data-analysis

The data-analysis skill generates statistical analysis code and performs a 4-round review process. It supports statistical testing, result interpretation, and report generation including p-values, effect sizes, and confidence intervals.

1.2K
Installs
4
Use cases
5/10
Quality

Is data-analysis safe to install?

Review the source first

Review the source first: our audit of data-analysis's source files found 4 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary Python scripts located in the user's local directory and reads/writes data files.

How we audit skills: our security review methodology.

Who is this skill for?

Researchers and data scientists analyzing experimental data for academic or technical papers.

What can you do with it?

  • Generating statistical analysis code for CSV, JSON, or pickle data sources.
  • Performing multi-round code reviews to identify mathematical or statistical errors.
  • Calculating statistical summaries and comparisons using Python scripts.
  • Formatting p-values for LaTeX or plain text reports.

How good is this skill?

Quality score: 5/10. The skill provides clear instructions, specific script examples, and a structured workflow for statistical analysis.

What does the skill file contain?

SKILL.md
# Data Analysis

Generate rigorous statistical analysis code with multi-round review.

## Input

- `$0` — Data source (CSV, JSON, pickle, or experiment logs)
- `$1` — Research goal or hypothesis to test

## References

- 4-round code review prompts: `~/.claude/skills/data-analysis/references/review-prompts.md`

## Scripts

### Statistical summary and comparison
```bash
python ~/.claude/skills/data-analysis/scripts/stat_summary.py --input results.csv --compare method --metric accuracy --output summary.json
python ~/.claude/skills/data-analysis/scripts/stat_summary.py --input results.csv --descr...

Frequently asked questions

What statistical packages does this skill use?

The skill uses pandas, numpy, scipy, statsmodels, sklearn, and pickle.

How does the code review process work?

The process consists of 4 rounds: checking for mathematical errors, verifying data handling, ensuring sensible values and uncertainty measures, and confirming cross-table consistency.

Can this skill analyze any data format?

It supports CSV, JSON, pickle, and experiment logs.

Data sourced from lingzhi227/agent-research-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills