data-profiler · aspi6246 — Claude Code skill: what it does, how to install
data-profiler enforces a structured R exploratory protocol for empirical datasets. It verifies observation units, missing patterns, and panel structure before any regression runs.
no license ★ 165 updated 2026-08-21
npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a claude-codeWhat data-profiler does
This skill guides Claude Code through a fixed four-step data inspection checklist. The assistant begins by inventorying file properties, variable types, and potential record keys. Next, it tests observation unit hypotheses to uncover key duplicates and clarifies whether panel records are balanced over time.
Detailed profiling covers numerical distributions, quantiles, and category counts, alongside date timeline continuity. The protocol also scans for domain red flags like inverted date intervals, negative values in bounded metrics, or broken financial identifier strings such as CUSIP or GVKEY.
All inspection routines operate strictly read-only using tidyverse, data.table, and arrow. The skill forbids modifying original data files and requires consulting an existing codebook before running code.
What it helps with
- Detect duplicate identifiers and confirm the true unit of observation
- Evaluate panel balance, entry, and exit spans across time periods
- Spot abnormal missing code conventions, outliers, and logical conflicts
Example prompts for the agent
- Profile this dataset before we run any regressions
- Explore this data and check the panel structure
- Examine variable definitions and check for duplicate keys in this table
How to install data-profiler
1Skills CLI (Vercel)
npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a claude-code2Manually: put the files in place
~/.claude/skills/data-profiler/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-profiler/
1Skills CLI (Vercel)
npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a codex2Manually: put the files in place
.agents/skills/data-profiler/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a cursor2Manually: put the files in place
.cursor/skills/data-profiler/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aspi6246/Claude-Code-Skills-for-Academics data-profiler2Manually: put the files in place
.github/skills/data-profiler/SKILL.md1Skills CLI (Vercel)
npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a gemini-cli2Platform CLI
gemini skills install https://github.com/aspi6246/Claude-Code-Skills-for-Academics --path data-profilerManually: put the files in place
.devin/skills/data-profiler/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about data-profiler
How to install data-profiler in Claude Code?
Run npx skills add aspi6246/Claude-Code-Skills-for-Academics --skill data-profiler -a claude-code in your terminal.
What does data-profiler do?
It applies a disciplined exploration workflow that produces a reference profile of dataset dimensions, key integrity, distributions, and anomalies.
Does data-profiler edit raw data files?
No, the protocol enforces read-only access. It parses tables via tools like fread() without writing modifications back to source files.
Similar skills
All skills for Data and databases →data-profiler by other authors comes first.