agentleFS
PawelBednarekPunksPawelBednarekPunks/aidevbird-skills/skills/xlsx-toolkit/SKILL.md

xlsx-toolkit

Skill1 starsChanged 7 days agoMITView on GitHub

Create, edit, clean or analyze Excel/CSV files with live formulas and no errors. Use when a spreadsheet (.xlsx, .xlsm, .csv, .tsv) is the input or the deliverable.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start: python scripts/inspect_xlsx.py FILE — sheets, size, first rows, formula and error counts.

    line 11
  2. Very specific:

    Use functions every Excel and LibreOffice has: SUMIFS, COUNTIFS, INDEX/MATCH, IFERROR, ROUND.

    line 15
  3. Distinctive:

    Verify before handing over:

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

XLSX Toolkit

Tools: openpyxl for cells, formulas and formatting; csv/pandas for bulk data. Install only if the import fails. Script paths are relative to this skill's folder.

Start: python scripts/inspect_xlsx.py FILE — sheets, size, first rows, formula and error counts. Plan edits from cell coordinates, not from a text dump.

Rules for every output:

  • Formulas, not computed results: =SUM(B2:B13), not the number Python summed. Inputs live in their own labeled cells; formulas reference them (=B5*(1+$B$2), never =B5*1.05).
  • Use functions every Excel and LibreOffice has: SUMIFS, COUNTIFS, INDEX/MATCH, IFERROR, ROUND. Avoid XLOOKUP, FILTER, UNIQUE, SORT, LET, LAMBDA — sort/filter/dedupe in Python first.
  • Guard every division: =IFERROR(B2/C2,0).
  • Quote sheet names with spaces: ='Raw Data'!A1.
  • Editing an existing file: keep its layout, styles, names and formulas. Write only into its input cells. Never save a workbook loaded with data_only=True (formulas become values). .xlsm: load with keep_vba=True.
  • New file: header row bold and frozen (ws.freeze_panes = "A2"), column widths set, one data table per sheet, no merged cells inside data, number formats set (#,##0.00, 0.0% stored as fractions, dates as real dates).
  • State assumptions and hardcoded numbers next to them (note cell or comment) with their source.

Verify before handing over:

  1. Re-run inspect_xlsx.py on the output. errors must be empty (exit code 1 means errors).
  2. formulas_without_cached_value is normal for files written by openpyxl — Excel computes them on open. If LibreOffice is installed, soffice --headless --convert-to xlsx --outdir checked FILE and inspect the copy to see real values.
  3. Spot-check 2–3 formulas against values you compute by hand — no errors does not mean correct ranges.

Report: file path, sheets, what changed, any assumption the user must confirm.

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.