CSV Stats Analyzer

Analyzes any CSV file and returns row count, column names, and basic statistics for numeric columns.

Security Scan

The skill's code and runtime instructions match its stated purpose (local CSV analysis); no unexplained credential or network behavior was found, though the SKILL.md mentions a runtime tool ('uv') and pandas dependency that the registry metadata did not declare.

Purpose & Capability

The skill name/description (CSV analysis) aligns with the provided analyzer.py and sample CSV. However, SKILL.md declares a required binary ('uv') and the need to run with pandas, while the registry metadata lists no required binaries or dependencies — a minor inconsistency but explainable (the script needs pandas and SKILL.md expects a 'uv' runner).

Instruction Scope

Instructions are narrowly scoped: run the included analyzer.py against a user-supplied CSV and return counts/numeric stats. The SKILL.md does not instruct reading other files, environment variables, or sending data externally. The analyzer.py only reads the given CSV and prints results.

Install Mechanism

No install specification is provided (instruction-only runtime with an included script). That keeps the disk/write footprint minimal. The only risk is relying on an external runner ('uv') and Python package pandas being present.

Credentials

The skill requests no environment variables, secrets, or config paths. analyzer.py does not access env vars or external credentials. The lack of credential requests is proportional to the stated CSV analysis purpose.

Persistence & Privilege

always is false and user-invocable is true (normal). The skill does not request persistent system privileges or modify other skills or system settings.

Assessment

This skill appears to do exactly what it says: locally read a CSV and print counts and simple numeric stats. Before installing or running it, confirm you have the 'uv' runner (SKILL.md calls for 'uv run --with pandas') or else run the script with a known Python interpreter (e.g., python analyzer.py). Ensure pandas is installed in the environment that will execute the script. Only provide CSVs you trust (the script reads the file path you pass) and verify that you are comfortable with the agent being allowed to run local commands. The registry metadata omits the declared 'uv' runtime and pandas dependency — that's likely an oversight but worth double-checking. If you need higher assurance, open and review analyzer.py (small and readable) or run it in a sandboxed environment first.

Usage

Invoke with: /csv-stats-analyzer <path-to-csv-file>

Example: /csv-stats-analyzer ./sales.csv

Features

• Shows total rows and columns
• Lists all column names
• Calculates min, max, and average for every numeric column

Rules

• The CSV must exist and be readable.
• Use the helper script at {baseDir}/analyzer.py
• Run it with: uv run --with pandas {baseDir}/analyzer.py [csv-path]
• Return the output in a clean, readable format with emojis.
• Never modify the original CSV file.