[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792894EB5G77KDQNES669X2":3,"skill-same:01M792894EB5G77KDQNES669X2":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},"01M792894EB5G77KDQNES669X2","graph-modeling-io",null,"Manipulate OSMnx NetworkX\u002FGeoPandas graph data structures and persist or restore them safely.","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\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graph-modeling-io\ndescription: \"Manipulate OSMnx NetworkX\u002FGeoPandas graph data structures and\n  persist or restore them safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Graph Modeling and I\u002FO\n\nUse this sub-skill when the task is about an existing OSMnx graph or GeoDataFrame: validating its schema, converting between NetworkX and GeoPandas representations, projecting CRS, simplifying or consolidating topology, truncating components, or saving\u002Floading graph files.\n\n## Route here\n\n- Validate OSMnx graph, node\u002Fedge GeoDataFrame, or features GeoDataFrame invariants.\n- Convert `MultiDiGraph`\u002F`MultiGraph` objects to\u002Ffrom node and edge GeoDataFrames.\n- Create directed\u002Fundirected graph views with `to_digraph` or `to_undirected`.\n- Project geometries, GeoDataFrames, or graphs with `project_geometry`, `project_gdf`, or `project_graph`.\n- Simplify topology, consolidate intersections, truncate by distance\u002Fbbox\u002Fpolygon, or keep the largest weak\u002Fstrong component.\n- Persist or restore graph data with GraphML, GeoPackage, or OSM XML.\n\n## Route elsewhere\n\n- Downloading, geocoding, Overpass\u002FNominatim settings, OSM tag queries, or local XML acquisition belong to `data-acquisition`.\n- Nearest-node\u002Fedge search, route computation, network statistics, bearings, orientation entropy, speeds, or travel times belong to `routing-analysis`.\n- Elevation, grade calculation, and plotting belong to `elevation-visualization`.\n\n## Operating references\n\nRead these before acting:\n\n1. [Data model and transformations](references\u002Fdata-model.md) for graph\u002FGDF invariants, validation, conversion, projection, simplification, consolidation, truncation, and difficult recovery patterns.\n2. [Persistence and file formats](references\u002Fio-reference.md) for GraphML, GeoPackage, OSM XML, dtype restoration, and format-choice rules.\n3. [Troubleshooting graph modeling and I\u002FO](references\u002Ftroubleshooting.md) for predictable validation, CRS, simplification, truncation, and save\u002Fload failures.\n\nBundled smoke script:\n\n- [Graph\u002FGDF\u002FGraphML smoke test](scripts\u002Fvalidate_graph_io_smoke.py) creates a tiny graph, validates it, round-trips through GeoDataFrames, saves\u002Floads GraphML in a temporary directory, and prints a concise success summary.\n\n## Minimal workflow\n\n1. Identify the object type: OSMnx `networkx.MultiDiGraph`, node\u002Fedge GeoDataFrames, features GeoDataFrame, geometry, or file path.\n2. Validate early with `osmnx.convert.validate_graph`, `validate_node_edge_gdfs`, or `validate_features_gdf`.\n3. Normalize the data model before analysis or persistence: ensure CRS, node `x`\u002F`y`, edge `(u, v, key)` index, edge `osmid`, and edge `length` are present with compatible types.\n4. Use projection before distance\u002Ftolerance operations that require metric units, then project back to lat-long only when needed for geographic output.\n5. Choose persistence format deliberately: GraphML for future OSMnx work, GeoPackage for GIS layer exchange, OSM XML only for unsimplified\u002Funprojected OSM-style export.\n6. Run the bundled smoke script when an environment or installation may be suspect.\n","# Graph Modeling and I\u002FO\n\nUse this sub-skill when the task is about an existing OSMnx graph or GeoDataFrame: validating its schema, converting between NetworkX and GeoPandas representations, projecting CRS, simplifying or consolidating topology, truncating components, or saving\u002Floading graph files.\n\n## Route here\n\n- Validate OSMnx graph, node\u002Fedge GeoDataFrame, or features GeoDataFrame invariants.\n- Convert `MultiDiGraph`\u002F`MultiGraph` objects to\u002Ffrom node and edge GeoDataFrames.\n- Create directed\u002Fundirected graph views with `to_digraph` or `to_undirected`.\n- Project geometries, GeoDataFrames, or graphs with `project_geometry`, `project_gdf`, or `project_graph`.\n- Simplify topology, consolidate intersections, truncate by distance\u002Fbbox\u002Fpolygon, or keep the largest weak\u002Fstrong component.\n- Persist or restore graph data with GraphML, GeoPackage, or OSM XML.\n\n## Route elsewhere\n\n- Downloading, geocoding, Overpass\u002FNominatim settings, OSM tag queries, or local XML acquisition belong to `data-acquisition`.\n- Nearest-node\u002Fedge search, route computation, network statistics, bearings, orientation entropy, speeds, or travel times belong to `routing-analysis`.\n- Elevation, grade calculation, and plotting belong to `elevation-visualization`.\n\n## Operating references\n\nRead these before acting:\n\n1. [Data model and transformations](references\u002Fdata-model.md) for graph\u002FGDF invariants, validation, conversion, projection, simplification, consolidation, truncation, and difficult recovery patterns.\n2. [Persistence and file formats](references\u002Fio-reference.md) for GraphML, GeoPackage, OSM XML, dtype restoration, and format-choice rules.\n3. [Troubleshooting graph modeling and I\u002FO](references\u002Ftroubleshooting.md) for predictable validation, CRS, simplification, truncation, and save\u002Fload failures.\n\nBundled smoke script:\n\n- [Graph\u002FGDF\u002FGraphML smoke test](scripts\u002Fvalidate_graph_io_smoke.py) creates a tiny graph, validates it, round-trips through GeoDataFrames, saves\u002Floads GraphML in a temporary directory, and prints a concise success summary.\n\n## Minimal workflow\n\n1. Identify the object type: OSMnx `networkx.MultiDiGraph`, node\u002Fedge GeoDataFrames, features GeoDataFrame, geometry, or file path.\n2. Validate early with `osmnx.convert.validate_graph`, `validate_node_edge_gdfs`, or `validate_features_gdf`.\n3. Normalize the data model before analysis or persistence: ensure CRS, node `x`\u002F`y`, edge `(u, v, key)` index, edge `osmid`, and edge `length` are present with compatible types.\n4. Use projection before distance\u002Ftolerance operations that require metric units, then project back to lat-long only when needed for geographic output.\n5. Choose persistence format deliberately: GraphML for future OSMnx work, GeoPackage for GIS layer exchange, OSM XML only for unsimplified\u002Funprojected OSM-style export.\n6. Run the bundled smoke script when an environment or installation may be suspect.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io",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 graph-modeling-io",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-modeling-io",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-modeling-io","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-model.md","REFERENCE","参考文档",13757,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002Freferences\u002Fdata-model.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fio-reference.md",8768,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002Freferences\u002Fio-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",12286,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fvalidate_graph_io_smoke.py","SCRIPT","脚本",4695,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fosmnx\u002Fsub-skills\u002Fgraph-modeling-io\u002Fscripts\u002Fvalidate_graph_io_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",[],[]]