Hire an AI spreadsheet and CSV cleaner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A cleaned file, with your original left alone
• Counts of blanks, duplicates and odd values before and after each round
• Every removed row, saved with its reason
• A list of what only a person can decide
• A rules file for the next export

How it does the job well

• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Guessing values to make the counts look good.
• Merging near duplicates that may be different real records, such as two people with the same name.
• Cleaning a file in a way the system receiving it will reject. Ask what it is for.
• Running more rounds when the counts have stopped falling.
• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.

What a good result looks like

An example, not your task: A report or import keeps failing because of blanks, duplicates or text where numbers should be.

• Result. One line saying passed or not passed, and how many rounds it took.
• Counts. Blanks, duplicates, wrong types and odd values, before and after each round.
• What was changed. Each rule applied and how many cells or rows it touched.
• removed.csv. Every removed row, saved with the reason it was removed.
• Left for a person. Each remaining cell or group, with what you need to decide.
• rules.md. The pass rules and column meanings, so the next export is cleaned the same way.

How the work is checked

• The original file is untouched.
• Every change maps to a rule, and no blank was filled with a guess.
• Every removed row is in clean/removed.csv with its reason.
• The counts after the last round are shown next to the counts before the first.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Read or write the rules. Uses last time's rules, or writes down what a passing file looks like and asks for your yes.
• Audit. Counts blanks, duplicates, wrong types and odd values, and checks formulas if the file has any.
• Choose the fix. Spacing, text numbers, mixed dates and exact duplicates get the simple cleaner. Blanks and odd values get the rule-based cleaner, only where a rule exists.
• Check again. Audits the new file. If the counts fell, it goes on. If they did not, it undoes the fix and says why.
• Stop at three rounds. Hands back what is left for a person to decide, because more rounds rarely help.
• Score and save the rules. Makes a scorecard and updates your rules file for the next export.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id data-file-clean-up-loop only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/data-file-clean-up-loop/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The data file, as a spreadsheet or CSV
• What each column means, and which ones must never be blank (optional but best)
• What the file is for, such as a report or an import into another system (optional)
• Your rules file from last time, after the first run

Helpful context (optional)

• A list of the allowed values for each coded column
• The last clean version of the file, for comparing

Tools and access

• Claude Code: It can open large files, keep the rules and removed-rows files, and run on each new export.
• Excel: Save the cleaned file back as a workbook if your team works in it.
• Claude Code: It can open and save .xlsx files and write formulas into the sheet.
• Any good chat AI: It can plan the fixes and write the formulas, but you paste them into Excel yourself.

Functions and deliverables

• Spreadsheet and CSV cleaner: Clean a spreadsheet or CSV using agreed rules. Recheck each round and keep unresolved cells for a person to decide.
  • A cleaned file, with your original left alone
  • Counts of blanks, duplicates and odd values before and after each round
  • Every removed row, saved with its reason
  • A list of what only a person can decide
  • A rules file for the next export
• Data quality auditor: Share data and quality rules. Get missing values, duplicates and unusual records, with ranked fixes and a score where supported.
  • Data quality score
  • Missing value and outlier findings
  • Ranked repair plan
  • Monitoring checklist
  Source: Alireza Rezvani.
• Indian spreadsheet data cleaner: Share an Excel file or range. Review fixes for spaces, dates, text numbers and duplicates, with original data protected.
  • A cleaned copy of your sheet, with fixes in helper columns
  • Dates and numbers in one format
  • Duplicates marked, and removed only after you say yes
  • A table of every fix: column, issue, count and fix used
  • A list of columns that mix types, for you to review
  Source: nighomni123.
• Dataset cleaner and validator: Give it a dataset and expected schema. Get a quality profile, proposed corrections, validation results and a change log.
  • Cleaned dataset file
  • Log of every transformation
  • Data quality report
  • List of remaining issues
  Source: Burhan Sebin.
• Spreadsheet formula auditor: Give it a spreadsheet. Get formula errors, broken links and model checks such as balance sheet tie-out listed.
  • A list of formula errors by cell
  • Broken link and reference flags
  • Balance sheet and cash tie-out results
  • Unit and fiscal period warnings
  Source: nighomni123.
• Data quality scorecard maker: Check a dataset for blanks, duplicates, broken links and stale data against your rules. Get a data quality scorecard and a shareable report.
  • HTML quality report
  • One page scorecard
  • Pass and fail counts per check
  • Severity ratings
  Source: Nimrod Fisher.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• A report or import keeps failing because of blanks, duplicates or text where numbers should be.
• You get the same kind of messy export every week or month.
• You want a clean file and a record of what was changed.

Limits to check before starting

• Your file already passes your rules and you want a one-off look: open it yourself or ask a person to scan it.
• You need to merge real records, such as two people who might be the same: use a person or a dedicated deduplication tool.
• You want blanks filled with guesses or averages: ask a person to choose the values, because this agent never guesses.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents.
• Attach the file, or put it in a folder the agent can open.
• Say what each column means, or let it propose rules and say yes to them.
• Read the hand-back. Fix the cells it left for you, or tell it the rule to use.
• Next time, give it the new export. It reads your rules file and cleans the same way.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/data-file-clean-up-loop for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.