CleanSheetv1.0.0

Profiles every column and reads it as dates, phones, emails, numbers, yes/no, categories, names, links or IDs, with day-first or month-first dates decided per column.

See what you can make

Made with this SkillA clean CSV, a log of every change and a list of what needs a person

194 rows in, 186 clean rows out

Open full example

What you get

A clean CSV, a log of every change and a list of what needs a person

What you can make

  • Profiles every column and reads it as dates, phones, emails, numbers, yes/no, categories, names, links or IDs, with day-first or month-first dates decided per column.
  • Writes ISO dates, E.164 phone numbers and plain numbers, merges spellings that differ only in case, accents or punctuation plus your own mappings, and removes duplicates by the columns you choose.
  • Logs every change by line, column and rule, lists values it could not clean, keeps removed rows, never touches the source file, and includes a studio to try settings.
Explore delivered files6 groups
  • cleaned.csv ready to import
  • changes.csv: every value changed, by line, column and rule
  • issues.csv: values it could not clean
  • removed.csv: duplicates as they were
  • index.html profile report with examples per column
  • Offline studio to set types and spellings

Good fit

Small businesses, marketers, researchers and operations teams importing CSV exports into another system.

Know the limits

Cleans one CSV at a time (export .xlsx sheets as CSV); checks that emails and phones are well formed, not that they exist; does not guess at typos.

About this skill

Your agent profiles the file first: what each column holds, how full it is, example values, and whether slash dates are day-first or month-first, and asks you about anything ambiguous before changing a thing. CleanSheet then writes dates as ISO 8601 from six common formats, phone numbers as E.164 with your country code, amounts with currency signs, thousands separators or decimal commas as plain numbers, emails trimmed and lower-cased, and yes/no in any spelling as true or false. Values in a category that differ only in case, accents, spaces or punctuation merge into their most common spelling, plus any mappings you approve, and empty markers like n/a are cleared. Duplicate rows are found by the columns you choose and the most complete is kept. You get the cleaned CSV, a change log with the line, column, before, after and rule for every value, the values it could not clean, the removed rows as they were, a profile report and a studio to try settings. Reads UTF-8 and Windows-1252; the source file is never modified. Requires Node.js 20+.

FROM PACKAGE TO FIRST RESULT

Your first result, with your agent

Choose a starting point, add the content you already have, then let your agent check the setup and create one result.

View example result

Purchase access is required. Unzip the package into the project folder below, or let your agent follow the installation guide. .agents/skills/cleansheet

Your project name, audience and the content or images you already have are enough to start. Your agent will ask for anything essential that is missing.

3. Let your agent guide the first result

Package location: .agents/skills/cleansheet

Use CleanSheet to clean my customer export before I import it into my email tool. Start from examples/cleansheet.json.

Use a new output folder and preserve existing files. Inspect the actual deliverables (cleaned.csv ready to import, changes.csv: every value changed, by line, column and rule, issues.csv: values it could not clean), open the visual result and explain failed checks. An incomplete dependency check is not a successful result. Ask before paid services and do not publish automatically.
Before calling it done
  • Dependencies checked before rendering
  • Actual files open and work with your content
  • Editable source saved in a new folder
Made your first result? Share your experience →
Installation options & technical requirements

Start with your agent

Give this request to Claude Code, Codex or Cursor. Your agent can collect the missing details and guide your first result.

Use CleanSheet to clean my customer export before I import it into my email tool. Start from examples/cleansheet.json.

Purchase access is required to install the package. Technical commands are available below when you need them.

US$4.99 · MIT licenseNode.js 20+ · no dependencies · no API keyNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/cleansheet

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/cleansheet
    No installation needed
    node scripts/render.mjs --input examples/cleansheet.json --output ./cleaned
    Your first result

    Review the merged spellings and the values to check, then import cleaned.csv; changes.csv shows exactly what was changed.

    The bike shop and its customers are fictional. CleanSheet checks that emails and phone numbers are well formed, not that they exist, and merges spellings only where the rules or your map say so.

    If cleaned already exists, change the output to ./cleaned-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use CleanSheet to clean my spreadsheet. Profile the columns, ask me about anything ambiguous, standardise dates, phone numbers, emails, amounts and yes/no values, merge spellings I approve, remove duplicate rows, and give me the clean CSV with a log of every change.

Reviews

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get CleanSheet?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: cleaned.csv ready to import; changes.csv: every value changed, by line, column and rule; issues.csv: values it could not clean; removed.csv: duplicates as they were; index.html profile report with examples per column; Offline studio to set types and spellings. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

The bike shop and its customers are fictional. CleanSheet checks that emails and phone numbers are well formed, not that they exist, and merges spellings only where the rules or your map say so.

$4.99One-time purchase