[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794VN8MAQE4TFRY7D89Q3JC":3,"skill-same:01M794VN8MAQE4TFRY7D89Q3JC":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},"01M794VN8MAQE4TFRY7D89Q3JC","api-server",null,"Guides segment-geospatial's FastAPI service, samgeo-api CLI, segmentation endpoints, model\u002Fcache behavior, output formats, and safe API smoke checks.","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\u002Fapi-server\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: api-server\ndescription: \"Guides segment-geospatial's FastAPI service, samgeo-api CLI,\n  segmentation endpoints, model\u002Fcache behavior, output formats, and safe API\n  smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# SamGeo REST API server\n\nUse this sub-skill when the task is about serving SamGeo segmentation over HTTP,\nusing the `samgeo-api` command, sending curl\u002FPython client requests, validating\nendpoint parameters, or debugging API model\u002Fimage caches.\n\n## Read this when\n\n- The user asks for `samgeo-api`, `uvicorn samgeo.api:app`, FastAPI docs, or\n  Swagger UI.\n- The task calls `GET \u002Fhealth`, `GET \u002Fmodels`, `DELETE \u002Fmodels`,\n  `POST \u002Fsegment\u002Fautomatic`, `POST \u002Fsegment\u002Fpredict`, or `POST \u002Fsegment\u002Ftext`.\n- The user needs `output_format=geojson|geotiff|png|json|detections`.\n- A request fails with invalid model ids, missing prompt parameters, bad output\n  format, cache problems, or GPU memory retention.\n\n## Route elsewhere\n\n- Direct Python class usage: [core-segmentation](..\u002Fcore-segmentation\u002FSKILL.md)\n  or [samgeo3-workflows](..\u002Fsamgeo3-workflows\u002FSKILL.md).\n- CRS\u002Fraster\u002Fvector prep before an API upload: [geospatial-utilities](..\u002Fgeospatial-utilities\u002FSKILL.md).\n- Optional model wrapper details: [specialized-models](..\u002Fspecialized-models\u002FSKILL.md).\n\n## API operating sequence\n\n1. Install `segment-geospatial[api]` plus the model extra needed by requests.\n   For SAM3 text endpoints, include `[samgeo3]` and verify CUDA\u002Fmodel access.\n2. Run the safe smoke script before starting a service:\n   `python scripts\u002Fapi_smoke.py --local-testclient`.\n3. Start the service only when a listener is wanted:\n   `samgeo-api --host 0.0.0.0 --port 8000`.\n4. Use `GET \u002Fmodels` to inspect available and loaded models.\n5. Use `DELETE \u002Fmodels` to clear model cache and free GPU memory after large\n   jobs.\n\n## References and scripts\n\n- [api-reference.md](references\u002Fapi-reference.md) lists endpoints, parameters,\n  model ids, output formats, and cache behavior.\n- [workflows.md](references\u002Fworkflows.md) gives server start, curl, and Python\n  client examples.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) covers common API errors\n  and cache\u002FGPU recovery.\n- [scripts\u002Fapi_smoke.py](scripts\u002Fapi_smoke.py) probes either the local FastAPI\n  TestClient or a running server without loading model weights.\n\n## Native validation candidates\n\n`tests\u002Ftest_api.py` is a strong native candidate because it uses mocks for model\nloads while validating endpoint errors, model registry exposure, output format\nchecks, SAM3 point prompt dispatch, and cache-key behavior.\n","# SamGeo REST API server\n\nUse this sub-skill when the task is about serving SamGeo segmentation over HTTP,\nusing the `samgeo-api` command, sending curl\u002FPython client requests, validating\nendpoint parameters, or debugging API model\u002Fimage caches.\n\n## Read this when\n\n- The user asks for `samgeo-api`, `uvicorn samgeo.api:app`, FastAPI docs, or\n  Swagger UI.\n- The task calls `GET \u002Fhealth`, `GET \u002Fmodels`, `DELETE \u002Fmodels`,\n  `POST \u002Fsegment\u002Fautomatic`, `POST \u002Fsegment\u002Fpredict`, or `POST \u002Fsegment\u002Ftext`.\n- The user needs `output_format=geojson|geotiff|png|json|detections`.\n- A request fails with invalid model ids, missing prompt parameters, bad output\n  format, cache problems, or GPU memory retention.\n\n## Route elsewhere\n\n- Direct Python class usage: [core-segmentation](..\u002Fcore-segmentation\u002FSKILL.md)\n  or [samgeo3-workflows](..\u002Fsamgeo3-workflows\u002FSKILL.md).\n- CRS\u002Fraster\u002Fvector prep before an API upload: [geospatial-utilities](..\u002Fgeospatial-utilities\u002FSKILL.md).\n- Optional model wrapper details: [specialized-models](..\u002Fspecialized-models\u002FSKILL.md).\n\n## API operating sequence\n\n1. Install `segment-geospatial[api]` plus the model extra needed by requests.\n   For SAM3 text endpoints, include `[samgeo3]` and verify CUDA\u002Fmodel access.\n2. Run the safe smoke script before starting a service:\n   `python scripts\u002Fapi_smoke.py --local-testclient`.\n3. Start the service only when a listener is wanted:\n   `samgeo-api --host 0.0.0.0 --port 8000`.\n4. Use `GET \u002Fmodels` to inspect available and loaded models.\n5. Use `DELETE \u002Fmodels` to clear model cache and free GPU memory after large\n   jobs.\n\n## References and scripts\n\n- [api-reference.md](references\u002Fapi-reference.md) lists endpoints, parameters,\n  model ids, output formats, and cache behavior.\n- [workflows.md](references\u002Fworkflows.md) gives server start, curl, and Python\n  client examples.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) covers common API errors\n  and cache\u002FGPU recovery.\n- [scripts\u002Fapi_smoke.py](scripts\u002Fapi_smoke.py) probes either the local FastAPI\n  TestClient or a running server without loading model weights.\n\n## Native validation candidates\n\n`tests\u002Ftest_api.py` is a strong native candidate because it uses mocks for model\nloads while validating endpoint errors, model registry exposure, output format\nchecks, SAM3 point prompt dispatch, and cache-key behavior.\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\u002Fapi-server",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 api-server",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill api-server",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill api-server","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\u002Fapi-server\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3664,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fapi-server\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",2167,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fapi-server\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",2283,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fapi-server\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fapi_smoke.py","SCRIPT","脚本",2117,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-geospatial\u002Fsub-skills\u002Fapi-server\u002Fscripts\u002Fapi_smoke.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",[],[]]