[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FAP4TFND6VP0VAVQAAXG7B":3,"skill-same:01M7FAP4TFND6VP0VAVQAAXG7B":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},"01M7FAP4TFND6VP0VAVQAAXG7B","runtime-utilities-and-visualization",null,"Use MMEngine logging, message hubs, visualizer backends, distributed and device utilities, environment checks, timers, progress bars, manager mixins, and testing helpers safely.","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\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: runtime-utilities-and-visualization\ndescription: \"Use MMEngine logging, message hubs, visualizer backends,\n  distributed and device utilities, environment checks, timers, progress bars,\n  manager mixins, and testing helpers safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Runtime Utilities and Visualization\n\nUse this sub-skill when a task mentions `MMLogger`, `print_log`, `MessageHub`, `Visualizer`, `LocalVisBackend`, `TensorboardVisBackend`, `WandbVisBackend`, MLflow\u002FClearML\u002FAim\u002FDVCLive\u002FNeptune backends, `init_dist`, `get_dist_info`, `collect_results`, `master_only`, `get_device`, `collect_env`, `ManagerMixin`, progress bars, `Timer`, or MMEngine testing helpers.\n\n## Read Order\n\n- [references\u002Flogging-visualization-workflows.md](references\u002Flogging-visualization-workflows.md): Choose and use loggers, message hubs, visualizers, local outputs, and optional tracking-service backends.\n- [references\u002Fdistributed-device-utilities.md](references\u002Fdistributed-device-utilities.md): Use distributed rank helpers, safe result collection, device detection, environment reports, timers, progress helpers, manager mixins, and testing utilities.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): Diagnose duplicate loggers, optional backend dependency failures, visualization output surprises, distributed no-op behavior, collection mismatches, device fallback, and test-helper pitfalls.\n- [scripts\u002Fruntime_env_check.py](scripts\u002Fruntime_env_check.py): Run a safe local import\u002Fenvironment diagnostic, construct a temporary `LocalVisBackend` visualizer, and report distributed availability without launching multi-process jobs.\n\n## Scope\n\nThis sub-skill owns MMEngine runtime utilities: `mmengine.logging`, `mmengine.visualization`, `mmengine.dist`, `mmengine.device`, `mmengine.utils`, `mmengine.utils.dl_utils.collect_env`, `mmengine.testing`, `ManagerMixin`-based singleton behavior, progress helpers, and timers.\n\nRoute adjacent issues to sibling skills:\n\n- Use `..\u002Frunner-and-training\u002FSKILL.md` for Runner `LoggerHook`, `NaiveVisualizationHook`, launch command placement, training log intervals, checkpoint\u002Fresume, and hook ordering.\n- Use `..\u002Fmodels-metrics-and-inference\u002FSKILL.md` for model complexity\u002Fanalysis APIs, `BaseModel`, `BaseMetric`, evaluator contracts, and inference\u002FTTA behavior.\n- Use `..\u002Fdata-structures-and-io\u002FSKILL.md` for file format IO, file backends, datasets, samplers, collation, and data element schemas.\n- Use `..\u002Fconfiguration-and-registry\u002FSKILL.md` for config syntax, registries, `DefaultScope`, and config-driven object construction.\n\n## Fast Workflow\n\n1. For one-off logging, call `print_log`; for reusable project logging, create a named `MMLogger.get_instance(...)` and reuse that instance name.\n2. For training\u002Fruntime state shared across components, store numeric histories with `MessageHub.update_scalar(s)` and overwrite current metadata with `MessageHub.update_info`.\n3. For visualization without credentials, prefer `Visualizer(..., vis_backends=[dict(type='LocalVisBackend')], save_dir=...)`; add TensorBoard or service backends only when dependencies and credentials are available.\n4. For distributed-safe code, call `get_dist_info()` first; expect `(0, 1)` outside distributed launch and remember `master_only` silently returns `None` on non-main ranks.\n5. Before debugging user environments, run `python scripts\u002Fruntime_env_check.py --help` from this sub-skill directory, then run it with an optional `--work-dir` that points to a disposable output directory.\n\n## Safe Operating Rules\n\n- Do not initialize distributed jobs from helper scripts unless the user has explicitly launched the process group with PyTorch, MPI, or Slurm environment variables.\n- Do not require optional tracking services, credentials, network access, or original MMEngine repository files; use `LocalVisBackend` as the safe fallback.\n- Treat visualizer `save_dir` as a user project output path and keep generated runtime skill files independent from any user experiment outputs.\n","# Runtime Utilities and Visualization\n\nUse this sub-skill when a task mentions `MMLogger`, `print_log`, `MessageHub`, `Visualizer`, `LocalVisBackend`, `TensorboardVisBackend`, `WandbVisBackend`, MLflow\u002FClearML\u002FAim\u002FDVCLive\u002FNeptune backends, `init_dist`, `get_dist_info`, `collect_results`, `master_only`, `get_device`, `collect_env`, `ManagerMixin`, progress bars, `Timer`, or MMEngine testing helpers.\n\n## Read Order\n\n- [references\u002Flogging-visualization-workflows.md](references\u002Flogging-visualization-workflows.md): Choose and use loggers, message hubs, visualizers, local outputs, and optional tracking-service backends.\n- [references\u002Fdistributed-device-utilities.md](references\u002Fdistributed-device-utilities.md): Use distributed rank helpers, safe result collection, device detection, environment reports, timers, progress helpers, manager mixins, and testing utilities.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): Diagnose duplicate loggers, optional backend dependency failures, visualization output surprises, distributed no-op behavior, collection mismatches, device fallback, and test-helper pitfalls.\n- [scripts\u002Fruntime_env_check.py](scripts\u002Fruntime_env_check.py): Run a safe local import\u002Fenvironment diagnostic, construct a temporary `LocalVisBackend` visualizer, and report distributed availability without launching multi-process jobs.\n\n## Scope\n\nThis sub-skill owns MMEngine runtime utilities: `mmengine.logging`, `mmengine.visualization`, `mmengine.dist`, `mmengine.device`, `mmengine.utils`, `mmengine.utils.dl_utils.collect_env`, `mmengine.testing`, `ManagerMixin`-based singleton behavior, progress helpers, and timers.\n\nRoute adjacent issues to sibling skills:\n\n- Use `..\u002Frunner-and-training\u002FSKILL.md` for Runner `LoggerHook`, `NaiveVisualizationHook`, launch command placement, training log intervals, checkpoint\u002Fresume, and hook ordering.\n- Use `..\u002Fmodels-metrics-and-inference\u002FSKILL.md` for model complexity\u002Fanalysis APIs, `BaseModel`, `BaseMetric`, evaluator contracts, and inference\u002FTTA behavior.\n- Use `..\u002Fdata-structures-and-io\u002FSKILL.md` for file format IO, file backends, datasets, samplers, collation, and data element schemas.\n- Use `..\u002Fconfiguration-and-registry\u002FSKILL.md` for config syntax, registries, `DefaultScope`, and config-driven object construction.\n\n## Fast Workflow\n\n1. For one-off logging, call `print_log`; for reusable project logging, create a named `MMLogger.get_instance(...)` and reuse that instance name.\n2. For training\u002Fruntime state shared across components, store numeric histories with `MessageHub.update_scalar(s)` and overwrite current metadata with `MessageHub.update_info`.\n3. For visualization without credentials, prefer `Visualizer(..., vis_backends=[dict(type='LocalVisBackend')], save_dir=...)`; add TensorBoard or service backends only when dependencies and credentials are available.\n4. For distributed-safe code, call `get_dist_info()` first; expect `(0, 1)` outside distributed launch and remember `master_only` silently returns `None` on non-main ranks.\n5. Before debugging user environments, run `python scripts\u002Fruntime_env_check.py --help` from this sub-skill directory, then run it with an optional `--work-dir` that points to a disposable output directory.\n\n## Safe Operating Rules\n\n- Do not initialize distributed jobs from helper scripts unless the user has explicitly launched the process group with PyTorch, MPI, or Slurm environment variables.\n- Do not require optional tracking services, credentials, network access, or original MMEngine repository files; use `LocalVisBackend` as the safe fallback.\n- Treat visualizer `save_dir` as a user project output path and keep generated runtime skill files independent from any user experiment outputs.\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\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization",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 runtime-utilities-and-visualization",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill runtime-utilities-and-visualization",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill runtime-utilities-and-visualization","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\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdistributed-device-utilities.md","REFERENCE","参考文档",6924,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization\u002Freferences\u002Fdistributed-device-utilities.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Flogging-visualization-workflows.md",6644,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization\u002Freferences\u002Flogging-visualization-workflows.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",7428,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmmengine\u002Fsub-skills\u002Fruntime-utilities-and-visualization\u002Freferences\u002Ftroubleshooting.md",[64,72,77,84,91,98],{"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":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":73,"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":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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",[],[]]