agentleFS
pabloirracionalpabloirracional/claude-skills/skills/organizing-spreadsheets/SKILL.md

organizing-spreadsheets

Skill0 starsChanged 4 months agoMITView on GitHub

Cleans, restructures, and analyzes messy spreadsheet data - deduplicating rows, fixing broken headers, standardizing date/number formats, building formulas, and creating pivot-style summary tables. Make sure to use this skill whenever the user uploads a spreadsheet, mentions Excel, Google Sheets, .xlsx/.csv files, messy data, formulas, VLOOKUP/XLOOKUP, or wants a data cleanup, summary table, or quick dashboard from tabular data - even if they don't explicitly use the word "spreadsheet".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the file. Identify: header row location (it's often not row 1), column data types, row count, and whether multiple tables are stacked …

    line 25
  2. Distinctive:

    Never delete data silently - if removing duplicates or outliers, keep a count of what was removed and mention it.

    line 43
  3. Very specific:

    Prefer XLOOKUP/FILTER over legacy VLOOKUP/array formulas when the target tool supports them (Excel 365, Google Sheets).

    line 47
  4. Distinctive:

    If the file has multiple sheets, ask which one is the source of truth before restructuring.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Organizing spreadsheets

Turns messy tabular data into a clean, analyzable spreadsheet with working formulas and a summary view.

Workflow

Copy this checklist and track progress:

Progress:
- [ ] Step 1: Inspect the data
- [ ] Step 2: Flag issues
- [ ] Step 3: Clean and standardize
- [ ] Step 4: Build formulas
- [ ] Step 5: Add a summary view

Step 1: Inspect the data

Read the file. Identify: header row location (it's often not row 1), column data types, row count, and whether multiple tables are stacked in one sheet.

Step 2: Flag issues

Common issues to check for, in this order:

  • Duplicate rows (exact or near-duplicate by key column)
  • Inconsistent date formats within the same column (e.g. 03/04/25 mixed with 2025-04-03)
  • Numbers stored as text (breaks SUM/AVERAGE)
  • Merged cells or blank rows breaking table continuity
  • Inconsistent category labels (e.g. "SP", "São Paulo", "sao paulo" as the same value)

Report what you found before fixing anything - the user may want to keep some "issues" (e.g. intentional blank separators).

Step 3: Clean and standardize

Fix issues from Step 2. Rules:

  • One format per column, always. Pick ISO dates (YYYY-MM-DD) unless the user's locale convention is stated otherwise.
  • Normalize categorical text to a single canonical form (title case, trimmed).
  • Never delete data silently - if removing duplicates or outliers, keep a count of what was removed and mention it.

Step 4: Build formulas

Prefer XLOOKUP/FILTER over legacy VLOOKUP/array formulas when the target tool supports them (Excel 365, Google Sheets). Fall back to VLOOKUP + IFERROR for older Excel compatibility - ask if unsure which the user needs.

For running totals, ranking, or category breakdowns, prefer a SUMIFS/COUNTIFS/AVERAGEIFS pattern over manual filtering formulas - it's more robust to new rows being added.

Step 5: Add a summary view

Build a separate summary sheet/section, never overwrite raw data. Default structure unless the user specifies otherwise:

## Summary
- Total records / date range covered
- Breakdown by [most relevant categorical column]
- Top/bottom N by [most relevant numeric column]
- Flags: any remaining data quality issues the user should manually review

Notes

  • If the file has multiple sheets, ask which one is the source of truth before restructuring.
  • For very large files (100k+ rows), process in chunks and confirm scope before running formulas that recalculate the whole sheet.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.