[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FFFVZQZ2GJ0C0TGP7JHD20":3,"skill-same:01M7FFFVZQZ2GJ0C0TGP7JHD20":62},{"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},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation",null,"Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","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\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: file-evaluation\ndescription: \"Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and\n  detection text files.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# file-evaluation\n\nUse this sub-skill when the user wants PASCAL VOC Average Precision (AP) or mean AP (mAP) from folders of ground-truth and detection `.txt` files, including YOLO-style relative detections, mixed `xywh`\u002F`xyrb` coordinate formats, or a noninteractive replacement for the legacy `pascalvoc.py` workflow.\n\n## Route here for\n\n- Compute VOC AP or mAP from `groundtruths\u002F` and `detections\u002F` text folders.\n- Evaluate detection text files with an IoU threshold such as `0.3`, `0.5`, or `0.75`.\n- Convert relative YOLO-like `center_x center_y width height` boxes to VOC AP\u002FmAP with a fixed image size.\n- Avoid the original script's save-path prompt\u002Fdeletion and plotting behavior.\n\n## Route away\n\n- Direct construction of `BoundingBox`, `BoundingBoxes`, or `Evaluator` objects, custom in-memory metrics, 11-point AP choices, or drawing\u002Fplotting API behavior: use `..\u002Fpython-api\u002FSKILL.md`.\n- COCO metrics, successor UI\u002Fnew-tool workflows, video metrics, model training, or detector inference are outside this legacy sub-skill.\n\n## Required inputs\n\n1. A ground-truth folder containing one `.txt` file per image id.\n2. A detection folder containing one `.txt` file per image id.\n3. The coordinate format for each folder:\n   - `xywh`: absolute `left top width height`; for relative coordinates this means YOLO-style `center_x center_y width height`.\n   - `xyrb`: absolute `left top right bottom` \u002F `XYX2Y2`.\n4. Coordinate reference for each folder: `abs` or `rel`.\n5. `WIDTH,HEIGHT` image size if either folder uses `rel` coordinates.\n6. IoU threshold for TP\u002FFP matching. Default is `0.5`.\n\nSee `references\u002Ffile-format.md` for exact schemas, matching rules, and relative-coordinate conversion.\n\n## Noninteractive helper\n\nThe bundled helper is self-contained and uses only the Python standard library:\n\n```bash\npython scripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections \\\n  --threshold 0.5 \\\n  --gt-format xywh --det-format xywh \\\n  --gt-coords abs --det-coords abs \\\n  --output-text voc-results.txt \\\n  --output-json voc-results.json \\\n  --pretty\n```\n\nFor YOLO-like relative detections against absolute ground truth:\n\n```bash\npython scripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections_rel \\\n  --threshold 0.3 \\\n  --gt-format xywh --det-format xywh \\\n  --gt-coords abs --det-coords rel \\\n  --img-size 200,200 \\\n  --output-text voc-results.txt\n```\n\nThe helper never plots, never prompts, and never deletes an output directory. It prints to stdout when no output file is requested and creates only the explicit `--output-text` and\u002For `--output-json` files.\n\n## Output contract\n\nText output contains:\n\n- IoU threshold.\n- Any validation warnings, such as unmatched file stems.\n- Per-class AP percentage, precision array, recall array, total positives, total TP, and total FP.\n- Final `mAP` percentage.\n\nJSON output contains:\n\n- `metric`, `threshold`, `classes`, `valid_classes`, `ignored_classes`, `mAP`, `mAP_percent`, and `warnings`.\n- Each item in `classes` includes `class`, `AP`, `AP_percent`, `precision`, `recall`, `interpolated_precision`, `interpolated_recall`, `total positives`, `total TP`, and `total FP`.\n\n## Evaluation semantics\n\n- AP uses VOC every-point interpolation, the default behavior of the legacy toolkit.\n- IoU uses inclusive VOC pixel area (`+1` in width and height).\n- Detections are sorted by descending confidence within each class.\n- A ground-truth box can be matched once. Duplicate detections of the same object become false positives after the first match.\n- mAP is the mean of AP values over classes with at least one ground-truth positive; detection-only classes are ignored with a warning.\n\n## Standard workflow\n\n1. Validate folder existence and text-line schema before running.\n2. Confirm file stems match image ids across ground-truth and detection folders.\n3. Select `--gt-format` and `--det-format`; wrong `xywh` vs `xyrb` selection can silently change IoU\u002FAP.\n4. If using `rel`, add `--img-size WIDTH,HEIGHT` and keep format `xywh`.\n5. Run the helper with `--output-json` for machine-readable reports or `--output-text` for a VOC-like summary.\n6. Interpret AP\u002FmAP using `references\u002Fworkflows.md`; troubleshoot failures using `references\u002Ftroubleshooting.md`.\n\n## Evidence distilled\n\nThis sub-skill is distilled from the repository's `README.md` PASCAL VOC metrics and CLI guidance, `pascalvoc.py` parser\u002Fevaluation behavior, the tiny text fixtures in `groundtruths\u002F`, `detections\u002F`, `groundtruths_rel\u002F`, `detections_rel\u002F`, `samples\u002Fsample_2\u002FREADME.md`, and the sample output shape in `results\u002Fresults.txt`.\n","# file-evaluation\n\nUse this sub-skill when the user wants PASCAL VOC Average Precision (AP) or mean AP (mAP) from folders of ground-truth and detection `.txt` files, including YOLO-style relative detections, mixed `xywh`\u002F`xyrb` coordinate formats, or a noninteractive replacement for the legacy `pascalvoc.py` workflow.\n\n## Route here for\n\n- Compute VOC AP or mAP from `groundtruths\u002F` and `detections\u002F` text folders.\n- Evaluate detection text files with an IoU threshold such as `0.3`, `0.5`, or `0.75`.\n- Convert relative YOLO-like `center_x center_y width height` boxes to VOC AP\u002FmAP with a fixed image size.\n- Avoid the original script's save-path prompt\u002Fdeletion and plotting behavior.\n\n## Route away\n\n- Direct construction of `BoundingBox`, `BoundingBoxes`, or `Evaluator` objects, custom in-memory metrics, 11-point AP choices, or drawing\u002Fplotting API behavior: use `..\u002Fpython-api\u002FSKILL.md`.\n- COCO metrics, successor UI\u002Fnew-tool workflows, video metrics, model training, or detector inference are outside this legacy sub-skill.\n\n## Required inputs\n\n1. A ground-truth folder containing one `.txt` file per image id.\n2. A detection folder containing one `.txt` file per image id.\n3. The coordinate format for each folder:\n   - `xywh`: absolute `left top width height`; for relative coordinates this means YOLO-style `center_x center_y width height`.\n   - `xyrb`: absolute `left top right bottom` \u002F `XYX2Y2`.\n4. Coordinate reference for each folder: `abs` or `rel`.\n5. `WIDTH,HEIGHT` image size if either folder uses `rel` coordinates.\n6. IoU threshold for TP\u002FFP matching. Default is `0.5`.\n\nSee `references\u002Ffile-format.md` for exact schemas, matching rules, and relative-coordinate conversion.\n\n## Noninteractive helper\n\nThe bundled helper is self-contained and uses only the Python standard library:\n\n```bash\npython scripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections \\\n  --threshold 0.5 \\\n  --gt-format xywh --det-format xywh \\\n  --gt-coords abs --det-coords abs \\\n  --output-text voc-results.txt \\\n  --output-json voc-results.json \\\n  --pretty\n```\n\nFor YOLO-like relative detections against absolute ground truth:\n\n```bash\npython scripts\u002Fvoc_metrics_eval.py \\\n  --gt-folder \u002Fpath\u002Fto\u002Fgroundtruths \\\n  --det-folder \u002Fpath\u002Fto\u002Fdetections_rel \\\n  --threshold 0.3 \\\n  --gt-format xywh --det-format xywh \\\n  --gt-coords abs --det-coords rel \\\n  --img-size 200,200 \\\n  --output-text voc-results.txt\n```\n\nThe helper never plots, never prompts, and never deletes an output directory. It prints to stdout when no output file is requested and creates only the explicit `--output-text` and\u002For `--output-json` files.\n\n## Output contract\n\nText output contains:\n\n- IoU threshold.\n- Any validation warnings, such as unmatched file stems.\n- Per-class AP percentage, precision array, recall array, total positives, total TP, and total FP.\n- Final `mAP` percentage.\n\nJSON output contains:\n\n- `metric`, `threshold`, `classes`, `valid_classes`, `ignored_classes`, `mAP`, `mAP_percent`, and `warnings`.\n- Each item in `classes` includes `class`, `AP`, `AP_percent`, `precision`, `recall`, `interpolated_precision`, `interpolated_recall`, `total positives`, `total TP`, and `total FP`.\n\n## Evaluation semantics\n\n- AP uses VOC every-point interpolation, the default behavior of the legacy toolkit.\n- IoU uses inclusive VOC pixel area (`+1` in width and height).\n- Detections are sorted by descending confidence within each class.\n- A ground-truth box can be matched once. Duplicate detections of the same object become false positives after the first match.\n- mAP is the mean of AP values over classes with at least one ground-truth positive; detection-only classes are ignored with a warning.\n\n## Standard workflow\n\n1. Validate folder existence and text-line schema before running.\n2. Confirm file stems match image ids across ground-truth and detection folders.\n3. Select `--gt-format` and `--det-format`; wrong `xywh` vs `xyrb` selection can silently change IoU\u002FAP.\n4. If using `rel`, add `--img-size WIDTH,HEIGHT` and keep format `xywh`.\n5. Run the helper with `--output-json` for machine-readable reports or `--output-text` for a VOC-like summary.\n6. Interpret AP\u002FmAP using `references\u002Fworkflows.md`; troubleshoot failures using `references\u002Ftroubleshooting.md`.\n\n## Evidence distilled\n\nThis sub-skill is distilled from the repository's `README.md` PASCAL VOC metrics and CLI guidance, `pascalvoc.py` parser\u002Fevaluation behavior, the tiny text fixtures in `groundtruths\u002F`, `detections\u002F`, `groundtruths_rel\u002F`, `detections_rel\u002F`, `samples\u002Fsample_2\u002FREADME.md`, and the sample output shape in `results\u002Fresults.txt`.\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\u002Fsub-skills\u002Ffile-evaluation",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 file-evaluation",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill file-evaluation",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill file-evaluation","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\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Ffile-format.md","REFERENCE","参考文档",4673,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002Freferences\u002Ffile-format.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Ftroubleshooting.md",5459,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002Freferences\u002Ftroubleshooting.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fworkflows.md",6500,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002Freferences\u002Fworkflows.md",[63,70,75,82,89,96],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]