Data Analyzer

Data analysis and visualization skill. Supports CSV, Excel, JSON data with statistical analysis, charts, and reports.

Security Scan

The skill's documentation describes running a local Python script (scripts/analyze.py) and requires data-processing libraries, but the skill bundle contains no code or install instructions—this mismatch is unclear and warrants caution.

Purpose & Capability

Name/description claim data analysis and visualization (CSV/Excel/JSON/Parquet, charts, stats). Achieving that legitimately requires a Python script or binary plus libraries (pandas, matplotlib/seaborn, pyarrow/openpyxl, etc.), but the package contains no code, binaries, or install spec. The declared requirements (none) do not match the capabilities described.

Instruction Scope

SKILL.md instructs the agent or user to run 'python3 scripts/analyze.py' with various flags and to read/write local files (input data and output charts/reports). That is scoped to data analysis, but the referenced script path (scripts/analyze.py) is not present in the skill and no fallback instructions are provided. The instructions do not request credentials or external endpoints, which is good, but they presume local tooling that isn't included.

Install Mechanism

No install spec (instruction-only), which is lower technical risk from installation. However, because the instructions expect a local script and likely Python libraries, the lack of an install mechanism or list of dependencies is a usability and coherence problem: users or agents would need to supply the missing code/tooling themselves.

Credentials

The skill requests no environment variables, no credentials, and no config paths. This is proportionate to a local data-analysis helper that operates on user-provided files.

Persistence & Privilege

always is false and the skill does not request persistent privileges or modify other skills or system-wide settings. It does instruct writing output files to user-specified paths (expected for this purpose).

What to consider before installing

This skill's README-like instructions assume a local script (scripts/analyze.py) and Python libraries, but the skill package contains no code or install steps. Before installing or enabling it: 1) Ask the publisher for the source code or a homepage and verify the analyze.py script and dependency list (pandas, matplotlib/seaborn, pyarrow/openpyxl, etc.). 2) If you intend to run the referenced script, inspect it for unexpected network calls, credential access, or data exfiltration. 3) If you want a drop-in skill, prefer one that includes code or a clear install spec from a trusted release (GitHub release, PyPI package, etc.). 4) If you try this locally, run it in an isolated environment (container or VM) with non-sensitive sample data first. 5) If the maintainer can't provide code or justification for missing artifacts, treat the skill as incomplete and avoid granting it access to sensitive data.

Analyze datasets and generate visualizations with statistical insights.

When to Use

• User wants to analyze a dataset
• Generate charts and visualizations
• Statistical analysis and summaries
• Data cleaning and transformation

Features

• Data formats: CSV, Excel, JSON, Parquet
• Statistics: Mean, median, std dev, correlations
• Visualizations: Bar, line, pie, scatter, heatmap
• Reports: Auto-generated analysis reports

Usage

Quick analysis

python3 scripts/analyze.py \
  --input ./data.csv \
  --output ./report/

Generate specific chart

python3 scripts/analyze.py \
  --input ./data.csv \
  --chart bar \
  --x "category" \
  --y "sales" \
  --output ./chart.png

Statistical summary

python3 scripts/analyze.py \
  --input ./data.csv \
  --stats \
  --columns "age,income,score"

Correlation analysis

python3 scripts/analyze.py \
  --input ./data.csv \
  --correlation \
  --output ./correlation_matrix.png

Data transformation

python3 scripts/analyze.py \
  --input ./data.csv \
  --transform "normalize" \
  --columns "price,quantity" \
  --output ./normalized.csv

Output

{
  "success": true,
  "rows": 1000,
  "columns": 10,
  "stats": {
    "mean": {"age": 35.2, "income": 55000},
    "std": {"age": 12.3, "income": 15000}
  },
  "charts": ["./chart1.png", "./chart2.png"],
  "report": "./report.html"
}