n\n## Start here\n\n- [video-and-longsana.md](references\u002Fvideo-and-longsana.md) for SANA-Video, LTX-2 refiner, and LongSANA.\n- [world-model-and-streaming.md](references\u002Fworld-model-and-streaming.md) for SANA-WM and SANA-Streaming.\n- [data-formats.md](references\u002Fdata-formats.md) for prompt, frame, camera, intrinsics, and MP4 shapes.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for the common failure modes.\n\n## Safe helpers\n\n- [scripts\u002Fplan_sana_video_command.py](scripts\u002Fplan_sana_video_command.py) prints command templates and mode-specific warnings only.\n- [scripts\u002Fvalidate_camera_controls.py](scripts\u002Fvalidate_camera_controls.py) validates action DSL strings and `.npy` camera \u002F intrinsics arrays without running any model.\n\n## Quick routing rules\n\n- Use `sana-video` when the user wants a direct SANA-Video clip plan.\n- Use `sana-video-refiner` when the user wants base SANA-Video plus LTX-2 refinement.\n- Use `sana-wm` when the user wants camera-controlled world-model generation from an image, prompt, and action string or pose trajectory.\n- Use `sana-wm-streaming` when the user wants the chunk-pipelined world-model path, including fp8\u002Ffp4 planning and progressive MP4 output.\n- Use `sana-streaming-v2v` when the user wants source-video editing with `long_streaming` or `bidirectional_short`.\n\n## Planning rules\n\n- Prefer the bundled planner script before assembling a command by hand.\n- Validate camera or intrinsics files before planning a world-model command.\n- Treat `a\u002Fd` as yaw and `j\u002Fl` as strafe in the updated action mapping.\n- Treat `fp8` and `fp4` as precision choices that need explicit hardware awareness.\n- Treat frame counts as mode-specific constraints, not arbitrary numbers.\n\n## What to verify in a plan\n\n- Inputs match the workflow: prompt-only, prompt+image, prompt+camera, or source video.\n- The chosen resolution matches the workflow family: 480p, 720p, or minute-scale long rollouts.\n- The frame budget matches the workflow family and any snapping rules.\n- Memory-sensitive features such as the LTX-2 refiner, streaming refiner window, or precision downgrade are called out.\n- Output naming matches the workflow: final MP4, generated MP4, or progressive streaming MP4.\n\n## When the plan is probably wrong\n\n- The command uses the wrong workflow family for the requested input type.\n- The frame budget does not match the documented defaults or snapping rule.\n- The action string uses the old `a\u002Fd` and `j\u002Fl` meaning.\n- The plan assumes `fp4` without Blackwell-class hardware.\n- The plan omits the refiner, offload flags, or source-video length check where they matter.\n\n## Reading order for common requests\n\n1. Pick the workflow family and resolution in [video-and-longsana.md](references\u002Fvideo-and-longsana.md) or [world-model-and-streaming.md](references\u002Fworld-model-and-streaming.md).\n2. Check the data layout in [data-formats.md](references\u002Fdata-formats.md).\n3. Run [scripts\u002Fvalidate_camera_controls.py](scripts\u002Fvalidate_camera_controls.py) when the request uses `--action`, `--camera`, or `--intrinsics`.\n4. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when the request mentions HF downloads, VRAM, fp8\u002Ffp4, Pi3X, or short source-video decodes.\n\n## Boundary reminders\n\n- Do not use this sub-skill for image-only requests.\n- Do not turn training or evaluation requests into generation plans.\n- Do not depend on source checkout files at runtime; keep all reusable guidance inside this sub-skill tree.\n","# video-world-streaming\n\nUse this sub-skill when a future agent needs to plan, compare, or debug Sana video workflows that share the same video-generation stack but differ in prompt surface, camera control, long-context rollouts, or streaming editing.\n\n## Owns\n\n- SANA-Video text-to-video and image-to-video command planning at 480p and 720p.\n- The SANA-Video + LTX-2 refiner two-stage path for higher-fidelity 720p outputs.\n- LongSANA minute-scale rollout planning and frame-budget checks.\n- SANA-WM bidirectional, chunk-causal, and streaming world-model command planning.\n- SANA-Streaming `bidirectional_short` and `long_streaming` video-to-video editing.\n\n## Route elsewhere\n\n- Image-only generation -> `image-generation`.\n- Training recipes, dataset prep, or data-layout construction -> `training-data-configs`.\n- Metrics, conversion, export, or deployment -> `evaluation-conversion-deployment`.\n\n## Start here\n\n- [video-and-longsana.md](references\u002Fvideo-and-longsana.md) for SANA-Video, LTX-2 refiner, and LongSANA.\n- [world-model-and-streaming.md](references\u002Fworld-model-and-streaming.md) for SANA-WM and SANA-Streaming.\n- [data-formats.md](references\u002Fdata-formats.md) for prompt, frame, camera, intrinsics, and MP4 shapes.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for the common failure modes.\n\n## Safe helpers\n\n- [scripts\u002Fplan_sana_video_command.py](scripts\u002Fplan_sana_video_command.py) prints command templates and mode-specific warnings only.\n- [scripts\u002Fvalidate_camera_controls.py](scripts\u002Fvalidate_camera_controls.py) validates action DSL strings and `.npy` camera \u002F intrinsics arrays without running any model.\n\n## Quick routing rules\n\n- Use `sana-video` when the user wants a direct SANA-Video clip plan.\n- Use `sana-video-refiner` when the user wants base SANA-Video plus LTX-2 refinement.\n- Use `sana-wm` when the user wants camera-controlled world-model generation from an image, prompt, and action string or pose trajectory.\n- Use `sana-wm-streaming` when the user wants the chunk-pipelined world-model path, including fp8\u002Ffp4 planning and progressive MP4 output.\n- Use `sana-streaming-v2v` when the user wants source-video editing with `long_streaming` or `bidirectional_short`.\n\n## Planning rules\n\n- Prefer the bundled planner script before assembling a command by hand.\n- Validate camera or intrinsics files before planning a world-model command.\n- Treat `a\u002Fd` as yaw and `j\u002Fl` as strafe in the updated action mapping.\n- Treat `fp8` and `fp4` as precision choices that need explicit hardware awareness.\n- Treat frame counts as mode-specific constraints, not arbitrary numbers.\n\n## What to verify in a plan\n\n- Inputs match the workflow: prompt-only, prompt+image, prompt+camera, or source video.\n- The chosen resolution matches the workflow family: 480p, 720p, or minute-scale long rollouts.\n- The frame budget matches the workflow family and any snapping rules.\n- Memory-sensitive features such as the LTX-2 refiner, streaming refiner window, or precision downgrade are called out.\n- Output naming matches the workflow: final MP4, generated MP4, or progressive streaming MP4.\n\n## When the plan is probably wrong\n\n- The command uses the wrong workflow family for the requested input type.\n- The frame budget does not match the documented defaults or snapping rule.\n- The action string uses the old `a\u002Fd` and `j\u002Fl` meaning.\n- The plan assumes `fp4` without Blackwell-class hardware.\n- The plan omits the refiner, offload flags, or source-video length check where they matter.\n\n## Reading order for common requests\n\n1. Pick the workflow family and resolution in [video-and-longsana.md](references\u002Fvideo-and-longsana.md) or [world-model-and-streaming.md](references\u002Fworld-model-and-streaming.md).\n2. Check the data layout in [data-formats.md](references\u002Fdata-formats.md).\n3. Run [scripts\u002Fvalidate_camera_controls.py](scripts\u002Fvalidate_camera_controls.py) when the request uses `--action`, `--camera`, or `--intrinsics`.\n4. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when the request mentions HF downloads, VRAM, fp8\u002Ffp4, Pi3X, or short source-video decodes.\n\n## Boundary reminders\n\n- Do not use this sub-skill for image-only requests.\n- Do not turn training or evaluation requests into generation plans.\n- Do not depend on source checkout files at runtime; keep all reusable guidance inside this sub-skill tree.\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\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming",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 video-world-streaming",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill video-world-streaming",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill video-world-streaming","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\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdata-formats.md","REFERENCE","参考文档",8280,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002Freferences\u002Fdata-formats.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftroubleshooting.md",9807,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002Freferences\u002Ftroubleshooting.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fvideo-and-longsana.md",9865,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002Freferences\u002Fvideo-and-longsana.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fworld-model-and-streaming.md",12048,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fsana\u002Fsub-skills\u002Fvideo-world-streaming\u002Freferences\u002Fworld-model-and-streaming.md",[68,76,81,88,95,102],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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",[],[]]