[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-bca17f13":3,"seo:featured-workflow:bca17f13-4ddd-11f1-9bc6-00163e2b0d79:zh":85,"workflow-related-asset-bca17f13-bca17f13-4ddd-11f1-9bc6-00163e2b0d79":86},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":12,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":14,"tags":21,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":28,"asset_kind":29,"target_tools":30,"install_mode":34,"entrypoint":18,"risk_profile":35,"dependencies":37,"verification":45,"agent_metadata":48,"agent_fit":61,"trust":73,"provenance":82,"created_at":84,"updated_at":84},3249,"bca17f13-4ddd-11f1-9bc6-00163e2b0d79","asset-bca17f13","MMAction2 — OpenMMLab Video Understanding Toolbox","MMAction2 provides a modular framework for action recognition, temporal action detection, and spatial-temporal action detection with 20+ methods and support for major video benchmarks.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot","",0,"en",[15],{"id":16,"step_order":17,"title":18,"description":11,"prompt_template":19,"variables":11,"depends_on":20,"expected_output":11},3812,1,"MMAction2 Video AI","# MMAction2 — OpenMMLab Video Understanding Toolbox\n\n## Quick Use\n```bash\npip install mmaction2 mmengine mmcv\npython demo\u002Fdemo.py \n    configs\u002Frecognition\u002Ftsn\u002Ftsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py \n    https:\u002F\u002Fdownload.openmmlab.com\u002Fmmaction\u002Frecognition\u002Ftsn\u002Ftsn_r50_1x1x3_100e_kinetics400_rgb.pth \n    demo\u002Fdemo.mp4 tools\u002Fdata\u002Fkinetics\u002Flabel_map_k400.txt\n```\n\n## Introduction\nMMAction2 is the next-generation video understanding toolbox from OpenMMLab. It covers action recognition, temporal action localization, and spatial-temporal action detection, providing a consistent PyTorch-based framework for researchers and practitioners working with video data.\n\n## What MMAction2 Does\n- Classifies human actions in video clips using 20+ recognition models\n- Localizes action segments temporally within untrimmed videos\n- Detects actions in space and time with spatial-temporal models\n- Supports skeleton-based action recognition via PoseC3D\n- Benchmarks on Kinetics, Something-Something, AVA, and more\n\n## Architecture Overview\nMMAction2 uses MMEngine as its training backend with a registry pattern for models, datasets, and pipelines. Recognition models process fixed-length clips through backbones like ResNet3D, SlowFast, or Video Swin Transformer. Temporal detectors use proposal generation and classification stages. All components are configured via Python config files.\n\n## Self-Hosting & Configuration\n- Install mmaction2, mmengine, and mmcv via pip\n- Download pre-trained checkpoints from the model zoo\n- Prepare video datasets in the expected directory structure\n- Modify config files for custom class labels and data paths\n- Use torchrun for multi-GPU distributed training\n\n## Key Features\n- Comprehensive coverage of action recognition paradigms (RGB, flow, skeleton)\n- UniFormerV2 and VideoMAE models achieve state-of-the-art on Kinetics\n- Modular design allows swapping backbones and temporal heads\n- Pre-built data pipelines for common video dataset formats\n- Integration with MMDeploy for production model conversion\n\n## Comparison with Similar Tools\n- **SlowFast (FAIR)** — reference implementation of the SlowFast network; MMAction2 includes SlowFast plus many other methods\n- **PyTorchVideo** — provides video-specific transforms and models; MMAction2 offers a broader set of methods and benchmarks\n- **TimeSformer** — single Transformer architecture; MMAction2 supports TimeSformer alongside CNN and hybrid approaches\n- **Decord** — video decoding library; MMAction2 uses Decord internally but adds full training and evaluation pipelines\n\n## FAQ\n**Q: Can I use MMAction2 for real-time action detection?**\nA: Yes. Lightweight models like MobileNetV2-TSM can run in real time on modern GPUs.\n\n**Q: Does it support skeleton-based recognition?**\nA: Yes. PoseC3D and ST-GCN models accept skeleton sequences extracted with MMPose.\n\n**Q: What video formats are supported?**\nA: MMAction2 reads any format supported by Decord or OpenCV, including MP4, AVI, and MKV.\n\n**Q: Can I fine-tune on my own action classes?**\nA: Yes. Update the label map and annotation files, then fine-tune from a Kinetics-pretrained checkpoint.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002Fopen-mmlab\u002Fmmaction2\n- https:\u002F\u002Fmmaction2.readthedocs.io\u002F","0",[22],{"id":23,"name":24,"slug":25,"icon":26},11,"Scripts","script","📜",false,"fc52b93e757d642599879a0899edd87d7519346d31a56efd74b073f064a5b9c8","skill",[31,32,33],"claude_code","codex","gemini_cli","single",{"executes_code":27,"modifies_global_config":27,"requires_secrets":36,"uses_absolute_paths":27,"network_access":27},[],{"npm":38,"pip":39,"brew":43,"system":44},[],[40,41,42],"mmaction2","mmcv","mmengine",[],[],{"commands":46,"expected_files":47},[],[18],{"asset_kind":29,"target_tools":49,"install_mode":34,"entrypoint":18,"risk_profile":50,"dependencies":52,"content_hash":28,"verification":57,"inferred":60},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":51,"uses_absolute_paths":27,"network_access":27},[],{"npm":53,"pip":54,"brew":55,"system":56},[],[40,41,42],[],[],{"commands":58,"expected_files":59},[],[18],true,{"target":32,"score":62,"status":63,"policy":64,"why":65,"asset_kind":29,"install_mode":34},98,"native","allow",[66,67,68,69,70,71,72],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":74,"verified_publisher":27,"asset_signed_hash":28,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":76,"review_status":77,"signals":78},"established","hash_only",[],"unreviewed",[79,80,81],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":83,"content_hash":28,"visibility":17,"created_at":84,"updated_at":84},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-bca17f13","2026-05-12 16:36:57",null,[87,137,184,233],{"id":88,"uuid":89,"slug":90,"title":91,"description":92,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":12,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":93,"tags":94,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":96,"asset_kind":29,"target_tools":97,"install_mode":34,"entrypoint":98,"risk_profile":99,"dependencies":101,"verification":106,"agent_metadata":109,"agent_fit":121,"trust":123,"provenance":126,"created_at":128,"updated_at":128,"__relatedScore":129,"__relatedReasons":130,"__sharedTags":135},3245,"7c63094f-4ddd-11f1-9bc6-00163e2b0d79","asset-7c63094f","MMSegmentation — OpenMMLab Semantic Segmentation Toolbox","MMSegmentation is a comprehensive semantic segmentation toolbox based on PyTorch, providing 50+ segmentation methods with a unified benchmark and modular design.",[],[95],{"id":23,"name":24,"slug":25,"icon":26},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[31,32,33],"SKILL.md",{"executes_code":27,"modifies_global_config":27,"requires_secrets":100,"uses_absolute_paths":27,"network_access":27},[],{"npm":102,"pip":103,"brew":104,"system":105},[],[],[],[],{"commands":107,"expected_files":108},[],[],{"asset_kind":29,"target_tools":110,"install_mode":34,"entrypoint":98,"risk_profile":111,"dependencies":113,"content_hash":96,"verification":118,"inferred":60},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":112,"uses_absolute_paths":27,"network_access":27},[],{"npm":114,"pip":115,"brew":116,"system":117},[],[],[],[],{"commands":119,"expected_files":120},[],[],{"target":32,"score":62,"status":63,"policy":64,"why":122,"asset_kind":29,"install_mode":34},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":27,"asset_signed_hash":96,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":124,"review_status":77,"signals":125},[],[79,80,81],{"owner_uuid":9,"owner_name":10,"source_url":127,"content_hash":96,"visibility":17,"created_at":128,"updated_at":128},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-7c63094f","2026-05-12 16:35:09",100,[131,132,133,134],"topic-match","same-kind","same-target","same-author",[25,136],"scripts",{"id":138,"uuid":139,"slug":140,"title":141,"description":142,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":143,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":144,"tags":145,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":147,"asset_kind":29,"target_tools":148,"install_mode":34,"entrypoint":149,"risk_profile":150,"dependencies":152,"verification":157,"agent_metadata":160,"agent_fit":172,"trust":174,"provenance":177,"created_at":179,"updated_at":180,"__relatedScore":181,"__relatedReasons":182,"__sharedTags":183},2458,"7e2317bb-453a-11f1-9bc6-00163e2b0d79","cogvideo-text-image-video-generation-7e2317bb","CogVideo — Text and Image to Video Generation","An open-source video generation framework from Zhipu AI supporting text-to-video and image-to-video with CogVideoX models. Generates high-quality clips up to 6 seconds.",79,[],[146],{"id":23,"name":24,"slug":25,"icon":26},"4a26ff53462e623ca42b9cec2ef2df5a01afa8fe0735e8fdf42b5dad217a44a6",[31,32,33],"CogVideo Overview",{"executes_code":27,"modifies_global_config":27,"requires_secrets":151,"uses_absolute_paths":27,"network_access":27},[],{"npm":153,"pip":154,"brew":155,"system":156},[],[],[],[],{"commands":158,"expected_files":159},[],[149],{"asset_kind":29,"target_tools":161,"install_mode":34,"entrypoint":149,"risk_profile":162,"dependencies":164,"content_hash":147,"verification":169},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":163,"uses_absolute_paths":27,"network_access":27},[],{"npm":165,"pip":166,"brew":167,"system":168},[],[],[],[],{"commands":170,"expected_files":171},[],[149],{"target":32,"score":62,"status":63,"policy":64,"why":173,"asset_kind":29,"install_mode":34},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":27,"asset_signed_hash":147,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":175,"review_status":77,"signals":176},[],[79,80,81],{"owner_uuid":9,"owner_name":10,"source_url":178,"content_hash":147,"visibility":17,"created_at":179,"updated_at":180},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcogvideo-text-image-video-generation-7e2317bb","2026-05-01 16:48:15","2026-05-12 14:26:04",85.85463498048792,[131,132,133,134],[25,136],{"id":185,"uuid":186,"slug":187,"title":188,"description":189,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":190,"time_saved":12,"model_used":191,"fork_count":12,"vote_count":12,"view_count":192,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":193,"tags":194,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":196,"asset_kind":29,"target_tools":197,"install_mode":34,"entrypoint":188,"risk_profile":198,"dependencies":200,"verification":205,"agent_metadata":208,"agent_fit":220,"trust":222,"provenance":226,"created_at":228,"updated_at":229,"__relatedScore":230,"__relatedReasons":231,"__sharedTags":232},104,"57b68929-f919-474a-99f1-81ac76e0bce6","moviepy-python-video-editing-library-57b68929","MoviePy — Python Video Editing Library","Python library for video editing: cutting, concatenating, adding titles, effects, and audio. Script-based video production for automation pipelines.",500,"Claude Code",390,[],[195],{"id":23,"name":24,"slug":25,"icon":26},"e5e02dd5dbc90f55da884bf59e06291d7f4f1ef1282bb146817b5b827b310c22",[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":199,"uses_absolute_paths":27,"network_access":27},[],{"npm":201,"pip":202,"brew":203,"system":204},[],[],[],[],{"commands":206,"expected_files":207},[],[188],{"asset_kind":29,"target_tools":209,"install_mode":34,"entrypoint":188,"risk_profile":210,"dependencies":212,"content_hash":196,"verification":217},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":211,"uses_absolute_paths":27,"network_access":27},[],{"npm":213,"pip":214,"brew":215,"system":216},[],[],[],[],{"commands":218,"expected_files":219},[],[188],{"target":32,"score":62,"status":63,"policy":64,"why":221,"asset_kind":29,"install_mode":34},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":27,"asset_signed_hash":196,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":223,"review_status":77,"signals":224},[],[225,79,80,81],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":227,"content_hash":196,"visibility":17,"created_at":228,"updated_at":229},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fmoviepy-python-video-editing-library-57b68929","2026-03-29 16:58:49","2026-05-12 19:12:34",83.88826513609379,[131,132,133,134],[25,136],{"id":234,"uuid":235,"slug":236,"title":237,"description":238,"author_id":239,"author_name":240,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":241,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":242,"tags":243,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":96,"asset_kind":29,"target_tools":249,"install_mode":34,"entrypoint":98,"risk_profile":250,"dependencies":252,"verification":257,"agent_metadata":260,"agent_fit":272,"trust":274,"provenance":277,"created_at":279,"updated_at":280,"__relatedScore":281,"__relatedReasons":282,"__sharedTags":283},3246,"8d12bfc9-4ddd-11f1-9bc6-00163e2b0d79","asset-8d12bfc9","MMPose — OpenMMLab Pose Estimation Toolbox","MMPose provides a modular framework for 2D and 3D pose estimation covering human body, hand, face, and animal keypoint detection with 30+ state-of-the-art methods.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source",2,[],[244],{"id":245,"name":246,"slug":247,"icon":248},12,"Configs","config","⚙️",[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":251,"uses_absolute_paths":27,"network_access":27},[],{"npm":253,"pip":254,"brew":255,"system":256},[],[],[],[],{"commands":258,"expected_files":259},[],[],{"asset_kind":29,"target_tools":261,"install_mode":34,"entrypoint":98,"risk_profile":262,"dependencies":264,"content_hash":96,"verification":269,"inferred":60},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":263,"uses_absolute_paths":27,"network_access":27},[],{"npm":265,"pip":266,"brew":267,"system":268},[],[],[],[],{"commands":270,"expected_files":271},[],[],{"target":32,"score":62,"status":63,"policy":64,"why":273,"asset_kind":29,"install_mode":34},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":27,"asset_signed_hash":96,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":275,"review_status":77,"signals":276},[],[79,80,81],{"owner_uuid":239,"owner_name":240,"source_url":278,"content_hash":96,"visibility":17,"created_at":279,"updated_at":280},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-8d12bfc9","2026-05-12 16:35:37","2026-05-12 19:50:33",83.7156818820795,[131,132,133],[]]