[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794VHWGH099990EB6R71WW1":3,"skill-same:01M794VHWGH099990EB6R71WW1":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M794VHWGH099990EB6R71WW1","segment-geospatial",null,"Guides segment-geospatial\u002FSamGeo workflows for geospatial SAM segmentation, SAM2\u002FSAM3 model variants, REST API serving, raster\u002Fvector IO, and optional text or caption model integrations.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: segment-geospatial\ndescription: \"Guides segment-geospatial\u002FSamGeo workflows for geospatial SAM\n  segmentation, SAM2\u002FSAM3 model variants, REST API serving, raster\u002Fvector IO,\n  and optional text or caption model integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# segment-geospatial (SamGeo)\n\nUse this repo skill when a task involves the `segment-geospatial` package, the\n`samgeo` Python import, or geospatial image segmentation with SAM-family models.\nIt is self-contained operating guidance distilled from package code, docs,\nexamples, tests, and installed-package inspection for version 1.4.1.\n\n## First choose the route\n\n| User task | Read |\n| --- | --- |\n| Segment a GeoTIFF or image with SAM1\u002FSAM2, automatic masks, point prompts, box prompts, or SAM2 video | [core-segmentation](sub-skills\u002Fcore-segmentation\u002FSKILL.md) |\n| Use SAM3\u002FSAM3.1, text prompts, point\u002Fbox instance prompts, tiled large-image segmentation, batch images, or SAM3 video tracking | [samgeo3-workflows](sub-skills\u002Fsamgeo3-workflows\u002FSKILL.md) |\n| Download map tiles, handle CRS, prepare multi-band imagery, convert raster masks to vectors, split\u002Fmerge rasters, inspect raster metadata, or use UTM helpers | [geospatial-utilities](sub-skills\u002Fgeospatial-utilities\u002FSKILL.md) |\n| Use FastSAM, HQ-SAM, LangSAM\u002FGroundingDINO text prompts, BLIP image captioning, or optional detectree2\u002FFER notes | [specialized-models](sub-skills\u002Fspecialized-models\u002FSKILL.md) |\n| Serve segmentation over HTTP, call `samgeo-api`, validate API parameters, handle output formats, or troubleshoot model\u002Fimage caches | [api-server](sub-skills\u002Fapi-server\u002FSKILL.md) |\n\nRead [model-and-workflow-overview.md](references\u002Fmodel-and-workflow-overview.md)\nfor the package map and [installation-and-dependencies.md](references\u002Finstallation-and-dependencies.md)\nbefore choosing extras or CUDA packages. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting install, GPU, model-download, CRS, and optional-dependency failures.\n\n## Minimal install and import checks\n\nUse a fresh environment. Python 3.10-3.12 is exercised by the repository CI;\nPython 3.11 is a safe default for ML\u002Fgeospatial dependencies.\n\n```bash\npip install \"segment-geospatial[samgeo2,samgeo3,fast,hq,text,api]\"\npython - \u003C\u003C'PY'\nimport samgeo\nfrom samgeo.model_registry import AVAILABLE_MODELS\nprint(samgeo.__version__)\nprint(AVAILABLE_MODELS)\nPY\n```\n\nFor SAM3 runtime work, verify CUDA before promising a run:\n\n```python\nimport torch\nprint(torch.__version__, torch.version.cuda)\nprint(torch.cuda.is_available(), torch.cuda.device_count())\n```\n\nRun the bundled safe diagnostic when an environment looks questionable:\n\n```bash\npython scripts\u002Fcheck_install.py --check-optional\npython scripts\u002Fcheck_install.py --require-cuda\n```\n\nThe scripts only import modules and inspect lightweight API state; they do not\ndownload model weights or start a service.\n\n## Package entry points and outputs\n\n- Python import: `samgeo`.\n- Distribution: `segment-geospatial`.\n- CLI entry point: `samgeo-api` for the FastAPI service.\n- Main classes: `SamGeo`, `SamGeo2`, `SamGeo3`, `SamGeo3Video`, `LangSAM`,\n  FastSAM\u002FHQ-SAM wrappers, and `ImageCaptioner`.\n- Typical inputs: GeoTIFF, PNG\u002FJPEG, NumPy arrays, URLs, point coordinates,\n  bounding boxes, GeoJSON\u002Fvector prompts, and videos\u002Ftime-series frames.\n- Typical outputs: mask GeoTIFF\u002FPNG, vector GeoPackage\u002FShapefile\u002FGeoJSON,\n  JSON\u002Fdetections from the API, caption\u002Ffeature lists, and blended videos.\n\n## Operating rules\n\n- Do not tell users to open notebooks, scripts, tests, or docs from the original\n  checkout. Use the bundled references and scripts in this skill.\n- Distinguish pixel coordinates from geographic coordinates. If points or boxes\n  are in a CRS, pass `point_crs` or `box_crs` where the selected API supports it.\n- SamGeo preserves the source raster CRS during segmentation; it does not\n  automatically reproject masks to EPSG:4326.\n- SAM3\u002FSAM3.1 guidance should be treated as CUDA-backed unless the task is only\n  inspecting imports or mock-backed tests. CPU import checks are not proof of\n  real SAM3 runtime capability.\n- Model-weight downloads, Hugging Face authentication, map-tile downloads,\n  long-running inference, notebooks, QGIS plugin operations, and detectree2 or\n  GDAL-specific paths require explicit user\u002Fenvironment readiness.\n- The user requested `not import` for this generated skill run; do not run the\n  repo-skill import helper unless a later instruction explicitly approves it.\n\n## Provenance and refresh\n\nRead [repo-provenance.md](references\u002Frepo-provenance.md) before deciding this\nskill matches a new checkout. If the commit, package version, public APIs, or\nmajor example\u002Ftest paths differ, refresh the skill before relying on stale\nrouting or API details.\n","# segment-geospatial (SamGeo)\n\nUse this repo skill when a task involves the `segment-geospatial` package, the\n`samgeo` Python import, or geospatial image segmentation with SAM-family models.\nIt is self-contained operating guidance distilled from package code, docs,\nexamples, tests, and installed-package inspection for version 1.4.1.\n\n## First choose the route\n\n| User task | Read |\n| --- | --- |\n| Segment a GeoTIFF or image with SAM1\u002FSAM2, automatic masks, point prompts, box prompts, or SAM2 video | [core-segmentation](sub-skills\u002Fcore-segmentation\u002FSKILL.md) |\n| Use SAM3\u002FSAM3.1, text prompts, point\u002Fbox instance prompts, tiled large-image segmentation, batch images, or SAM3 video tracking | [samgeo3-workflows](sub-skills\u002Fsamgeo3-workflows\u002FSKILL.md) |\n| Download map tiles, handle CRS, prepare multi-band imagery, convert raster masks to vectors, split\u002Fmerge rasters, inspect raster metadata, or use UTM helpers | [geospatial-utilities](sub-skills\u002Fgeospatial-utilities\u002FSKILL.md) |\n| Use FastSAM, HQ-SAM, LangSAM\u002FGroundingDINO text prompts, BLIP image captioning, or optional detectree2\u002FFER notes | [specialized-models](sub-skills\u002Fspecialized-models\u002FSKILL.md) |\n| Serve segmentation over HTTP, call `samgeo-api`, validate API parameters, handle output formats, or troubleshoot model\u002Fimage caches | [api-server](sub-skills\u002Fapi-server\u002FSKILL.md) |\n\nRead [model-and-workflow-overview.md](references\u002Fmodel-and-workflow-overview.md)\nfor the package map and [installation-and-dependencies.md](references\u002Finstallation-and-dependencies.md)\nbefore choosing extras or CUDA packages. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting install, GPU, model-download, CRS, and optional-dependency failures.\n\n## Minimal install and import checks\n\nUse a fresh environment. Python 3.10-3.12 is exercised by the repository CI;\nPython 3.11 is a safe default for ML\u002Fgeospatial dependencies.\n\n```bash\npip install \"segment-geospatial[samgeo2,samgeo3,fast,hq,text,api]\"\npython - \u003C\u003C'PY'\nimport samgeo\nfrom samgeo.model_registry import AVAILABLE_MODELS\nprint(samgeo.__version__)\nprint(AVAILABLE_MODELS)\nPY\n```\n\nFor SAM3 runtime work, verify CUDA before promising a run:\n\n```python\nimport torch\nprint(torch.__version__, torch.version.cuda)\nprint(torch.cuda.is_available(), torch.cuda.device_count())\n```\n\nRun the bundled safe diagnostic when an environment looks questionable:\n\n```bash\npython scripts\u002Fcheck_install.py --check-optional\npython scripts\u002Fcheck_install.py --require-cuda\n```\n\nThe scripts only import modules and inspect lightweight API state; they do not\ndownload model weights or start a service.\n\n## Package entry points and outputs\n\n- Python import: `samgeo`.\n- Distribution: `segment-geospatial`.\n- CLI entry point: `samgeo-api` for the FastAPI service.\n- Main classes: `SamGeo`, `SamGeo2`, `SamGeo3`, `SamGeo3Video`, `LangSAM`,\n  FastSAM\u002FHQ-SAM wrappers, and `ImageCaptioner`.\n- Typical inputs: GeoTIFF, PNG\u002FJPEG, NumPy arrays, URLs, point coordinates,\n  bounding boxes, GeoJSON\u002Fvector prompts, and videos\u002Ftime-series frames.\n- Typical outputs: mask GeoTIFF\u002FPNG, vector GeoPackage\u002FShapefile\u002FGeoJSON,\n  JSON\u002Fdetections from the API, caption\u002Ffeature lists, and blended videos.\n\n## Operating rules\n\n- Do not tell users to open notebooks, scripts, tests, or docs from the original\n  checkout. Use the bundled references and scripts in this skill.\n- Distinguish pixel coordinates from geographic coordinates. If points or boxes\n  are in a CRS, pass `point_crs` or `box_crs` where the selected API supports it.\n- SamGeo preserves the source raster CRS during segmentation; it does not\n  automatically reproject masks to EPSG:4326.\n- SAM3\u002FSAM3.1 guidance should be treated as CUDA-backed unless the task is only\n  inspecting imports or mock-backed tests. CPU import checks are not proof of\n  real SAM3 runtime capability.\n- Model-weight downloads, Hugging Face authentication, map-tile downloads,\n  long-running inference, notebooks, QGIS plugin operations, and detectree2 or\n  GDAL-specific paths require explicit user\u002Fenvironment readiness.\n- The user requested `not import` for this generated skill run; do not run the\n  repo-skill import helper unless a later instruction explicitly approves it.\n\n## Provenance and refresh\n\nRead [repo-provenance.md](references\u002Frepo-provenance.md) before deciding this\nskill matches a new checkout. If the commit, package version, public APIs, or\nmajor example\u002Ftest paths differ, refresh the skill before relying on stale\nrouting or API details.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill segment-geospatial",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill segment-geospatial",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill segment-geospatial","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-dependencies.md","REFERENCE","参考文档",5402,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Freferences\u002Finstallation-and-dependencies.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmodel-and-workflow-overview.md",5136,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Freferences\u002Fmodel-and-workflow-overview.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",2332,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",6025,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_install.py","SCRIPT","脚本",5929,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fscripts\u002Fcheck_install.py",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]