Cleaning Data

Systematic data quality remediation - detect duplicates/outliers/inconsistencies, design cleaning strategy, execute transformations, verify results (component skill for DataPeeker analysis sessions)

5 stars 2 forksFrontend & Design Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add tilmon-engineering/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add tilmon-engineering/claude-skills --skill cleaning-data
Manual install
git clone --depth 1 https://github.com/tilmon-engineering/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/datapeeker/skills/cleaning-data ~/.claude/skills/cleaning-data

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Cleaning Data - Component Skill

## Purpose

Use this skill when:
- Have completed the `importing-data` skill with quality report generated
- Need to address data quality issues before analysis (duplicates, outliers, NULL handling, free text categorization)
- Want systematic approach to cleaning decisions with documented rationale
- Need to create clean tables ready for process skills (exploratory-analysis, guided-investigation, etc.)
- Following DataPeeker principle: **cleaning is ALWAYS mandatory** even if minimal issues found

This skill is a **prerequisite** for all DataPeeker analysis workflows and consumes the quality report from importing-data.

## Prerequisites

Before using this skill, you MUST:
1. Have completed the `importing-data` skill successfully
2. Have access to `05-quality-report.md` generated by importing-data
3. Have `raw_*` table(s) in `data/analytics.db`
4. Be familiar with basic SQLite for validation queries
5. Understand data quality concepts: duplicates, outliers, NULL handling, categorical standardization

## Data Cleaning Process

Create a TodoWrite checklist for the 5-phase data cleaning process:

```
Phase 1: Quality Report Review - pending
Phase 2: Issue Detection (Agent-Delegated) - pending
Phase 3: Cleaning Strategy Design - pending
Phase 4: Cleaning Execution - pending
Phase 5: Verification & Documentation - pending
```
Read the full skill on GitHub

Details

Skill name
cleaning-data
Path
plugins/datapeeker/skills/cleaning-data/SKILL.md
License
MIT
Repo updated
22 May 2026

FAQ

What does the Cleaning Data skill do?

Systematic data quality remediation - detect duplicates/outliers/inconsistencies, design cleaning strategy, execute transformations, verify results (component skill for DataPeeker analysis sessions)

How do I install the Cleaning Data skill?

Claude Code plugin: /plugin marketplace add tilmon-engineering/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cleaning Data popular?

It lives in tilmon-engineering/claude-skills, which has 5 GitHub stars and 2 forks.

Related skills

Analyze Branch

5

tilmon-engineering/claude-skills

Use when analyzing another branch's iteration journals to extract findings, decisions, and insights from divergent work

Git & Code Review

Branch Status

5

tilmon-engineering/claude-skills

Use when user wants detailed status report for single autonomy branch including iteration timeline and metrics progression

Git & Code Review

Checkpoint Iteration

5

tilmon-engineering/claude-skills

Use when saving current iteration progress mid-conversation, before context compaction, or at interim pause points

Other

Interpreting Results

5

tilmon-engineering/claude-skills

Component skill for systematic result interpretation with intellectual honesty in DataPeeker analysis sessions

Frontend & Design

Yuwakisa Game Factor

5

roby2358/skills

Factor a single-file browser game (a yuwakisaweb-style canvas prototype — one big index.js of module-level state, an immediate-mode render(), and inline event listeners) into a server-portable five-module split: GameArtifacts, GameDisplayArtifacts, GameState, GameEngine, GameUI. Use when asked to "factor/refactor this game", split a monolithic game into GameEngine/GameState/GameUI, make a prototype "portable to a server" or to yuwakisacloud, separate rules from rendering, or add seeded/reproducible RNG to a canvas game. Also use when deciding where a new game feature (terrain, skills, affixes,

Frontend & Design

Kymera Brand

5

astoreyai/claude-skills

Kymera Systems brand design - Jarvis-inspired HUD aesthetic with dark and light modes. Use for branded UI, dashboards, presentations, and technical artifacts.

Frontend & Design

Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.