Forensic Sweep
Flag data that looks suspiciously clean, imputed, smoothed, or pre-normalized.
About
Forensic Sweep is a data skill from the Claude Data Analyst plugin that checks whether your dataset looks suspiciously clean — imputed values, smoothed series, or pre-normalized columns — so you know what was done upstream before the data reached you.
It is an unusual and valuable first-pass check. The limitation: it flags suspicion, not proof; it cannot distinguish careful data engineering from manipulation, so findings need a human judgment call.
What it can do
- Clean-data detection
- Imputation flagging
- Smoothing detection
- Pre-normalization checks
Setup
- Run: claude plugins install claude-data-analyst@danielrosehill
- Point it at a CSV, Parquet, or Excel file and ask for a forensic sweep.
Prerequisites
Claude Code. duckdb, csvkit, or uv on PATH are recommended by the plugin.
Use cases
Works with
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: 12 stars, 5 commits, MIT; 14-skill data analyst plugin; flags suspicion not proof — needs human judgment. License: MIT.
★ 12 GitHub stars
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 4.0/10
- Maintenance · recency, releases, issue load
- 5.0/10
- Openness · license + docs
- 8.0/10
- Manual review · sanity read + red-flag check
- 6.0/10
- · 12 stars, 5 commits, MIT
- · 14-skill data analyst plugin
- · flags suspicion not proof — needs human judgment
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.