[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F76R57QE2R1617P3CZ8FN3":3,"skill-same:01M7F76R57QE2R1617P3CZ8FN3":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},"01M7F76R57QE2R1617P3CZ8FN3","3d-resnets-pytorch",null,"Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.","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\u002F06-前端与设计\u002F3d-resnets-pytorch\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: \"3d-resnets-pytorch\"\ndescription: \"Routes 3D ResNets PyTorch video action-recognition workflows\n  across training, inference, and data preparation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# 3D ResNets PyTorch\n\nUse this root skill when the user asks about the 3D ResNets PyTorch repository, its CLI flags, its dataset layouts, or its video action-recognition workflows.\n\n## Read first\n\n- `references\u002Fcli-reference.md`\n- `references\u002Ftroubleshooting.md`\n- `references\u002Frepo-provenance.md`\n- `scripts\u002Fcheck_imports.py`\n- `scripts\u002Fcheck_main_help.py`\n\n## What this skill covers\n\n- Training, validation, inference, and fine-tuning for video action recognition.\n- Dataset preparation from raw videos into JPEG frame trees, RGB HDF5 files, and annotation JSONs.\n- Checkpoint handling, model-family selection, and result evaluation.\n- Common data-layout and runtime compatibility pitfalls.\n\n## Route to a sub-skill\n\n### `training-and-inference`\nUse this route for:\n\n- Fresh training runs, resume flows, and pretrained fine-tuning.\n- Validation-only runs and sliding-window inference.\n- Result scoring and DataParallel checkpoint cleanup.\n- Questions about model families, class counts, `ft_begin_module`, or `resume_path` \u002F `pretrain_path` behavior.\n\nRead:\n\n- `sub-skills\u002Ftraining-and-inference\u002FSKILL.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Fworkflows.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Fmodel-catalog.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Ftroubleshooting.md`\n- `sub-skills\u002Ftraining-and-inference\u002Fscripts\u002Fevaluate_results.py`\n- `sub-skills\u002Ftraining-and-inference\u002Fscripts\u002Fstrip_dataparallel.py`\n\n### `data-preparation`\nUse this route for:\n\n- Extracting JPEG frames or RGB HDF5 files from raw videos.\n- Building Kinetics, UCF101, HMDB51, MIT, or ActivityNet JSON metadata.\n- Adding ActivityNet `fps` fields.\n- Questions about class directories, split files, HDF5 manifests, or `jpg` versus `hdf5` layout.\n\nRead:\n\n- `sub-skills\u002Fdata-preparation\u002FSKILL.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Fworkflows.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Fdata-formats.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Ftroubleshooting.md`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fextract_video_frames.py`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fextract_video_hdf5.py`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fbuild_annotation_json.py`\n\n## Quick runtime helpers\n\n- `scripts\u002Fcheck_imports.py` verifies that the core source modules import from a checkout and applies the temporary legacy `Scale` alias when needed.\n- `scripts\u002Fcheck_main_help.py` prints the full `main.py` CLI help through the same compatibility shim.\n- `scripts\u002Frun_main.py` forwards into the repository CLI after preparing the checkout and compatibility shim.\n\n## Shared environment facts\n\nThis repo expects a Python environment with PyTorch, torchvision, pandas, h5py, scikit-learn, joblib, and FFmpeg\u002FFFprobe available on PATH.\n\nA modern torchvision wheel may not expose `torchvision.transforms.Scale`. If that happens, use the compatibility shim in `scripts\u002F_torchvision_compat.py` or a legacy torchvision release that still ships `Scale`.\n\n## Route selection guidance\n\n- If the user already has prepared videos and annotation JSONs, start with `training-and-inference`.\n- If the user still needs frames, HDF5 files, or split JSONs, start with `data-preparation`.\n- If the request mentions both, do data preparation first unless the videos and labels are already ready.\n- If the user only wants command discovery or environment checks, use the root helpers and the sub-skill references rather than reopening the source repo.\n\n## Common handoff sequence\n\n1. Prepare or verify the dataset layout with `data-preparation`.\n2. Verify the environment with `scripts\u002Fcheck_imports.py`.\n3. Inspect the CLI with `scripts\u002Fcheck_main_help.py`.\n4. Run the desired training or inference command with `scripts\u002Frun_main.py`.\n5. Score or clean outputs with the training-and-inference helpers.\n\n## Don’t do this\n\n- Do not point future agents back to the original checkout paths.\n- Do not use `flow` with JPEG inputs.\n- Do not assume resume checkpoints can change architecture.\n- Do not score `--inference_no_average` JSON with the result evaluator before aggregating segment outputs.\n","# 3D ResNets PyTorch\n\nUse this root skill when the user asks about the 3D ResNets PyTorch repository, its CLI flags, its dataset layouts, or its video action-recognition workflows.\n\n## Read first\n\n- `references\u002Fcli-reference.md`\n- `references\u002Ftroubleshooting.md`\n- `references\u002Frepo-provenance.md`\n- `scripts\u002Fcheck_imports.py`\n- `scripts\u002Fcheck_main_help.py`\n\n## What this skill covers\n\n- Training, validation, inference, and fine-tuning for video action recognition.\n- Dataset preparation from raw videos into JPEG frame trees, RGB HDF5 files, and annotation JSONs.\n- Checkpoint handling, model-family selection, and result evaluation.\n- Common data-layout and runtime compatibility pitfalls.\n\n## Route to a sub-skill\n\n### `training-and-inference`\nUse this route for:\n\n- Fresh training runs, resume flows, and pretrained fine-tuning.\n- Validation-only runs and sliding-window inference.\n- Result scoring and DataParallel checkpoint cleanup.\n- Questions about model families, class counts, `ft_begin_module`, or `resume_path` \u002F `pretrain_path` behavior.\n\nRead:\n\n- `sub-skills\u002Ftraining-and-inference\u002FSKILL.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Fworkflows.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Fmodel-catalog.md`\n- `sub-skills\u002Ftraining-and-inference\u002Freferences\u002Ftroubleshooting.md`\n- `sub-skills\u002Ftraining-and-inference\u002Fscripts\u002Fevaluate_results.py`\n- `sub-skills\u002Ftraining-and-inference\u002Fscripts\u002Fstrip_dataparallel.py`\n\n### `data-preparation`\nUse this route for:\n\n- Extracting JPEG frames or RGB HDF5 files from raw videos.\n- Building Kinetics, UCF101, HMDB51, MIT, or ActivityNet JSON metadata.\n- Adding ActivityNet `fps` fields.\n- Questions about class directories, split files, HDF5 manifests, or `jpg` versus `hdf5` layout.\n\nRead:\n\n- `sub-skills\u002Fdata-preparation\u002FSKILL.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Fworkflows.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Fdata-formats.md`\n- `sub-skills\u002Fdata-preparation\u002Freferences\u002Ftroubleshooting.md`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fextract_video_frames.py`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fextract_video_hdf5.py`\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fbuild_annotation_json.py`\n\n## Quick runtime helpers\n\n- `scripts\u002Fcheck_imports.py` verifies that the core source modules import from a checkout and applies the temporary legacy `Scale` alias when needed.\n- `scripts\u002Fcheck_main_help.py` prints the full `main.py` CLI help through the same compatibility shim.\n- `scripts\u002Frun_main.py` forwards into the repository CLI after preparing the checkout and compatibility shim.\n\n## Shared environment facts\n\nThis repo expects a Python environment with PyTorch, torchvision, pandas, h5py, scikit-learn, joblib, and FFmpeg\u002FFFprobe available on PATH.\n\nA modern torchvision wheel may not expose `torchvision.transforms.Scale`. If that happens, use the compatibility shim in `scripts\u002F_torchvision_compat.py` or a legacy torchvision release that still ships `Scale`.\n\n## Route selection guidance\n\n- If the user already has prepared videos and annotation JSONs, start with `training-and-inference`.\n- If the user still needs frames, HDF5 files, or split JSONs, start with `data-preparation`.\n- If the request mentions both, do data preparation first unless the videos and labels are already ready.\n- If the user only wants command discovery or environment checks, use the root helpers and the sub-skill references rather than reopening the source repo.\n\n## Common handoff sequence\n\n1. Prepare or verify the dataset layout with `data-preparation`.\n2. Verify the environment with `scripts\u002Fcheck_imports.py`.\n3. Inspect the CLI with `scripts\u002Fcheck_main_help.py`.\n4. Run the desired training or inference command with `scripts\u002Frun_main.py`.\n5. Score or clean outputs with the training-and-inference helpers.\n\n## Don’t do this\n\n- Do not point future agents back to the original checkout paths.\n- Do not use `flow` with JPEG inputs.\n- Do not assume resume checkpoints can change architecture.\n- Do not score `--inference_no_average` JSON with the result evaluator before aggregating segment outputs.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002F3d-resnets-pytorch",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 3d-resnets-pytorch",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill 3d-resnets-pytorch",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill 3d-resnets-pytorch","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\u002F3d-resnets-pytorch\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcli-reference.md","REFERENCE","参考文档",2207,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002F3d-resnets-pytorch\u002Freferences\u002Fcli-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",1097,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002F3d-resnets-pytorch\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",342,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002F3d-resnets-pytorch\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",2033,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002F3d-resnets-pytorch\u002Freferences\u002Ftroubleshooting.md",[67,74,79,86,93,100],{"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":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.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"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":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]