[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5936AMK40618VQC4HGA5P":3,"skill-same:01M7F5936AMK40618VQC4HGA5P":70},{"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},"01M7F5936AMK40618VQC4HGA5P","scenario-studio",null,"Define, generate, inspect, and troubleshoot SMARTS scenarios from supported maps, traffic, missions, social agents, bubbles, surface patches, traffic histories, and metadata. Use this route when the task is scenario DSL or generated scenario layout; route live SUMO\u002FTraCI, Envision replay, or environment lifecycle elsewhere.","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\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: scenario-studio\ndescription: \"Define, generate, inspect, and troubleshoot SMARTS scenarios from\n  supported maps, traffic, missions, social agents, bubbles, surface patches,\n  traffic histories, and metadata. Use this route when the task is scenario DSL\n  or generated scenario layout; route live SUMO\u002FTraCI, Envision replay, or\n  environment lifecycle elsewhere.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Scenario Studio\n\nUse this route when you need a self-contained SMARTS scenario definition or\nneed to explain why generated scenario artifacts are missing or incompatible.\nThe runtime DSL is `smarts.sstudio.types` (`smarts.sstudio.sstypes` is the\nimplementation module) and the high-level entry point is\n`smarts.sstudio.genscenario.gen_scenario(scenario, output_dir, seed=42)`.\n\n## Decide the boundary first\n\n- Use `Scenario` from `smarts.sstudio.types` for the authoring DSL. It combines\n  `map_spec`, named `traffic`, `ego_missions`, `social_agent_missions`,\n  `bubbles`, `friction_maps`, `traffic_histories`, and `scenario_metadata`.\n- Use the runtime `smarts.core.scenario.Scenario` only after generation, when\n  SMARTS discovers a map and `build\u002F` assets. It is not the authoring dataclass.\n- Use `scripts\u002Fvalidate_scenario_layout.py` for a read-only layout check and\n  `scripts\u002Fgenerate_minimal_scenario.py` for a bounded local fixture. Both take\n  explicit paths and never start SUMO, TraCI, Envision, or a network download.\n- Route `scl scenario build`, `scl scenario clean`, SUMO\u002FTraCI, Waymo\u002FArgoverse\n  conversion, and other system integrations to `cli-integrations`.\n- Route Gym\u002FRLlib environment reset\u002Fstep\u002Fclose to `simulation-environments`.\n  Route Envision replay and rendered sensors to `sensors-visualization`.\n\nRead the linked references before authoring a nontrivial scenario:\n\n- [API reference](references\u002Fapi-reference.md) for live constructor signatures\n  and the stable meaning of each DSL object.\n- [Workflows](references\u002Fworkflows.md) for minimal generation, custom maps,\n  social agents, histories, deterministic rebuilds, and discovery.\n- [Data formats](references\u002Fdata-formats.md) for source-vs-build layout and\n  artifact ownership.\n- [Maps and traffic](references\u002Fmaps-and-traffic.md) for map engines, routes,\n  flows, missions, bubbles, friction, and dataset boundaries.\n- [Troubleshooting](references\u002Ftroubleshooting.md) for actionable recovery.\n\n## Minimal authoring contract\n\n1. Create an application-owned scenario directory and put a `scenario.py` in\n   it. Keep input maps and data paths explicit; do not depend on the current\n   working directory.\n2. Select a map source: `map.net.xml`\u002Fanother `.net.xml` for SUMO, `map.xodr`\n   for OpenDRIVE, a Waymo `.tfrecord` source, an Argoverse map archive, or a\n   `MapSpec(source=..., builder_fn=...)` for a custom `RoadMap` implementation.\n3. Define named traffic, missions, and optional social\u002Fbubble\u002Fhistory metadata.\n   Use edge\u002Flane\u002Foffset tuples only when the referenced roads and lanes exist.\n4. Call `gen_scenario(..., output_dir=scenario_dir, seed=\u003Cinteger>)`. Set the\n   same seed for comparable generated output; seed random choices before the\n   call as well when authoring code uses Python or NumPy randomness.\n5. Validate the source and then the generated `build\u002F` tree. Build assets are\n   generated state, not source code; regenerate after changing the DSL or map.\n6. Before simulation, ensure the selected engine is compatible with the map and\n   manually check that ego mission starts do not overlap traffic starts. Studio\n   does not detect that collision-prone overlap for you.\n\n## Fast recipe\n\n```python\nfrom pathlib import Path\nfrom smarts.sstudio import gen_scenario, types as t\n\nroot = Path(\"my_scenario\").resolve()\ncar = t.TrafficActor(name=\"car\")\nscenario = t.Scenario(\n    map_spec=t.MapSpec(source=str(root \u002F \"map.net.xml\")),\n    traffic={\"background\": t.Traffic(\n        engine=\"SUMO\",\n        flows=[t.Flow(\n            route=t.Route(begin=(\"edge_in\", 0, \"random\"),\n                          end=(\"edge_out\", 0, \"max\")),\n            rate=60, begin=0, end=60, actors={car: 1.0},\n        )]\n    )},\n    ego_missions=[t.Mission(t.Route(\n        begin=(\"edge_in\", 1, 10), end=(\"edge_out\", 1, \"max\")\n    ))],\n)\ngen_scenario(scenario, root, seed=42)\n```\n\n`SUMO` traffic requires a SUMO road network and the SUMO Python\u002Fruntime\nintegration; use `engine=\"SMARTS\"` for supported non-SUMO road maps. The recipe\nis a shape example: replace edge ids with ids from the selected map and install\noptional dependencies before claiming a successful build.\n\n## Generated-artifact explanation\n\nA successful generation normally creates `build\u002Fbuild.db`, a map artifact under\n`build\u002Fmap\u002F`, route files under `build\u002Ftraffic\u002F`, and optional files for\nmissions, social agents, bubbles, friction, histories, and metadata. The exact\nset is determined by non-empty `Scenario` fields; see the data-format reference.\n`smarts.core.scenario.Scenario.is_valid_scenario()` checks that a map can be\nbuilt, not that every optional artifact or traffic combination is semantically\nsafe. Missing `build\u002Fmap\u002Fmap.glb`, stale `build.db`, or absent route files means\nregenerate\u002Fbuild rather than edit generated pickle\u002FXML files manually.\n\n## Checks and handoff\n\nRun the validator from any cwd:\n\n```bash\npython \u002Fpath\u002Fto\u002Fskills\u002Fdisco\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Fscripts\u002Fvalidate_scenario_layout.py \\\n  --scenario \u002Fabsolute\u002Fpath\u002Fto\u002Fmy_scenario --require-build\n```\n\nFor a safe local fixture (OpenDRIVE is used only when the installed optional\nparser can load the supplied map), write to an explicit empty output directory:\n\n```bash\npython \u002Fpath\u002Fto\u002Fskills\u002Fdisco\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Fscripts\u002Fgenerate_minimal_scenario.py \\\n  --map \u002Fabsolute\u002Fpath\u002Fto\u002Fmap.net.xml --output \u002Fabsolute\u002Fpath\u002Fto\u002Fout --seed 42\n```\n\nThe helper refuses to overwrite non-empty output unless `--force` is supplied,\nuses no external service, and exits nonzero with the failing path or import\nreason. Treat missing SUMO, Waymo, Argoverse, or dataset packages as explicit\nintegration gaps, not as evidence that core Scenario Studio is broken.\n","# Scenario Studio\n\nUse this route when you need a self-contained SMARTS scenario definition or\nneed to explain why generated scenario artifacts are missing or incompatible.\nThe runtime DSL is `smarts.sstudio.types` (`smarts.sstudio.sstypes` is the\nimplementation module) and the high-level entry point is\n`smarts.sstudio.genscenario.gen_scenario(scenario, output_dir, seed=42)`.\n\n## Decide the boundary first\n\n- Use `Scenario` from `smarts.sstudio.types` for the authoring DSL. It combines\n  `map_spec`, named `traffic`, `ego_missions`, `social_agent_missions`,\n  `bubbles`, `friction_maps`, `traffic_histories`, and `scenario_metadata`.\n- Use the runtime `smarts.core.scenario.Scenario` only after generation, when\n  SMARTS discovers a map and `build\u002F` assets. It is not the authoring dataclass.\n- Use `scripts\u002Fvalidate_scenario_layout.py` for a read-only layout check and\n  `scripts\u002Fgenerate_minimal_scenario.py` for a bounded local fixture. Both take\n  explicit paths and never start SUMO, TraCI, Envision, or a network download.\n- Route `scl scenario build`, `scl scenario clean`, SUMO\u002FTraCI, Waymo\u002FArgoverse\n  conversion, and other system integrations to `cli-integrations`.\n- Route Gym\u002FRLlib environment reset\u002Fstep\u002Fclose to `simulation-environments`.\n  Route Envision replay and rendered sensors to `sensors-visualization`.\n\nRead the linked references before authoring a nontrivial scenario:\n\n- [API reference](references\u002Fapi-reference.md) for live constructor signatures\n  and the stable meaning of each DSL object.\n- [Workflows](references\u002Fworkflows.md) for minimal generation, custom maps,\n  social agents, histories, deterministic rebuilds, and discovery.\n- [Data formats](references\u002Fdata-formats.md) for source-vs-build layout and\n  artifact ownership.\n- [Maps and traffic](references\u002Fmaps-and-traffic.md) for map engines, routes,\n  flows, missions, bubbles, friction, and dataset boundaries.\n- [Troubleshooting](references\u002Ftroubleshooting.md) for actionable recovery.\n\n## Minimal authoring contract\n\n1. Create an application-owned scenario directory and put a `scenario.py` in\n   it. Keep input maps and data paths explicit; do not depend on the current\n   working directory.\n2. Select a map source: `map.net.xml`\u002Fanother `.net.xml` for SUMO, `map.xodr`\n   for OpenDRIVE, a Waymo `.tfrecord` source, an Argoverse map archive, or a\n   `MapSpec(source=..., builder_fn=...)` for a custom `RoadMap` implementation.\n3. Define named traffic, missions, and optional social\u002Fbubble\u002Fhistory metadata.\n   Use edge\u002Flane\u002Foffset tuples only when the referenced roads and lanes exist.\n4. Call `gen_scenario(..., output_dir=scenario_dir, seed=\u003Cinteger>)`. Set the\n   same seed for comparable generated output; seed random choices before the\n   call as well when authoring code uses Python or NumPy randomness.\n5. Validate the source and then the generated `build\u002F` tree. Build assets are\n   generated state, not source code; regenerate after changing the DSL or map.\n6. Before simulation, ensure the selected engine is compatible with the map and\n   manually check that ego mission starts do not overlap traffic starts. Studio\n   does not detect that collision-prone overlap for you.\n\n## Fast recipe\n\n```python\nfrom pathlib import Path\nfrom smarts.sstudio import gen_scenario, types as t\n\nroot = Path(\"my_scenario\").resolve()\ncar = t.TrafficActor(name=\"car\")\nscenario = t.Scenario(\n    map_spec=t.MapSpec(source=str(root \u002F \"map.net.xml\")),\n    traffic={\"background\": t.Traffic(\n        engine=\"SUMO\",\n        flows=[t.Flow(\n            route=t.Route(begin=(\"edge_in\", 0, \"random\"),\n                          end=(\"edge_out\", 0, \"max\")),\n            rate=60, begin=0, end=60, actors={car: 1.0},\n        )]\n    )},\n    ego_missions=[t.Mission(t.Route(\n        begin=(\"edge_in\", 1, 10), end=(\"edge_out\", 1, \"max\")\n    ))],\n)\ngen_scenario(scenario, root, seed=42)\n```\n\n`SUMO` traffic requires a SUMO road network and the SUMO Python\u002Fruntime\nintegration; use `engine=\"SMARTS\"` for supported non-SUMO road maps. The recipe\nis a shape example: replace edge ids with ids from the selected map and install\noptional dependencies before claiming a successful build.\n\n## Generated-artifact explanation\n\nA successful generation normally creates `build\u002Fbuild.db`, a map artifact under\n`build\u002Fmap\u002F`, route files under `build\u002Ftraffic\u002F`, and optional files for\nmissions, social agents, bubbles, friction, histories, and metadata. The exact\nset is determined by non-empty `Scenario` fields; see the data-format reference.\n`smarts.core.scenario.Scenario.is_valid_scenario()` checks that a map can be\nbuilt, not that every optional artifact or traffic combination is semantically\nsafe. Missing `build\u002Fmap\u002Fmap.glb`, stale `build.db`, or absent route files means\nregenerate\u002Fbuild rather than edit generated pickle\u002FXML files manually.\n\n## Checks and handoff\n\nRun the validator from any cwd:\n\n```bash\npython \u002Fpath\u002Fto\u002Fskills\u002Fdisco\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Fscripts\u002Fvalidate_scenario_layout.py \\\n  --scenario \u002Fabsolute\u002Fpath\u002Fto\u002Fmy_scenario --require-build\n```\n\nFor a safe local fixture (OpenDRIVE is used only when the installed optional\nparser can load the supplied map), write to an explicit empty output directory:\n\n```bash\npython \u002Fpath\u002Fto\u002Fskills\u002Fdisco\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Fscripts\u002Fgenerate_minimal_scenario.py \\\n  --map \u002Fabsolute\u002Fpath\u002Fto\u002Fmap.net.xml --output \u002Fabsolute\u002Fpath\u002Fto\u002Fout --seed 42\n```\n\nThe helper refuses to overwrite non-empty output unless `--force` is supplied,\nuses no external service, and exits nonzero with the failing path or import\nreason. Treat missing SUMO, Waymo, Argoverse, or dataset packages as explicit\nintegration gaps, not as evidence that core Scenario Studio is broken.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio",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 scenario-studio",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill scenario-studio",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill scenario-studio","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",5480,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdata-formats.md",5125,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Freferences\u002Fdata-formats.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fmaps-and-traffic.md",5019,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Freferences\u002Fmaps-and-traffic.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",6145,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Freferences\u002Ftroubleshooting.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fworkflows.md",7430,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsmarts\u002Fsub-skills\u002Fscenario-studio\u002Freferences\u002Fworkflows.md",[71,78,83,90,97,104],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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",[],[]]