What do I need to use Data Cleaning Pass?

The data; The destination; The authority questions.

Is Data Cleaning Pass free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Data Cleaning Pass

Q: How do I know the Data Cleaning Pass output is good?

The skill verifies itself against its own quality checks: Profiling produced counts before any edit; The order ran normalize-before-dedupe; The duplicate key and conflict authority are stated; No blank was filled without a confirmed semantic.

🔵 Stable🕐 updated 2026-10-06 🔷 SkillSpec L3 pm-cowork

Clean a messy dataset methodically — the profiling pass that finds what's actually wrong (dupes, format drift, phantom spaces, mixed types), the fix order that doesn't corrupt while correcting, and the log that makes the cleaning defensible. Use when asked clean this export, why is my pivot double-counting, these names don't match between sheets, or prep this data for analysis. Produces the profile of what's wrong, the ordered cleaning plan, the join-key repairs, and the cleaning log.

▶ Run it free — no key needed 📝 Grade your existing draft ⬇ Add to Claude (works in Duet) 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Clean this export.”“Why is my pivot double-counting?”“Prep this data for analysis.”

What to give it

▸The data — the sheet/export, and where it came from (system exports have signature messes: leading zeros eaten, dates re-typed, thousands separators as text)

▸The destination — a pivot, a join, a chart, an import; the destination defines "clean enough" (a join needs perfect keys; a chart needs consistent types)

▸The authority questions — when duplicates conflict (two rows, same customer, different phone), which source wins? Cleaning makes merge decisions; someone must own the rule

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Profiling produced counts before any edit

✓The order ran normalize-before-dedupe

✓The duplicate key and conflict authority are stated

✓No blank was filled without a confirmed semantic

✓The log accounts for every transformation, and the original survives untouched

⚠️ What it refuses to do

Do not clean in place — the original is the rollback and the audit

Do not dedupe first — un-normalized duplicates hide from the dedupe

Do not invent values for should-have-value blanks — flag them; fabrication compounds downstream

Do not global find-replace without column scoping — the classic self-inflicted corruption

Do not deliver cleaned data without the log — numbers whose provenance can't be stated get re-cleaned by the next skeptic

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="data-cleaning-pass"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Data Cleaning Pass is one of 1326 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog