Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadrivenconstruction/df-merger
Merge pandas DataFrames from multiple construction sources. Handle different schemas, keys, and data quality issues.
Passed 15 of 21 test cases with the skill, and 11 of 21 without it.
and 4 more in the full report
5 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
During column name semantic matching between two datasets, if a candidate column pair is not listed in standard variant dictionaries, what ratio cutoff determines if they are semantically similar?
| Checked | Without skill | With skill |
|---|---|---|
| Applies SequenceMatcher similarity ratio threshold greater than 0.8 | Missed | Passed |
The instructions your model reads when the skill loads.
Construction projects combine data from BIM, schedules, costs, and sensors. This skill merges DataFrames from disparate sources with intelligent key matching and schema reconciliation.
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass
from enum import Enum
from difflib import SequenceMatcher
class MergeStrategy(Enum):
"""DataFrame merge strategies."""
INNER = "inner" # Only matching rows
LEFT = "left" # All left, matching right
RIGHT = "right" # Matching left, all right
OUTER = "outer" # All rows from both
CROSS = "cross" # Cartesian product
@dataclass
class MergeResult:
"""Result of merge operation."""
merged_df: pd.DataFrame
matched_rows: int
left_only: int
right_only: int
merge_quality: float # 0-1 score
class ConstructionDFMerger:
"""Merge DataFrames from construction sources."""
# Common construction column name mappings
COLUMN_MAPPINGS = {
test cases passed, vs 11 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.