[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FC0R278YN9PZ1JX274AMYZ":3,"skill-same:01M7FC0R278YN9PZ1JX274AMYZ":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},"01M7FC0R278YN9PZ1JX274AMYZ","feature-postprocessing",null,"Guides RoboSat prediction post-processing from probability PNGs to masks, parking GeoJSON features, merge\u002Fdedupe cleanup, visual comparison, and vector artifact validation.","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\u002F06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: feature-postprocessing\ndescription: \"Guides RoboSat prediction post-processing from probability PNGs to\n  masks, parking GeoJSON features, merge\u002Fdedupe cleanup, visual comparison, and\n  vector artifact validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# RoboSat feature post-processing\n\nUse this sub-skill when a task already has RoboSat prediction probability tiles or mask tiles and needs to turn them into inspectable masks, parking-lot vector features, cleaned GeoJSON, or visual QA mosaics.\n\n## Use this for\n\n- Converting binary foreground-probability PNG Slippy Map outputs into palette mask tiles with `rs masks`.\n- Extracting parking-lot WGS84 GeoJSON polygons from mask tiles with `rs features --type parking`.\n- Merging adjacent predicted polygons with a meter threshold via `rs merge`.\n- Deduplicating predictions against existing OSM-derived GeoJSON with an IoU threshold via `rs dedupe`.\n- Building side-by-side image \u002F label \u002F mask mosaics with `rs compare`.\n- Validating post-processing artifacts using bundled scripts.\n\n## Route elsewhere\n\n- Need to train a model, load checkpoints, export ONNX, run batch prediction, or produce probability PNGs first: use the `model-lifecycle` sub-skill.\n- Need to extract OSM features before training, cover tiles, download imagery, rasterize labels, compute class weights, or subset tile sets: use the `data-preparation` sub-skill.\n- Need non-parking post-processing handlers: this sub-skill explains the handler contract, but the installed CLI only registers the parking handler by default.\n\n## Fast workflow map\n\n1. Confirm that probability or mask directories are Slippy Map trees such as `18\u002F69108\u002F105091.png`; see [data formats](references\u002Fdata-formats.md).\n2. Convert probabilities to masks:\n   `rs masks out\u002Fmasks probs\u002Frun-a [probs\u002Frun-b ...] [--weights 0.7 0.3]`.\n3. Convert parking masks to GeoJSON:\n   `rs features out\u002Fmasks --type parking --dataset dataset.toml out\u002Ffeatures.geojson`.\n4. Clean vector output:\n   `rs merge out\u002Ffeatures.geojson --threshold 3 out\u002Ffeatures-merged.geojson`, then optionally `rs dedupe osm.geojson out\u002Ffeatures-merged.geojson --threshold 0.5 out\u002Ffeatures-new.geojson`.\n5. Compare visual quality:\n   `rs compare out\u002Fcompare images labels out\u002Fmasks [other\u002Fmasks ...] --minimum 0.01 --maximum 0.95`.\n6. Validate artifacts with [`scripts\u002Fvalidate_feature_collection.py`](scripts\u002Fvalidate_feature_collection.py) and smoke-test soft voting with [`scripts\u002Fsoftvote_smoke.py`](scripts\u002Fsoftvote_smoke.py).\n\nDetailed command recipes are in [workflows](references\u002Fworkflows.md). API behavior is summarized in [API reference](references\u002Fapi-reference.md). Common failure modes are in [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Key constraints to remember\n\n- RoboSat probability PNG post-processing is binary: one quantized foreground-probability channel is reconstructed as foreground plus `1 - foreground` background.\n- `rs features` is parking-only in the default installed CLI; the dataset config must include the `parking` class and mask class index must match it.\n- `ParkingHandler` thresholds are tuned for zoom 18 and will raise on other zoom levels.\n- `rs merge --threshold` is measured in meters; `rs dedupe --threshold` is intersection-over-union, not distance or model confidence.\n- Post-processing is CPU-oriented. CUDA is not needed for the commands in this sub-skill.\n","# RoboSat feature post-processing\n\nUse this sub-skill when a task already has RoboSat prediction probability tiles or mask tiles and needs to turn them into inspectable masks, parking-lot vector features, cleaned GeoJSON, or visual QA mosaics.\n\n## Use this for\n\n- Converting binary foreground-probability PNG Slippy Map outputs into palette mask tiles with `rs masks`.\n- Extracting parking-lot WGS84 GeoJSON polygons from mask tiles with `rs features --type parking`.\n- Merging adjacent predicted polygons with a meter threshold via `rs merge`.\n- Deduplicating predictions against existing OSM-derived GeoJSON with an IoU threshold via `rs dedupe`.\n- Building side-by-side image \u002F label \u002F mask mosaics with `rs compare`.\n- Validating post-processing artifacts using bundled scripts.\n\n## Route elsewhere\n\n- Need to train a model, load checkpoints, export ONNX, run batch prediction, or produce probability PNGs first: use the `model-lifecycle` sub-skill.\n- Need to extract OSM features before training, cover tiles, download imagery, rasterize labels, compute class weights, or subset tile sets: use the `data-preparation` sub-skill.\n- Need non-parking post-processing handlers: this sub-skill explains the handler contract, but the installed CLI only registers the parking handler by default.\n\n## Fast workflow map\n\n1. Confirm that probability or mask directories are Slippy Map trees such as `18\u002F69108\u002F105091.png`; see [data formats](references\u002Fdata-formats.md).\n2. Convert probabilities to masks:\n   `rs masks out\u002Fmasks probs\u002Frun-a [probs\u002Frun-b ...] [--weights 0.7 0.3]`.\n3. Convert parking masks to GeoJSON:\n   `rs features out\u002Fmasks --type parking --dataset dataset.toml out\u002Ffeatures.geojson`.\n4. Clean vector output:\n   `rs merge out\u002Ffeatures.geojson --threshold 3 out\u002Ffeatures-merged.geojson`, then optionally `rs dedupe osm.geojson out\u002Ffeatures-merged.geojson --threshold 0.5 out\u002Ffeatures-new.geojson`.\n5. Compare visual quality:\n   `rs compare out\u002Fcompare images labels out\u002Fmasks [other\u002Fmasks ...] --minimum 0.01 --maximum 0.95`.\n6. Validate artifacts with [`scripts\u002Fvalidate_feature_collection.py`](scripts\u002Fvalidate_feature_collection.py) and smoke-test soft voting with [`scripts\u002Fsoftvote_smoke.py`](scripts\u002Fsoftvote_smoke.py).\n\nDetailed command recipes are in [workflows](references\u002Fworkflows.md). API behavior is summarized in [API reference](references\u002Fapi-reference.md). Common failure modes are in [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Key constraints to remember\n\n- RoboSat probability PNG post-processing is binary: one quantized foreground-probability channel is reconstructed as foreground plus `1 - foreground` background.\n- `rs features` is parking-only in the default installed CLI; the dataset config must include the `parking` class and mask class index must match it.\n- `ParkingHandler` thresholds are tuned for zoom 18 and will raise on other zoom levels.\n- `rs merge --threshold` is measured in meters; `rs dedupe --threshold` is intersection-over-union, not distance or model confidence.\n- Post-processing is CPU-oriented. CUDA is not needed for the commands in this sub-skill.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing",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 feature-postprocessing",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill feature-postprocessing",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill feature-postprocessing","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\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",6940,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdata-formats.md",5540,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002Freferences\u002Fdata-formats.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",7453,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflows.md",7060,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Frobosat\u002Fsub-skills\u002Ffeature-postprocessing\u002Freferences\u002Fworkflows.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},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]