data-cleaning

スター7

フォーク3

更新日2026年3月23日 09:56

Clean and transform raw data for analysis. Triggers on 'clean data', 'fix data quality', 'normalize data', 'preprocess data'. NOT for data collection — use data-collection.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

ソース

brainbrewlabs

brainbrewlabs/brainbrew-devkit

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

When to Use

Raw data has quality issues (nulls, duplicates, inconsistent formats)
Data types need conversion or normalization before analysis
Merging datasets that need schema alignment
Preparing data for a downstream analysis or visualization pipeline

When NOT to Use

Data has not been collected yet — use data-collection first
You need to analyze clean data — use data-analysis
You need narrative text editing — use a writing/editing skill

Instructions

Load the dataset from the path or source specified in $ARGUMENTS.
Profile the data to identify quality issues:
- Count nulls and missing values per column
- Detect duplicate rows
- Check for format inconsistencies (dates, currencies, encodings)
- Identify outliers and invalid ranges
Apply cleaning operations in order:
- Remove or flag exact duplicate rows
- Handle missing values (drop, impute with mean/median/mode, or forward-fill as appropriate)
- Fix data types (strings to numbers, date parsing, boolean normalization)
- Normalize text fields (trim whitespace, lowercase, remove special characters)
- Standardize formats (ISO dates, consistent currency, uniform units)
Validate the cleaned output:
- Confirm no remaining nulls in required fields
- Verify record count delta is expected (document removals)
- Spot-check transformed values against originals
Write the cleaned dataset to the output location.
Produce a cleaning report documenting every change.

Output

## Data Cleaning Report

### Input
- File: [path]
- Records: [count]
- Columns: [count]

### Issues Found & Actions Taken
| Issue | Count | Action |
|-------|-------|--------|
| ... | ... | ... |

### Output
- File: [path]
- Records: [count after cleaning]
- Quality score: [percentage of clean rows]

このリポジトリの他の Skills

同じリポジトリ

brainbrew-codex-setup

brainbrewlabs/brainbrew-devkit

Use when setting up, verifying, or repairing BrainBrew DevKit in Codex, including hooks, global skills, MCP config, runner files, and plugin-native assets.

2026-05-177

brainbrew-mcp-guidance

brainbrewlabs/brainbrew-devkit

Use when configuring or troubleshooting BrainBrew MCP access in Codex, including .mcp.json, codex mcp commands, and available BrainBrew MCP tools.

2026-05-177

brainbrew-workflow-recipes

brainbrewlabs/brainbrew-devkit

Use when the user wants to run or follow a BrainBrew workflow in Codex, including develop, review, docs, devops, research, support, data, moderation, marketing, or skill-dev recipes.

2026-05-177

chain-builder

brainbrewlabs/brainbrew-devkit

Set up workflow templates and manage chain flows. Trigger when user says: "set up a workflow", "create a development workflow", "I need a CI/CD pipeline", "set up devops", "bump develop", "bump devops", "add agent to chain", "show chain flow", "edit chain config", "create custom workflow", "add a team node", "run agents in parallel", "create agent team", "validate chain", "check chain config", "verify chain".

2026-05-157

docs

brainbrewlabs/brainbrew-devkit

Build and manage VitePress documentation site. Trigger when user says: "build docs", "deploy docs", "preview docs", "update docs", "docs dev server", "run docs locally", "check docs build".

2026-03-297

skill-finder

brainbrewlabs/brainbrew-devkit

Search and install skills from multiple sources (Vercel Skills, GitHub, Anthropic official). Use when user says "find skill", "search skill", "install skill", or when agent-improver needs to find skills for an agent.

2026-03-297

name	data-cleaning
description	Clean and transform raw data for analysis. Triggers on 'clean data', 'fix data quality', 'normalize data', 'preprocess data'. NOT for data collection — use data-collection.
allowed-tools	Bash, Read, Write, Edit

When to Use

Raw data has quality issues (nulls, duplicates, inconsistent formats)
Data types need conversion or normalization before analysis
Merging datasets that need schema alignment
Preparing data for a downstream analysis or visualization pipeline

When NOT to Use

Data has not been collected yet — use data-collection first
You need to analyze clean data — use data-analysis
You need narrative text editing — use a writing/editing skill

Instructions

Load the dataset from the path or source specified in $ARGUMENTS.
Profile the data to identify quality issues:
- Count nulls and missing values per column
- Detect duplicate rows
- Check for format inconsistencies (dates, currencies, encodings)
- Identify outliers and invalid ranges
Apply cleaning operations in order:
- Remove or flag exact duplicate rows
- Handle missing values (drop, impute with mean/median/mode, or forward-fill as appropriate)
- Fix data types (strings to numbers, date parsing, boolean normalization)
- Normalize text fields (trim whitespace, lowercase, remove special characters)
- Standardize formats (ISO dates, consistent currency, uniform units)
Validate the cleaned output:
- Confirm no remaining nulls in required fields
- Verify record count delta is expected (document removals)
- Spot-check transformed values against originals
Write the cleaned dataset to the output location.
Produce a cleaning report documenting every change.

Output

## Data Cleaning Report

### Input
- File: [path]
- Records: [count]
- Columns: [count]

### Issues Found & Actions Taken
| Issue | Count | Action |
|-------|-------|--------|
| ... | ... | ... |

### Output
- File: [path]
- Records: [count after cleaning]
- Quality score: [percentage of clean rows]