merge-agent

Automating tabular merges involves inspecting file headers, detecting delimiters and encodings, and generating a runnable script with sequential joins. This approach validates keys across formats like CSV, Excel, and Parquet to prevent schema misalignment.

Generating a reproducible merge script requires inspecting input headers, inferring dtypes, and writing sequential joins with source-based suffixes. This produces a runnable Python, R, or Julia script that preserves column provenance across merged data.

Yes, you can merge HDF5 and Excel files by inspecting headers, inferring dtypes, and applying source-based suffixes. This preserves column provenance by appending source identifiers to overlapping column names in the final merged output.

The best way to validate merge keys is to inspect headers, infer cardinality, and normalize keys across input files. This process prevents join errors by detecting mismatches early and includes a validation summary printed after execution.

Data merges often fail when input files have mismatched data types. Inferring dtypes and cardinality during preparation resolves this by ensuring schema alignment and validating keys before generating the final merge script.

Yes, the merge-agent Skill supports generating runnable merge scripts in Julia, as well as Python and R. It inspects headers, validates merge keys, and outputs a reproducible sequence of joins tailored to your chosen language.