[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FFFSFNYSE77SJ6PE1CK2DA":3,"skill-same:01M7FFFSFNYSE77SJ6PE1CK2DA":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},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics",null,"Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","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\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: object-detection-metrics\ndescription: \"Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP\n  evaluation from detection text folders and direct Python API classes.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Object-Detection-Metrics\n\nUse this repo skill when the user needs the legacy Object-Detection-Metrics toolkit behavior for PASCAL VOC-style object-detection metrics: AP, mAP, precision\u002Frecall curves, text-folder evaluation, or direct use of the `BoundingBox` \u002F `BoundingBoxes` \u002F `Evaluator` classes.\n\nThis skill is self-contained for operating guidance. Prefer its bundled helpers and references instead of reopening or running original repository examples or scripts.\n\n## Quick route\n\n| User task | Read next |\n|---|---|\n| Evaluate `groundtruths\u002F` and `detections\u002F` text folders for VOC AP\u002FmAP | `sub-skills\u002Ffile-evaluation\u002FSKILL.md` |\n| Handle `xywh` versus `xyrb`, absolute versus relative coordinates, or YOLO-like normalized boxes in text files | `sub-skills\u002Ffile-evaluation\u002Freferences\u002Ffile-format.md` |\n| Run a noninteractive, safe replacement for the legacy folder-evaluation script | `sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py` |\n| Build `BoundingBox` objects and call `Evaluator.GetPascalVOCMetrics` from Python data | `sub-skills\u002Fpython-api\u002FSKILL.md` |\n| Choose every-point versus 11-point AP, understand duplicate detections, or inspect inclusive IoU behavior | `sub-skills\u002Fpython-api\u002Freferences\u002Fmetric-behavior.md` |\n| Check whether a user-provided checkout\u002Fcopy can import the source-style API | `sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py` or `scripts\u002Fcheck_env.py` |\n| Decide whether this skill is stale for a checkout | `references\u002Frepo-provenance.md` |\n| Understand selected capabilities and non-goals | `references\u002Fworkflow-map.md` |\n| Diagnose install\u002Fimport\u002Fdependency\u002Fversion problems | `references\u002Ftroubleshooting.md` |\n\n## Scope and non-goals\n\nThis skill covers:\n\n- PASCAL VOC AP\u002FmAP from simple text folders.\n- Ground-truth and detection schemas with `xywh` and `xyrb`\u002F`XYX2Y2` coordinates.\n- Relative YOLO-like center\u002Fsize coordinates when a shared image size is available.\n- Direct Python API use of the legacy source modules.\n- Safe noninteractive metric helpers and smoke checks.\n\nThis skill does **not** cover:\n\n- COCO metrics, video\u002FSTT-AP metrics, UI workflows, or file formats added by the newer successor toolkit.\n- Training or running an object detector.\n- General computer-vision model evaluation outside this repository's PASCAL VOC metric implementation.\n- Paper distillation or benchmark-survey reproduction.\n\n## Environment model\n\nFor folder evaluation, the bundled `file-evaluation` helper is standard-library-only and does not require the original checkout.\n\nFor direct source API use, the legacy repository is source-style rather than a pip-installable package. A user working with a checkout or copied source must make the `lib` directory importable and install the source API dependencies used by imports:\n\n```bash\npython -m pip install numpy matplotlib opencv-python-headless\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --repo-root \u002Fpath\u002Fto\u002Fcheckout\n```\n\nUse `opencv-python-headless` on servers unless GUI drawing is explicitly needed. Set `MPLBACKEND=Agg` before importing `Evaluator` when plotting in a headless process.\n\n## Minimal validation commands\n\nCheck only the generated helpers:\n\n```bash\npython scripts\u002Fcheck_env.py\npython sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py --help\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --help\n```\n\nCheck a user-provided checkout or copied `lib` directory plus API dependencies:\n\n```bash\npython scripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002Fcheckout --require-api-deps\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --repo-root \u002Fpath\u002Fto\u002Fcheckout --case duplicate\n```\n\nRun folder AP\u002FmAP with the self-contained helper:\n\n```bash\npython sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections \\\n  --threshold 0.5 \\\n  --output-text voc-results.txt \\\n  --output-json voc-results.json \\\n  --pretty\n```\n\n## Metric reminders\n\n- Default AP is PASCAL VOC every-point interpolation.\n- IoU uses inclusive pixel-area arithmetic: `(right - left + 1) * (bottom - top + 1)`.\n- Detections are sorted by confidence within each class.\n- Only one detection can match a ground-truth object; duplicate detections become false positives.\n- mAP is the mean AP across classes with at least one ground-truth positive.\n\n## Provenance and refresh\n\nRead `references\u002Frepo-provenance.md` before using this skill as evidence for a different checkout. Refresh the repo skill if the commit, dirty state, package layout, core source files, CLI flags, or public examples differ from the recorded snapshot.\n","# Object-Detection-Metrics\n\nUse this repo skill when the user needs the legacy Object-Detection-Metrics toolkit behavior for PASCAL VOC-style object-detection metrics: AP, mAP, precision\u002Frecall curves, text-folder evaluation, or direct use of the `BoundingBox` \u002F `BoundingBoxes` \u002F `Evaluator` classes.\n\nThis skill is self-contained for operating guidance. Prefer its bundled helpers and references instead of reopening or running original repository examples or scripts.\n\n## Quick route\n\n| User task | Read next |\n|---|---|\n| Evaluate `groundtruths\u002F` and `detections\u002F` text folders for VOC AP\u002FmAP | `sub-skills\u002Ffile-evaluation\u002FSKILL.md` |\n| Handle `xywh` versus `xyrb`, absolute versus relative coordinates, or YOLO-like normalized boxes in text files | `sub-skills\u002Ffile-evaluation\u002Freferences\u002Ffile-format.md` |\n| Run a noninteractive, safe replacement for the legacy folder-evaluation script | `sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py` |\n| Build `BoundingBox` objects and call `Evaluator.GetPascalVOCMetrics` from Python data | `sub-skills\u002Fpython-api\u002FSKILL.md` |\n| Choose every-point versus 11-point AP, understand duplicate detections, or inspect inclusive IoU behavior | `sub-skills\u002Fpython-api\u002Freferences\u002Fmetric-behavior.md` |\n| Check whether a user-provided checkout\u002Fcopy can import the source-style API | `sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py` or `scripts\u002Fcheck_env.py` |\n| Decide whether this skill is stale for a checkout | `references\u002Frepo-provenance.md` |\n| Understand selected capabilities and non-goals | `references\u002Fworkflow-map.md` |\n| Diagnose install\u002Fimport\u002Fdependency\u002Fversion problems | `references\u002Ftroubleshooting.md` |\n\n## Scope and non-goals\n\nThis skill covers:\n\n- PASCAL VOC AP\u002FmAP from simple text folders.\n- Ground-truth and detection schemas with `xywh` and `xyrb`\u002F`XYX2Y2` coordinates.\n- Relative YOLO-like center\u002Fsize coordinates when a shared image size is available.\n- Direct Python API use of the legacy source modules.\n- Safe noninteractive metric helpers and smoke checks.\n\nThis skill does **not** cover:\n\n- COCO metrics, video\u002FSTT-AP metrics, UI workflows, or file formats added by the newer successor toolkit.\n- Training or running an object detector.\n- General computer-vision model evaluation outside this repository's PASCAL VOC metric implementation.\n- Paper distillation or benchmark-survey reproduction.\n\n## Environment model\n\nFor folder evaluation, the bundled `file-evaluation` helper is standard-library-only and does not require the original checkout.\n\nFor direct source API use, the legacy repository is source-style rather than a pip-installable package. A user working with a checkout or copied source must make the `lib` directory importable and install the source API dependencies used by imports:\n\n```bash\npython -m pip install numpy matplotlib opencv-python-headless\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --repo-root \u002Fpath\u002Fto\u002Fcheckout\n```\n\nUse `opencv-python-headless` on servers unless GUI drawing is explicitly needed. Set `MPLBACKEND=Agg` before importing `Evaluator` when plotting in a headless process.\n\n## Minimal validation commands\n\nCheck only the generated helpers:\n\n```bash\npython scripts\u002Fcheck_env.py\npython sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py --help\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --help\n```\n\nCheck a user-provided checkout or copied `lib` directory plus API dependencies:\n\n```bash\npython scripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002Fcheckout --require-api-deps\npython sub-skills\u002Fpython-api\u002Fscripts\u002Fapi_metric_smoke.py --repo-root \u002Fpath\u002Fto\u002Fcheckout --case duplicate\n```\n\nRun folder AP\u002FmAP with the self-contained helper:\n\n```bash\npython sub-skills\u002Ffile-evaluation\u002Fscripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections \\\n  --threshold 0.5 \\\n  --output-text voc-results.txt \\\n  --output-json voc-results.json \\\n  --pretty\n```\n\n## Metric reminders\n\n- Default AP is PASCAL VOC every-point interpolation.\n- IoU uses inclusive pixel-area arithmetic: `(right - left + 1) * (bottom - top + 1)`.\n- Detections are sorted by confidence within each class.\n- Only one detection can match a ground-truth object; duplicate detections become false positives.\n- mAP is the mean AP across classes with at least one ground-truth positive.\n\n## Provenance and refresh\n\nRead `references\u002Frepo-provenance.md` before using this skill as evidence for a different checkout. Refresh the repo skill if the commit, dirty state, package layout, core source files, CLI flags, or public examples differ from the recorded snapshot.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fobject-detection-metrics",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 object-detection-metrics",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill object-detection-metrics",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill object-detection-metrics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2831,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Freferences\u002Frepo-provenance.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-routing-metadata.json",357,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Freferences\u002Frepo-routing-metadata.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",3765,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflow-map.md",3779,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Freferences\u002Fworkflow-map.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},"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",[],[],{"skillNo":101,"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":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FFFJBWP8P1E18AET8X31X0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns-antigravity-awesome-skills-main\u002FSKILL.md",[],[]]