myskill

Remove duplicate rows from CSV files by key columns. Use when asked to deduplicate CSVs or keep unique records.

Security Scan

The skill's files and runtime instructions match its stated purpose (deduplicating CSVs); the bundled Python script is simple, has no network or credential usage, and only reads/writes the specified files.

Purpose & Capability

Name/description, SKILL.md, and the included Python script all describe CSV deduplication and require only the input/output paths and optional key columns — nothing extra is requested.

Instruction Scope

SKILL.md directs the agent to run the included script with explicit input/output paths and optional flags. The script only reads the specified input file, processes it in memory, and writes the specified output file; it does not access other files, environment variables, or network endpoints.

Install Mechanism

No install spec is provided and no external downloads or package installs are required. The skill is instruction-only with one bundled Python script.

Credentials

The skill declares no required environment variables, credentials, or config paths, and the code does not read any environment variables or secrets.

Persistence & Privilege

Skill does not request persistent presence (always:false) and does not modify other skills or system-wide settings.

Assessment

This skill appears to be what it says: a simple CSV deduper implemented in Python with no network access and no credential requirements. Before installing or running: (1) review and back up your CSVs — the script overwrites only the output file you specify and could cause data loss if used incorrectly; (2) note the script loads the entire file into memory (may be memory-heavy for very large CSVs); (3) the script will exit if a specified key column is missing, and it lowercases keys only when --case-insensitive is used; (4) encoding errors are replaced (errors='replace'), which can alter problematic characters; (5) if you need streaming/disk-based deduplication for huge files, consider a tool designed for that. Otherwise the code is straightforward and contains no hidden network calls, obfuscated logic, or unexpected credential access.

Overview

Deduplicate CSV rows using one or more key columns. Keeps the first row by default.

Inputs

• A CSV file.
• Optional key columns (comma separated).

Outputs

• A new CSV file with duplicates removed.

Workflow

1. Choose the key columns (or use the whole row).
2. Run the script to produce a deduped CSV.
3. Validate row counts.

Usage

python scripts/csv_dedupe.py --input data.csv --output data.deduped.csv --keys id,email
python scripts/csv_dedupe.py --input data.csv --output data.deduped.csv

Safety

• No network access.
• Only reads/writes the file paths you pass in.