[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FAHWB2EPDXF7H5AAT003MW":3,"skill-same:01M7FAHWB2EPDXF7H5AAT003MW":59},{"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},"01M7FAHWB2EPDXF7H5AAT003MW","data-validation",null,"Inspect class membership and ground-truth\u002Fdetection-result file-set intersections for mAP-style inputs with safe report-first repair guidance.","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\u002Fmap\u002Fsub-skills\u002Fdata-validation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: data-validation\ndescription: \"Inspect class membership and ground-truth\u002Fdetection-result\n  file-set intersections for mAP-style inputs with safe report-first repair\n  guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# data-validation\n\nUse this sub-skill when a future agent must decide whether mAP-style ground-truth and detection-result folders are ready for evaluation, find which files contain a class, or safely repair mismatched `.txt` file sets before running metrics.\n\n## Route here for\n\n- Checking that `ground-truth\u002F` and `detection-results\u002F` contain top-level `.txt` files with matching filenames.\n- Diagnosing evaluator errors that imply a missing ground-truth or detection-result pair.\n- Finding every GT and DR file whose first token on any annotation line equals a requested class name.\n- Reporting GT-only and DR-only files before evaluation.\n- Moving non-intersecting files into an explicit backup folder after a report-only dry run and explicit confirmation.\n\n## Do not handle here\n\n- Computing AP, mAP, IoU matching, ignored classes, custom IoU thresholds, plots, animations, or evaluator output files: use `..\u002Fevaluation\u002FSKILL.md`.\n- Converting PASCAL VOC XML, YOLO, darkflow JSON, darknet result text, or keras-yolo3 annotations into mAP text files: use `..\u002Fconversion\u002FSKILL.md`.\n- Deep validation of bounding-box coordinates, confidence values, optional `difficult` behavior, or metric semantics beyond the file-set and first-token class checks owned here.\n\n## Evidence-backed assumptions\n\n- The evaluator expects one ground-truth `.txt` file and one detection-result `.txt` file per image, with matching filenames such as `image_1.txt` on both sides.\n- Ground-truth lines start with the class name and then contain box coordinates plus optional `difficult`.\n- Detection-result lines start with the class name, then confidence and box coordinates.\n- The legacy class finder searched both folders for a class by comparing the first whitespace-separated token of each line.\n- The legacy intersection helper moved non-intersecting files immediately; this generated skill uses a bundled report-first helper instead.\n\n## First checks\n\n1. Identify the actual GT and DR folders the user wants evaluated. Do not assume implicit repository-relative folders; pass explicit paths to the helper.\n2. Run a non-mutating readiness report:\n\n   ```bash\n   python sub-skills\u002Fdata-validation\u002Fscripts\u002Fcheck_map_inputs.py \\\n     --gt-dir \u002Fpath\u002Fto\u002Fground-truth \\\n     --dr-dir \u002Fpath\u002Fto\u002Fdetection-results\n   ```\n\n3. If the user asks about a class, add `--class-name CLASS` and read both GT and DR results. A class absent from both folders usually means the class label is misspelled, conversion mapped it differently, or the wrong folders were selected.\n4. If the report shows GT-only or DR-only files, inspect the listed basenames before moving anything. Same counts can still be invalid when basenames differ.\n5. Repair only when the user accepts moving the non-intersecting `.txt` files out of evaluator inputs. Use a backup root outside the GT\u002FDR folders and require explicit confirmation:\n\n   ```bash\n   python sub-skills\u002Fdata-validation\u002Fscripts\u002Fcheck_map_inputs.py \\\n     --gt-dir \u002Fpath\u002Fto\u002Fground-truth \\\n     --dr-dir \u002Fpath\u002Fto\u002Fdetection-results \\\n     --move-extra-to \u002Fpath\u002Fto\u002Fmap-input-backup \\\n     --confirm-move\n   ```\n\n6. Rerun the report after any repair. Route to evaluation only when the helper reports matching file sets and non-empty intersections.\n\n## Reference map\n\n- Read `references\u002Fworkflows.md` for step-by-step class lookup, file-set readiness, dry-run interpretation, and explicit backup repair workflows.\n- Read `references\u002Ftroubleshooting.md` for empty folders, same-count\u002Fdifferent-basename failures, non-intersecting sets, missing classes, unsafe legacy moves, wrong filenames, and backup conflicts.\n- Run `scripts\u002Fcheck_map_inputs.py --help` when you need exact helper options and exit-code behavior.\n\n## Safety rules\n\n- The bundled helper is report-only by default. Supplying `--move-extra-to` without `--confirm-move` prints a plan but still does not move files.\n- Never delete GT or DR files as a repair step. The only bundled repair moves non-intersecting `.txt` files to a named backup root.\n- Do not move files when the GT\u002FDR intersection is empty; that usually means wrong paths, wrong extensions, or incompatible naming rather than a safe partial mismatch.\n- Keep conversion fixes in the conversion sub-skill and metric\u002Fdebug interpretation in the evaluation sub-skill so this sub-skill stays focused on class lookup and file-set intersection readiness.\n","# data-validation\n\nUse this sub-skill when a future agent must decide whether mAP-style ground-truth and detection-result folders are ready for evaluation, find which files contain a class, or safely repair mismatched `.txt` file sets before running metrics.\n\n## Route here for\n\n- Checking that `ground-truth\u002F` and `detection-results\u002F` contain top-level `.txt` files with matching filenames.\n- Diagnosing evaluator errors that imply a missing ground-truth or detection-result pair.\n- Finding every GT and DR file whose first token on any annotation line equals a requested class name.\n- Reporting GT-only and DR-only files before evaluation.\n- Moving non-intersecting files into an explicit backup folder after a report-only dry run and explicit confirmation.\n\n## Do not handle here\n\n- Computing AP, mAP, IoU matching, ignored classes, custom IoU thresholds, plots, animations, or evaluator output files: use `..\u002Fevaluation\u002FSKILL.md`.\n- Converting PASCAL VOC XML, YOLO, darkflow JSON, darknet result text, or keras-yolo3 annotations into mAP text files: use `..\u002Fconversion\u002FSKILL.md`.\n- Deep validation of bounding-box coordinates, confidence values, optional `difficult` behavior, or metric semantics beyond the file-set and first-token class checks owned here.\n\n## Evidence-backed assumptions\n\n- The evaluator expects one ground-truth `.txt` file and one detection-result `.txt` file per image, with matching filenames such as `image_1.txt` on both sides.\n- Ground-truth lines start with the class name and then contain box coordinates plus optional `difficult`.\n- Detection-result lines start with the class name, then confidence and box coordinates.\n- The legacy class finder searched both folders for a class by comparing the first whitespace-separated token of each line.\n- The legacy intersection helper moved non-intersecting files immediately; this generated skill uses a bundled report-first helper instead.\n\n## First checks\n\n1. Identify the actual GT and DR folders the user wants evaluated. Do not assume implicit repository-relative folders; pass explicit paths to the helper.\n2. Run a non-mutating readiness report:\n\n   ```bash\n   python sub-skills\u002Fdata-validation\u002Fscripts\u002Fcheck_map_inputs.py \\\n     --gt-dir \u002Fpath\u002Fto\u002Fground-truth \\\n     --dr-dir \u002Fpath\u002Fto\u002Fdetection-results\n   ```\n\n3. If the user asks about a class, add `--class-name CLASS` and read both GT and DR results. A class absent from both folders usually means the class label is misspelled, conversion mapped it differently, or the wrong folders were selected.\n4. If the report shows GT-only or DR-only files, inspect the listed basenames before moving anything. Same counts can still be invalid when basenames differ.\n5. Repair only when the user accepts moving the non-intersecting `.txt` files out of evaluator inputs. Use a backup root outside the GT\u002FDR folders and require explicit confirmation:\n\n   ```bash\n   python sub-skills\u002Fdata-validation\u002Fscripts\u002Fcheck_map_inputs.py \\\n     --gt-dir \u002Fpath\u002Fto\u002Fground-truth \\\n     --dr-dir \u002Fpath\u002Fto\u002Fdetection-results \\\n     --move-extra-to \u002Fpath\u002Fto\u002Fmap-input-backup \\\n     --confirm-move\n   ```\n\n6. Rerun the report after any repair. Route to evaluation only when the helper reports matching file sets and non-empty intersections.\n\n## Reference map\n\n- Read `references\u002Fworkflows.md` for step-by-step class lookup, file-set readiness, dry-run interpretation, and explicit backup repair workflows.\n- Read `references\u002Ftroubleshooting.md` for empty folders, same-count\u002Fdifferent-basename failures, non-intersecting sets, missing classes, unsafe legacy moves, wrong filenames, and backup conflicts.\n- Run `scripts\u002Fcheck_map_inputs.py --help` when you need exact helper options and exit-code behavior.\n\n## Safety rules\n\n- The bundled helper is report-only by default. Supplying `--move-extra-to` without `--confirm-move` prints a plan but still does not move files.\n- Never delete GT or DR files as a repair step. The only bundled repair moves non-intersecting `.txt` files to a named backup root.\n- Do not move files when the GT\u002FDR intersection is empty; that usually means wrong paths, wrong extensions, or incompatible naming rather than a safe partial mismatch.\n- Keep conversion fixes in the conversion sub-skill and metric\u002Fdebug interpretation in the evaluation sub-skill so this sub-skill stays focused on class lookup and file-set intersection readiness.\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\u002Fmap\u002Fsub-skills\u002Fdata-validation",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 data-validation",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill data-validation",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill data-validation","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\u002Fmap\u002Fsub-skills\u002Fdata-validation\u002FSKILL.md",[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",7142,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmap\u002Fsub-skills\u002Fdata-validation\u002Freferences\u002Ftroubleshooting.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fworkflows.md",6420,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmap\u002Fsub-skills\u002Fdata-validation\u002Freferences\u002Fworkflows.md",[60,68,73,80,87,94],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]