[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794W01K8232CQKVMCH308GP":3,"skill-same:01M794W01K8232CQKVMCH308GP":66},{"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},"01M794W01K8232CQKVMCH308GP","specialized-models",null,"Routes SamGeo optional model integrations including FastSAM, HQ-SAM, LangSAM\u002FGroundingDINO text prompts, BLIP captioning, detectree2 notes, and FER\u002FGDAL gaps.","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\u002Fsub-skills\u002Fspecialized-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: specialized-models\ndescription: \"Routes SamGeo optional model integrations including FastSAM,\n  HQ-SAM, LangSAM\u002FGroundingDINO text prompts, BLIP captioning, detectree2 notes,\n  and FER\u002FGDAL gaps.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Specialized model integrations\n\nUse this sub-skill for optional model families and auxiliary workflows that sit\noutside the primary `SamGeo`, `SamGeo2`, and `SamGeo3` routes.\n\n## Read this when\n\n- The user asks for FastSAM (`samgeo.fast_sam`) speed-oriented segmentation.\n- The user asks for HQ-SAM (`samgeo.hq_sam`) high-quality masks.\n- The user asks for `LangSAM`, GroundingDINO, or text prompts with SAM1\u002FSAM2.\n- The user asks for BLIP image captioning or extracting aerial features from a\n  caption\u002Fimage.\n- The user asks about detectree2 tree crowns or FER\u002FGDAL feature edge\n  reconstruction and needs to know why those are optional\u002Fgap paths.\n\n## Route elsewhere\n\n- Standard SAM1\u002FSAM2 segmentation: [core-segmentation](..\u002Fcore-segmentation\u002FSKILL.md).\n- SAM3 text\u002Fprompt\u002Fvideo\u002Ftiled workflows: [samgeo3-workflows](..\u002Fsamgeo3-workflows\u002FSKILL.md).\n- Raster\u002Fvector\u002FCRS utilities: [geospatial-utilities](..\u002Fgeospatial-utilities\u002FSKILL.md).\n- HTTP API text\u002Fautomatic\u002Fpredict endpoints: [api-server](..\u002Fapi-server\u002FSKILL.md).\n\n## Before using optional models\n\n1. Install only the extra needed for the workflow: `[fast]`, `[hq]`, `[text]`,\n   `[samgeo3]`, or a selected combined set.\n2. Run [scripts\u002Foptional_model_imports.py](scripts\u002Foptional_model_imports.py)\n   before constructing models.\n3. Confirm whether the workflow downloads model weights, Hugging Face assets,\n   spaCy models, map tiles, or detectree2\u002FDetectron2 dependencies.\n4. Use one image\u002Fcrop and save a simple mask before scaling to batches.\n\n## References and scripts\n\n- [model-overview.md](references\u002Fmodel-overview.md) compares FastSAM, HQ-SAM,\n  LangSAM, captioning, detectree2, and FER support.\n- [workflows.md](references\u002Fworkflows.md) gives focused recipes for the\n  optional workflows.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) covers optional import,\n  model download, `pkg_resources`, GroundingDINO, BLIP\u002FspaCy, detectree2, and\n  GDAL issues.\n- [scripts\u002Foptional_model_imports.py](scripts\u002Foptional_model_imports.py) checks\n  optional imports without loading weights; caption import is opt-in because it\n  performs a network vocabulary fetch.\n\n## Validation candidates\n\n- FastSAM, HQ-SAM, LangSAM, and captioning example notebooks are evidence and\n  optional native candidates; they require model\u002Fnetwork readiness.\n- detectree2 and FER are documented as optional gaps in this skill because the\n  prepared environment did not install Detectron2\u002Fdetectree2 or GDAL.\n","# Specialized model integrations\n\nUse this sub-skill for optional model families and auxiliary workflows that sit\noutside the primary `SamGeo`, `SamGeo2`, and `SamGeo3` routes.\n\n## Read this when\n\n- The user asks for FastSAM (`samgeo.fast_sam`) speed-oriented segmentation.\n- The user asks for HQ-SAM (`samgeo.hq_sam`) high-quality masks.\n- The user asks for `LangSAM`, GroundingDINO, or text prompts with SAM1\u002FSAM2.\n- The user asks for BLIP image captioning or extracting aerial features from a\n  caption\u002Fimage.\n- The user asks about detectree2 tree crowns or FER\u002FGDAL feature edge\n  reconstruction and needs to know why those are optional\u002Fgap paths.\n\n## Route elsewhere\n\n- Standard SAM1\u002FSAM2 segmentation: [core-segmentation](..\u002Fcore-segmentation\u002FSKILL.md).\n- SAM3 text\u002Fprompt\u002Fvideo\u002Ftiled workflows: [samgeo3-workflows](..\u002Fsamgeo3-workflows\u002FSKILL.md).\n- Raster\u002Fvector\u002FCRS utilities: [geospatial-utilities](..\u002Fgeospatial-utilities\u002FSKILL.md).\n- HTTP API text\u002Fautomatic\u002Fpredict endpoints: [api-server](..\u002Fapi-server\u002FSKILL.md).\n\n## Before using optional models\n\n1. Install only the extra needed for the workflow: `[fast]`, `[hq]`, `[text]`,\n   `[samgeo3]`, or a selected combined set.\n2. Run [scripts\u002Foptional_model_imports.py](scripts\u002Foptional_model_imports.py)\n   before constructing models.\n3. Confirm whether the workflow downloads model weights, Hugging Face assets,\n   spaCy models, map tiles, or detectree2\u002FDetectron2 dependencies.\n4. Use one image\u002Fcrop and save a simple mask before scaling to batches.\n\n## References and scripts\n\n- [model-overview.md](references\u002Fmodel-overview.md) compares FastSAM, HQ-SAM,\n  LangSAM, captioning, detectree2, and FER support.\n- [workflows.md](references\u002Fworkflows.md) gives focused recipes for the\n  optional workflows.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) covers optional import,\n  model download, `pkg_resources`, GroundingDINO, BLIP\u002FspaCy, detectree2, and\n  GDAL issues.\n- [scripts\u002Foptional_model_imports.py](scripts\u002Foptional_model_imports.py) checks\n  optional imports without loading weights; caption import is opt-in because it\n  performs a network vocabulary fetch.\n\n## Validation candidates\n\n- FastSAM, HQ-SAM, LangSAM, and captioning example notebooks are evidence and\n  optional native candidates; they require model\u002Fnetwork readiness.\n- detectree2 and FER are documented as optional gaps in this skill because the\n  prepared environment did not install Detectron2\u002Fdetectree2 or GDAL.\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\u002Fsub-skills\u002Fspecialized-models",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 specialized-models",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill specialized-models",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill specialized-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fspecialized-models\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmodel-overview.md","REFERENCE","参考文档",2687,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fspecialized-models\u002Freferences\u002Fmodel-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",2632,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fspecialized-models\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",2707,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fspecialized-models\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Foptional_model_imports.py","SCRIPT","脚本",2588,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fspecialized-models\u002Fscripts\u002Foptional_model_imports.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]