[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BZCYNT3Y70RPF7BMBHPY83":3,"skill-same:01M7BZCYNT3Y70RPF7BMBHPY83":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BZCYNT3Y70RPF7BMBHPY83","geospatial-routing-data",null,"Handle depot\u002Fstation coordinates, ID↔index mappings, distance matrices, and route-distance reconstruction for routing outputs that use latitude\u002Flongitude.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_clean_20261004_finalized\u002Ftasks\u002Fbike-rebalance\u002Frepaired_skill\u002Fgeospatial-routing-data\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: geospatial-routing-data\ndescription: Handle depot\u002Fstation coordinates, ID↔index mappings, distance matrices, and route-distance reconstruction for routing outputs that use latitude\u002Flongitude.\n---\n\n# Geospatial Routing Data\n\nUse this skill before building a routing model or validating a routing report that contains coordinates, depots, station IDs, and route sequences.\n\nThe main risk is mixing user-facing IDs with internal array indices or using a different distance metric from the task.\n\n## Parse Data Safely\n\nLoad structured data with a parser and build explicit mappings between external IDs and internal indices.\n\n```python\nstation_ids = [int(rec[\"id\"]) for rec in station_records]\nif len(station_ids) != len(set(station_ids)):\n    raise ValueError(\"duplicate station ids\")\n\nid_to_idx = {sid: idx for idx, sid in enumerate(station_ids)}\nidx_to_id = {idx: sid for sid, idx in id_to_idx.items()}\n```\n\nDecision rule: use internal indices in optimization variables; convert back to original IDs only when producing the final report.\n\n## Coordinate Validation\n\nValidate coordinate ranges before building distances.\n\n```python\ndef parse_location(record):\n    lat = float(record[\"latitude\"])\n    lon = float(record[\"longitude\"])\n    if not (-90.0 \u003C= lat \u003C= 90.0):\n        raise ValueError(\"latitude out of range\")\n    if not (-180.0 \u003C= lon \u003C= 180.0):\n        raise ValueError(\"longitude out of range\")\n    return {\"latitude\": lat, \"longitude\": lon}\n```\n\n## Great-Circle Distance\n\nMatch the task’s declared distance metric and constants; if the statement provides an Earth radius, use that exact value.\n\n```python\nimport math\n\ndef great_circle(a, b, radius):\n    deg_to_rad = math.pi \u002F 180.0\n    lat1, lon1 = float(a[\"latitude\"]), float(a[\"longitude\"])\n    lat2, lon2 = float(b[\"latitude\"]), float(b[\"longitude\"])\n\n    phi1 = (90.0 - lat1) * deg_to_rad\n    phi2 = (90.0 - lat2) * deg_to_rad\n    theta1 = lon1 * deg_to_rad\n    theta2 = lon2 * deg_to_rad\n\n    cos_arc = (\n        math.sin(phi1) * math.sin(phi2) * math.cos(theta1 - theta2)\n        + math.cos(phi1) * math.cos(phi2)\n    )\n    cos_arc = max(-1.0, min(1.0, cos_arc))\n    return math.acos(cos_arc) * float(radius)\n```\n\nDecision rule: never mix Euclidean distance on degrees, a different radius\u002Funit system, or rounded distances inside the objective.\n\n## Route Distance Reconstruction\n\nRecompute reported travel distance from route sequences using the same arc set and distance function.\n\n```python\ndef pairwise(items):\n    return zip(items, items[1:])\n\ndef route_distance(route_nodes, dist):\n    return sum(dist[i, j] for i, j in pairwise(route_nodes))\n```\n\nRead references\u002Fsandbox-path-and-tooling-awareness.md when you can locate the input path but cannot read it due to tool sandbox restrictions or malformed shell commands. Skip when input reading is already working and reproducible.\n\n## Common Pitfalls\n\n- Treating external IDs as contiguous indices, causing mis-addressed distances, constraints, or reports.\n- Using the wrong distance metric\u002Funits\u002Fconstant (e.g., wrong Earth radius) or copying distances instead of reconstructing from coordinates.\n- Computing route distance from a different arc set than the solver used (missing depot arcs or allowing forbidden arcs).\n","# Geospatial Routing Data\n\nUse this skill before building a routing model or validating a routing report that contains coordinates, depots, station IDs, and route sequences.\n\nThe main risk is mixing user-facing IDs with internal array indices or using a different distance metric from the task.\n\n## Parse Data Safely\n\nLoad structured data with a parser and build explicit mappings between external IDs and internal indices.\n\n```python\nstation_ids = [int(rec[\"id\"]) for rec in station_records]\nif len(station_ids) != len(set(station_ids)):\n    raise ValueError(\"duplicate station ids\")\n\nid_to_idx = {sid: idx for idx, sid in enumerate(station_ids)}\nidx_to_id = {idx: sid for sid, idx in id_to_idx.items()}\n```\n\nDecision rule: use internal indices in optimization variables; convert back to original IDs only when producing the final report.\n\n## Coordinate Validation\n\nValidate coordinate ranges before building distances.\n\n```python\ndef parse_location(record):\n    lat = float(record[\"latitude\"])\n    lon = float(record[\"longitude\"])\n    if not (-90.0 \u003C= lat \u003C= 90.0):\n        raise ValueError(\"latitude out of range\")\n    if not (-180.0 \u003C= lon \u003C= 180.0):\n        raise ValueError(\"longitude out of range\")\n    return {\"latitude\": lat, \"longitude\": lon}\n```\n\n## Great-Circle Distance\n\nMatch the task’s declared distance metric and constants; if the statement provides an Earth radius, use that exact value.\n\n```python\nimport math\n\ndef great_circle(a, b, radius):\n    deg_to_rad = math.pi \u002F 180.0\n    lat1, lon1 = float(a[\"latitude\"]), float(a[\"longitude\"])\n    lat2, lon2 = float(b[\"latitude\"]), float(b[\"longitude\"])\n\n    phi1 = (90.0 - lat1) * deg_to_rad\n    phi2 = (90.0 - lat2) * deg_to_rad\n    theta1 = lon1 * deg_to_rad\n    theta2 = lon2 * deg_to_rad\n\n    cos_arc = (\n        math.sin(phi1) * math.sin(phi2) * math.cos(theta1 - theta2)\n        + math.cos(phi1) * math.cos(phi2)\n    )\n    cos_arc = max(-1.0, min(1.0, cos_arc))\n    return math.acos(cos_arc) * float(radius)\n```\n\nDecision rule: never mix Euclidean distance on degrees, a different radius\u002Funit system, or rounded distances inside the objective.\n\n## Route Distance Reconstruction\n\nRecompute reported travel distance from route sequences using the same arc set and distance function.\n\n```python\ndef pairwise(items):\n    return zip(items, items[1:])\n\ndef route_distance(route_nodes, dist):\n    return sum(dist[i, j] for i, j in pairwise(route_nodes))\n```\n\nRead references\u002Fsandbox-path-and-tooling-awareness.md when you can locate the input path but cannot read it due to tool sandbox restrictions or malformed shell commands. Skip when input reading is already working and reproducible.\n\n## Common Pitfalls\n\n- Treating external IDs as contiguous indices, causing mis-addressed distances, constraints, or reports.\n- Using the wrong distance metric\u002Funits\u002Fconstant (e.g., wrong Earth radius) or copying distances instead of reconstructing from coordinates.\n- Computing route distance from a different arc set than the solver used (missing depot arcs or allowing forbidden arcs).\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FSkillGrad\u002Fmain31_clean_20261004_finalized\u002Ftasks\u002Fbike-rebalance\u002Frepaired_skill\u002Fgeospatial-routing-data",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill geospatial-routing-data",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill geospatial-routing-data",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill geospatial-routing-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillGrad\u002Fmain31_clean_20261004_finalized\u002Ftasks\u002Fbike-rebalance\u002Frepaired_skill\u002Fgeospatial-routing-data\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]