[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BWM1CT7MR4FG75X4FRXJV2":3,"skill-same:01M7BWM1CT7MR4FG75X4FRXJV2":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},"01M7BWM1CT7MR4FG75X4FRXJV2","geospatial-analysis",null,"Analyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"MIT","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fearthquake-plate-calculation-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fgeospatial-analysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: geospatial-analysis\ndescription: Analyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.\nlicense: MIT\n---\n\n# Geospatial Analysis with GeoPandas\n\n## Overview\n\nWhen working with geographic data (earthquakes, plate boundaries, etc.), using geopandas with proper coordinate projections provides accurate distance calculations and efficient spatial operations. This guide covers best practices for geospatial analysis.\n\n## Key Concepts\n\n### Geographic vs Projected Coordinate Systems\n\n| Coordinate System | Type | Units | Use Case |\n|-------------------|------|-------|----------|\n| EPSG:4326 (WGS84) | Geographic | Degrees (lat\u002Flon) | Data storage, display |\n| EPSG:4087 (World Equidistant Cylindrical) | Projected | Meters | Distance calculations |\n\n**Critical Rule**: Never calculate distances directly in geographic coordinates (EPSG:4326). Always project to a metric coordinate system first.\n\n### Why Projection Matters\n\n```python\n# ❌ INCORRECT: Calculating distance in EPSG:4326\n# This treats degrees as if they were equal distances everywhere on Earth\ngdf = gpd.GeoDataFrame(..., crs=\"EPSG:4326\")\ndistance = point1.distance(point2)  # Wrong! Returns degrees, not meters\n\n# ✅ CORRECT: Project to metric CRS first\ngdf_projected = gdf.to_crs(\"EPSG:4087\")\ndistance_meters = point1_proj.distance(point2_proj)  # Correct! Returns meters\ndistance_km = distance_meters \u002F 1000.0\n```\n\n## Loading Geospatial Data\n\n### From GeoJSON Files\n\n```python\nimport geopandas as gpd\n\n# Load GeoJSON files directly\ngdf_plates = gpd.read_file(\"plates.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n```\n\n### From Regular Data with Coordinates\n\n```python\nfrom shapely.geometry import Point\nimport geopandas as gpd\n\n# Convert coordinate data to GeoDataFrame\ndata = [\n    {\"id\": 1, \"lat\": 35.0, \"lon\": 140.0, \"value\": 5.5},\n    {\"id\": 2, \"lat\": 36.0, \"lon\": 141.0, \"value\": 6.0},\n]\n\ngeometry = [Point(row[\"lon\"], row[\"lat\"]) for row in data]\ngdf = gpd.GeoDataFrame(data, geometry=geometry, crs=\"EPSG:4326\")\n```\n\n## Spatial Filtering\n\n### Finding Points Within a Polygon\n\n```python\n# Get the polygon of interest\ntarget_poly = gdf_plates[gdf_plates[\"Name\"] == \"Pacific\"].geometry.unary_union\n\n# Filter points that fall within the polygon\npoints_inside = gdf_points[gdf_points.within(target_poly)]\n\nprint(f\"Found {len(points_inside)} points inside the polygon\")\n```\n\n### Using `.unary_union` for Multiple Geometries\n\nWhen you have multiple polygons or lines that should be treated as one:\n\n```python\n# Combine multiple boundary segments into one geometry\nall_boundaries = gdf_boundaries.geometry.unary_union\n\n# Or filter first, then combine\npacific_boundaries = gdf_boundaries[\n    gdf_boundaries[\"Name\"].str.contains(\"PA\")\n].geometry.unary_union\n```\n\n## Distance Calculations\n\n### Point to Line\u002FBoundary Distance\n\n```python\n# 1. Load your data\ngdf_points = gpd.read_file(\"points.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n\n# 2. Project to metric coordinate system\nMETRIC_CRS = \"EPSG:4087\"\npoints_proj = gdf_points.to_crs(METRIC_CRS)\nboundaries_proj = gdf_boundaries.to_crs(METRIC_CRS)\n\n# 3. Combine boundary segments if needed\nboundary_geom = boundaries_proj.geometry.unary_union\n\n# 4. Calculate distances (returns meters)\ngdf_points[\"distance_m\"] = points_proj.geometry.distance(boundary_geom)\ngdf_points[\"distance_km\"] = gdf_points[\"distance_m\"] \u002F 1000.0\n```\n\n### Finding Furthest Point\n\n```python\n# Sort by distance and get the furthest point\nfurthest = gdf_points.nlargest(1, \"distance_km\").iloc[0]\n\nprint(f\"Furthest point: {furthest['id']}\")\nprint(f\"Distance: {furthest['distance_km']:.2f} km\")\n```\n\n## Common Workflow Pattern\n\nHere's a complete example for analyzing earthquakes near plate boundaries:\n\n```python\nimport geopandas as gpd\nfrom shapely.geometry import Point\n\n# 1. Load data\nearthquakes_data = [...]  # Your earthquake data\ngdf_plates = gpd.read_file(\"plates.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n\n# 2. Create earthquake GeoDataFrame\ngeometry = [Point(eq[\"longitude\"], eq[\"latitude\"]) for eq in earthquakes_data]\ngdf_eq = gpd.GeoDataFrame(earthquakes_data, geometry=geometry, crs=\"EPSG:4326\")\n\n# 3. Spatial filtering - find earthquakes in specific plate\ntarget_plate = gdf_plates[gdf_plates[\"Code\"] == \"PA\"].geometry.unary_union\nearthquakes_in_plate = gdf_eq[gdf_eq.within(target_plate)].copy()\n\n# 4. Calculate distances (project to metric CRS)\nMETRIC_CRS = \"EPSG:4087\"\neq_proj = earthquakes_in_plate.to_crs(METRIC_CRS)\n\n# Filter and combine relevant boundaries\nplate_boundaries = gdf_boundaries[\n    gdf_boundaries[\"Name\"].str.contains(\"PA\")\n].to_crs(METRIC_CRS).geometry.unary_union\n\n# Calculate distances\nearthquakes_in_plate[\"distance_km\"] = eq_proj.geometry.distance(plate_boundaries) \u002F 1000.0\n\n# 5. Find the furthest earthquake\nfurthest_eq = earthquakes_in_plate.nlargest(1, \"distance_km\").iloc[0]\n```\n\n## Filtering by Attributes\n\n```python\n# Filter by name or code\npacific_plate = gdf_plates[gdf_plates[\"PlateName\"] == \"Pacific\"]\npacific_plate_alt = gdf_plates[gdf_plates[\"Code\"] == \"PA\"]\n\n# Filter boundaries involving a specific plate\npacific_bounds = gdf_boundaries[\n    (gdf_boundaries[\"PlateA\"] == \"PA\") | \n    (gdf_boundaries[\"PlateB\"] == \"PA\")\n]\n\n# String pattern matching\npa_related = gdf_boundaries[gdf_boundaries[\"Name\"].str.contains(\"PA\")]\n```\n\n## Performance Tips\n\n1. **Filter before projecting**: Reduce data size before expensive operations\n2. **Project once**: Convert to metric CRS once, not in loops\n3. **Use `.unary_union`**: Combine geometries before distance calculations\n4. **Copy when modifying**: Use `.copy()` when creating filtered DataFrames\n\n```python\n# Good: Filter first, then project\nsmall_subset = gdf_large[gdf_large[\"region\"] == \"Pacific\"]\nsmall_projected = small_subset.to_crs(METRIC_CRS)\n\n# Avoid: Projecting large dataset just to filter\n# gdf_projected = gdf_large.to_crs(METRIC_CRS)\n# small_subset = gdf_projected[gdf_projected[\"region\"] == \"Pacific\"]\n```\n\n## Common Pitfalls\n\n| Issue | Problem | Solution |\n|-------|---------|----------|\n| Distance in degrees | Using EPSG:4326 for distance calculations | Project to EPSG:4087 or similar metric CRS |\n| Antimeridian issues | Manual longitude adjustments (±360) | Use geopandas spatial operations, they handle it |\n| Slow performance | Calculating distance to each boundary point separately | Use `.unary_union` + single `.distance()` call |\n| Missing geometries | Some features have no geometry | Filter with `gdf[gdf.geometry.notna()]` |\n\n## When NOT to Use Manual Calculations\n\nAvoid implementing your own:\n- Haversine distance formulas (use geopandas projections instead)\n- Point-in-polygon checks (use `.within()`)\n- Iterating through boundary points (use `.distance()` with `.unary_union`)\n\nThese manual approaches are slower, more error-prone, and less accurate than geopandas methods.\n\n## Best Practices Summary\n\n1. ✅ Load GeoJSON with `gpd.read_file()`\n2. ✅ Use `.within()` for spatial filtering\n3. ✅ Project to metric CRS (`EPSG:4087`) before distance calculations\n4. ✅ Combine geometries with `.unary_union` before distance calculation\n5. ✅ Use `.distance()` method for point-to-geometry distances\n6. ✅ Use `.nlargest()` \u002F `.nsmallest()` for finding extreme values\n7. ❌ Never calculate distances in EPSG:4326\n8. ❌ Avoid manual Haversine implementations\n9. ❌ Don't iterate through individual boundary points\n","# Geospatial Analysis with GeoPandas\n\n## Overview\n\nWhen working with geographic data (earthquakes, plate boundaries, etc.), using geopandas with proper coordinate projections provides accurate distance calculations and efficient spatial operations. This guide covers best practices for geospatial analysis.\n\n## Key Concepts\n\n### Geographic vs Projected Coordinate Systems\n\n| Coordinate System | Type | Units | Use Case |\n|-------------------|------|-------|----------|\n| EPSG:4326 (WGS84) | Geographic | Degrees (lat\u002Flon) | Data storage, display |\n| EPSG:4087 (World Equidistant Cylindrical) | Projected | Meters | Distance calculations |\n\n**Critical Rule**: Never calculate distances directly in geographic coordinates (EPSG:4326). Always project to a metric coordinate system first.\n\n### Why Projection Matters\n\n```python\n# ❌ INCORRECT: Calculating distance in EPSG:4326\n# This treats degrees as if they were equal distances everywhere on Earth\ngdf = gpd.GeoDataFrame(..., crs=\"EPSG:4326\")\ndistance = point1.distance(point2)  # Wrong! Returns degrees, not meters\n\n# ✅ CORRECT: Project to metric CRS first\ngdf_projected = gdf.to_crs(\"EPSG:4087\")\ndistance_meters = point1_proj.distance(point2_proj)  # Correct! Returns meters\ndistance_km = distance_meters \u002F 1000.0\n```\n\n## Loading Geospatial Data\n\n### From GeoJSON Files\n\n```python\nimport geopandas as gpd\n\n# Load GeoJSON files directly\ngdf_plates = gpd.read_file(\"plates.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n```\n\n### From Regular Data with Coordinates\n\n```python\nfrom shapely.geometry import Point\nimport geopandas as gpd\n\n# Convert coordinate data to GeoDataFrame\ndata = [\n    {\"id\": 1, \"lat\": 35.0, \"lon\": 140.0, \"value\": 5.5},\n    {\"id\": 2, \"lat\": 36.0, \"lon\": 141.0, \"value\": 6.0},\n]\n\ngeometry = [Point(row[\"lon\"], row[\"lat\"]) for row in data]\ngdf = gpd.GeoDataFrame(data, geometry=geometry, crs=\"EPSG:4326\")\n```\n\n## Spatial Filtering\n\n### Finding Points Within a Polygon\n\n```python\n# Get the polygon of interest\ntarget_poly = gdf_plates[gdf_plates[\"Name\"] == \"Pacific\"].geometry.unary_union\n\n# Filter points that fall within the polygon\npoints_inside = gdf_points[gdf_points.within(target_poly)]\n\nprint(f\"Found {len(points_inside)} points inside the polygon\")\n```\n\n### Using `.unary_union` for Multiple Geometries\n\nWhen you have multiple polygons or lines that should be treated as one:\n\n```python\n# Combine multiple boundary segments into one geometry\nall_boundaries = gdf_boundaries.geometry.unary_union\n\n# Or filter first, then combine\npacific_boundaries = gdf_boundaries[\n    gdf_boundaries[\"Name\"].str.contains(\"PA\")\n].geometry.unary_union\n```\n\n## Distance Calculations\n\n### Point to Line\u002FBoundary Distance\n\n```python\n# 1. Load your data\ngdf_points = gpd.read_file(\"points.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n\n# 2. Project to metric coordinate system\nMETRIC_CRS = \"EPSG:4087\"\npoints_proj = gdf_points.to_crs(METRIC_CRS)\nboundaries_proj = gdf_boundaries.to_crs(METRIC_CRS)\n\n# 3. Combine boundary segments if needed\nboundary_geom = boundaries_proj.geometry.unary_union\n\n# 4. Calculate distances (returns meters)\ngdf_points[\"distance_m\"] = points_proj.geometry.distance(boundary_geom)\ngdf_points[\"distance_km\"] = gdf_points[\"distance_m\"] \u002F 1000.0\n```\n\n### Finding Furthest Point\n\n```python\n# Sort by distance and get the furthest point\nfurthest = gdf_points.nlargest(1, \"distance_km\").iloc[0]\n\nprint(f\"Furthest point: {furthest['id']}\")\nprint(f\"Distance: {furthest['distance_km']:.2f} km\")\n```\n\n## Common Workflow Pattern\n\nHere's a complete example for analyzing earthquakes near plate boundaries:\n\n```python\nimport geopandas as gpd\nfrom shapely.geometry import Point\n\n# 1. Load data\nearthquakes_data = [...]  # Your earthquake data\ngdf_plates = gpd.read_file(\"plates.json\")\ngdf_boundaries = gpd.read_file(\"boundaries.json\")\n\n# 2. Create earthquake GeoDataFrame\ngeometry = [Point(eq[\"longitude\"], eq[\"latitude\"]) for eq in earthquakes_data]\ngdf_eq = gpd.GeoDataFrame(earthquakes_data, geometry=geometry, crs=\"EPSG:4326\")\n\n# 3. Spatial filtering - find earthquakes in specific plate\ntarget_plate = gdf_plates[gdf_plates[\"Code\"] == \"PA\"].geometry.unary_union\nearthquakes_in_plate = gdf_eq[gdf_eq.within(target_plate)].copy()\n\n# 4. Calculate distances (project to metric CRS)\nMETRIC_CRS = \"EPSG:4087\"\neq_proj = earthquakes_in_plate.to_crs(METRIC_CRS)\n\n# Filter and combine relevant boundaries\nplate_boundaries = gdf_boundaries[\n    gdf_boundaries[\"Name\"].str.contains(\"PA\")\n].to_crs(METRIC_CRS).geometry.unary_union\n\n# Calculate distances\nearthquakes_in_plate[\"distance_km\"] = eq_proj.geometry.distance(plate_boundaries) \u002F 1000.0\n\n# 5. Find the furthest earthquake\nfurthest_eq = earthquakes_in_plate.nlargest(1, \"distance_km\").iloc[0]\n```\n\n## Filtering by Attributes\n\n```python\n# Filter by name or code\npacific_plate = gdf_plates[gdf_plates[\"PlateName\"] == \"Pacific\"]\npacific_plate_alt = gdf_plates[gdf_plates[\"Code\"] == \"PA\"]\n\n# Filter boundaries involving a specific plate\npacific_bounds = gdf_boundaries[\n    (gdf_boundaries[\"PlateA\"] == \"PA\") | \n    (gdf_boundaries[\"PlateB\"] == \"PA\")\n]\n\n# String pattern matching\npa_related = gdf_boundaries[gdf_boundaries[\"Name\"].str.contains(\"PA\")]\n```\n\n## Performance Tips\n\n1. **Filter before projecting**: Reduce data size before expensive operations\n2. **Project once**: Convert to metric CRS once, not in loops\n3. **Use `.unary_union`**: Combine geometries before distance calculations\n4. **Copy when modifying**: Use `.copy()` when creating filtered DataFrames\n\n```python\n# Good: Filter first, then project\nsmall_subset = gdf_large[gdf_large[\"region\"] == \"Pacific\"]\nsmall_projected = small_subset.to_crs(METRIC_CRS)\n\n# Avoid: Projecting large dataset just to filter\n# gdf_projected = gdf_large.to_crs(METRIC_CRS)\n# small_subset = gdf_projected[gdf_projected[\"region\"] == \"Pacific\"]\n```\n\n## Common Pitfalls\n\n| Issue | Problem | Solution |\n|-------|---------|----------|\n| Distance in degrees | Using EPSG:4326 for distance calculations | Project to EPSG:4087 or similar metric CRS |\n| Antimeridian issues | Manual longitude adjustments (±360) | Use geopandas spatial operations, they handle it |\n| Slow performance | Calculating distance to each boundary point separately | Use `.unary_union` + single `.distance()` call |\n| Missing geometries | Some features have no geometry | Filter with `gdf[gdf.geometry.notna()]` |\n\n## When NOT to Use Manual Calculations\n\nAvoid implementing your own:\n- Haversine distance formulas (use geopandas projections instead)\n- Point-in-polygon checks (use `.within()`)\n- Iterating through boundary points (use `.distance()` with `.unary_union`)\n\nThese manual approaches are slower, more error-prone, and less accurate than geopandas methods.\n\n## Best Practices Summary\n\n1. ✅ Load GeoJSON with `gpd.read_file()`\n2. ✅ Use `.within()` for spatial filtering\n3. ✅ Project to metric CRS (`EPSG:4087`) before distance calculations\n4. ✅ Combine geometries with `.unary_union` before distance calculation\n5. ✅ Use `.distance()` method for point-to-geometry distances\n6. ✅ Use `.nlargest()` \u002F `.nsmallest()` for finding extreme values\n7. ❌ Never calculate distances in EPSG:4326\n8. ❌ Avoid manual Haversine implementations\n9. ❌ Don't iterate through individual boundary points\n",{"name":5,"license":15,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fearthquake-plate-calculation-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fgeospatial-analysis",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-analysis",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill geospatial-analysis",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill geospatial-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fearthquake-plate-calculation-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fgeospatial-analysis\u002FSKILL.md",true,[],[46,54,61,68,73,78],{"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":50,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","Apache-2.0","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":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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",[],[]]