[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BWYNJMXA2PPEZBGYDNADGC":3,"skill-same:01M7BWYNJMXA2PPEZBGYDNADGC":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},"01M7BWYNJMXA2PPEZBGYDNADGC","glm-output",null,"Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.","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\u002Fglm-lake-mendota-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fglm-output\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: glm-output\ndescription: Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.\nlicense: MIT\n---\n\n# GLM Output Guide\n\n## Overview\n\nGLM produces NetCDF output containing simulated water temperature profiles. Processing this output requires understanding the coordinate system and matching with observations.\n\n## Output File\n\nAfter running GLM, results are in `output\u002Foutput.nc`:\n\n| Variable | Description | Shape |\n|----------|-------------|-------|\n| `time` | Hours since simulation start | (n_times,) |\n| `z` | Height from lake bottom (not depth!) | (n_times, n_layers, 1, 1) |\n| `temp` | Water temperature (°C) | (n_times, n_layers, 1, 1) |\n\n## Reading Output with Python\n```python\nfrom netCDF4 import Dataset\nimport numpy as np\nimport pandas as pd\nfrom datetime import datetime\n\nnc = Dataset('output\u002Foutput.nc', 'r')\ntime = nc.variables['time'][:]\nz = nc.variables['z'][:]\ntemp = nc.variables['temp'][:]\nnc.close()\n```\n\n## Coordinate Conversion\n\n**Important**: GLM `z` is height from lake bottom, not depth from surface.\n```python\n# Convert to depth from surface\n# Set LAKE_DEPTH based on lake_depth in &init_profiles section of glm3.nml\nLAKE_DEPTH = \u003Clake_depth_from_nml>\ndepth_from_surface = LAKE_DEPTH - z\n```\n\n## Complete Output Processing\n```python\nfrom netCDF4 import Dataset\nimport numpy as np\nimport pandas as pd\nfrom datetime import datetime\n\ndef read_glm_output(nc_path, lake_depth):\n    nc = Dataset(nc_path, 'r')\n    time = nc.variables['time'][:]\n    z = nc.variables['z'][:]\n    temp = nc.variables['temp'][:]\n    start_date = datetime(2009, 1, 1, 12, 0, 0)\n\n    records = []\n    for t_idx in range(len(time)):\n        hours = float(time[t_idx])\n        date = pd.Timestamp(start_date) + pd.Timedelta(hours=hours)\n        heights = z[t_idx, :, 0, 0]\n        temps = temp[t_idx, :, 0, 0]\n\n        for d_idx in range(len(heights)):\n            h_val = heights[d_idx]\n            t_val = temps[d_idx]\n            if not np.ma.is_masked(h_val) and not np.ma.is_masked(t_val):\n                depth = lake_depth - float(h_val)\n                if 0 \u003C= depth \u003C= lake_depth:\n                    records.append({\n                        'datetime': date,\n                        'depth': round(depth),\n                        'temp_sim': float(t_val)\n                    })\n    nc.close()\n\n    df = pd.DataFrame(records)\n    df = df.groupby(['datetime', 'depth']).agg({'temp_sim': 'mean'}).reset_index()\n    return df\n```\n\n## Reading Observations\n```python\ndef read_observations(obs_path):\n    df = pd.read_csv(obs_path)\n    df['datetime'] = pd.to_datetime(df['datetime'])\n    df['depth'] = df['depth'].round().astype(int)\n    df = df.rename(columns={'temp': 'temp_obs'})\n    return df[['datetime', 'depth', 'temp_obs']]\n```\n\n## Calculating RMSE\n```python\ndef calculate_rmse(sim_df, obs_df):\n    merged = pd.merge(obs_df, sim_df, on=['datetime', 'depth'], how='inner')\n    if len(merged) == 0:\n        return 999.0\n    rmse = np.sqrt(np.mean((merged['temp_sim'] - merged['temp_obs'])**2))\n    return rmse\n\n# Usage: get lake_depth from glm3.nml &init_profiles section\nsim_df = read_glm_output('output\u002Foutput.nc', lake_depth=25)\nobs_df = read_observations('field_temp_oxy.csv')\nrmse = calculate_rmse(sim_df, obs_df)\nprint(f\"RMSE: {rmse:.2f}C\")\n```\n\n## Common Issues\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| RMSE very high | Wrong depth conversion | Use `lake_depth - z`, not `z` directly |\n| No matched observations | Datetime mismatch | Check datetime format consistency |\n| Empty merged dataframe | Depth rounding issues | Round depths to integers |\n\n## Best Practices\n\n- Check `lake_depth` in `&init_profiles` section of `glm3.nml`\n- Always convert z to depth from surface before comparing with observations\n- Round depths to integers for matching\n- Group by datetime and depth to handle duplicate records\n- Check number of matched observations after merge\n","# GLM Output Guide\n\n## Overview\n\nGLM produces NetCDF output containing simulated water temperature profiles. Processing this output requires understanding the coordinate system and matching with observations.\n\n## Output File\n\nAfter running GLM, results are in `output\u002Foutput.nc`:\n\n| Variable | Description | Shape |\n|----------|-------------|-------|\n| `time` | Hours since simulation start | (n_times,) |\n| `z` | Height from lake bottom (not depth!) | (n_times, n_layers, 1, 1) |\n| `temp` | Water temperature (°C) | (n_times, n_layers, 1, 1) |\n\n## Reading Output with Python\n```python\nfrom netCDF4 import Dataset\nimport numpy as np\nimport pandas as pd\nfrom datetime import datetime\n\nnc = Dataset('output\u002Foutput.nc', 'r')\ntime = nc.variables['time'][:]\nz = nc.variables['z'][:]\ntemp = nc.variables['temp'][:]\nnc.close()\n```\n\n## Coordinate Conversion\n\n**Important**: GLM `z` is height from lake bottom, not depth from surface.\n```python\n# Convert to depth from surface\n# Set LAKE_DEPTH based on lake_depth in &init_profiles section of glm3.nml\nLAKE_DEPTH = \u003Clake_depth_from_nml>\ndepth_from_surface = LAKE_DEPTH - z\n```\n\n## Complete Output Processing\n```python\nfrom netCDF4 import Dataset\nimport numpy as np\nimport pandas as pd\nfrom datetime import datetime\n\ndef read_glm_output(nc_path, lake_depth):\n    nc = Dataset(nc_path, 'r')\n    time = nc.variables['time'][:]\n    z = nc.variables['z'][:]\n    temp = nc.variables['temp'][:]\n    start_date = datetime(2009, 1, 1, 12, 0, 0)\n\n    records = []\n    for t_idx in range(len(time)):\n        hours = float(time[t_idx])\n        date = pd.Timestamp(start_date) + pd.Timedelta(hours=hours)\n        heights = z[t_idx, :, 0, 0]\n        temps = temp[t_idx, :, 0, 0]\n\n        for d_idx in range(len(heights)):\n            h_val = heights[d_idx]\n            t_val = temps[d_idx]\n            if not np.ma.is_masked(h_val) and not np.ma.is_masked(t_val):\n                depth = lake_depth - float(h_val)\n                if 0 \u003C= depth \u003C= lake_depth:\n                    records.append({\n                        'datetime': date,\n                        'depth': round(depth),\n                        'temp_sim': float(t_val)\n                    })\n    nc.close()\n\n    df = pd.DataFrame(records)\n    df = df.groupby(['datetime', 'depth']).agg({'temp_sim': 'mean'}).reset_index()\n    return df\n```\n\n## Reading Observations\n```python\ndef read_observations(obs_path):\n    df = pd.read_csv(obs_path)\n    df['datetime'] = pd.to_datetime(df['datetime'])\n    df['depth'] = df['depth'].round().astype(int)\n    df = df.rename(columns={'temp': 'temp_obs'})\n    return df[['datetime', 'depth', 'temp_obs']]\n```\n\n## Calculating RMSE\n```python\ndef calculate_rmse(sim_df, obs_df):\n    merged = pd.merge(obs_df, sim_df, on=['datetime', 'depth'], how='inner')\n    if len(merged) == 0:\n        return 999.0\n    rmse = np.sqrt(np.mean((merged['temp_sim'] - merged['temp_obs'])**2))\n    return rmse\n\n# Usage: get lake_depth from glm3.nml &init_profiles section\nsim_df = read_glm_output('output\u002Foutput.nc', lake_depth=25)\nobs_df = read_observations('field_temp_oxy.csv')\nrmse = calculate_rmse(sim_df, obs_df)\nprint(f\"RMSE: {rmse:.2f}C\")\n```\n\n## Common Issues\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| RMSE very high | Wrong depth conversion | Use `lake_depth - z`, not `z` directly |\n| No matched observations | Datetime mismatch | Check datetime format consistency |\n| Empty merged dataframe | Depth rounding issues | Round depths to integers |\n\n## Best Practices\n\n- Check `lake_depth` in `&init_profiles` section of `glm3.nml`\n- Always convert z to depth from surface before comparing with observations\n- Round depths to integers for matching\n- Group by datetime and depth to handle duplicate records\n- Check number of matched observations after merge\n",{"name":5,"license":15,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FOpus47-OriginalSkill-79Tasks-20260920\u002Fruns\u002Fopus47-original-skill\u002Fglm-lake-mendota-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fglm-output",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 glm-output",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill glm-output",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill glm-output","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\u002Fglm-lake-mendota-opus47-original-skill-r001\u002Finputs\u002Fskills\u002Fglm-output\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",[],[]]