agentsclimarketplace

Run2 Identify Pacific Plate Identifier

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Identify-Pacific-Plate-Identifier

Examine the plates dataset to find the exact identifier used for the Pacific plate (e.g., "PA", "Pacific", etc.). Use this skill early in the analysis to ensure consistent filtering across boundaries and plates.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_Identify-Pacific-Plate-Identifier

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.3 KB, 246 tokens by cl100k_base, as published. Nobody here has run it

def find_pacific_plate_id(plates_gdf):
    """
    Identify the correct Pacific plate identifier in the dataset.
    
    Args:
        plates_gdf: GeoDataFrame containing plate data
        
    Returns:
        String representing the Pacific plate identifier
    """
    # Find plate identifier column (commonly 'PlateName', 'Name', or similar)
    plate_name_col = None
    for col in plates_gdf.columns:
        if col.lower() in ['platename', 'name', 'plate']:
            plate_name_col = col
            break
    
    if plate_name_col is None:
        raise ValueError("Could not identify plate name column")
    
    unique_plates = plates_gdf[plate_name_col].unique()
    print("Unique plates:", unique_plates)
    
    # Search for Pacific plate variations
    pacific_id = None
    for plate in unique_plates:
        if 'pac' in str(plate).lower():
            pacific_id = plate
            break
    
    if pacific_id is None:
        raise ValueError(f"Pacific plate not found. Available plates: {unique_plates}")
    
    return pacific_id, plate_name_col

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.