agentleFS
kiku-jwkiku-jw/codex-skills/spreadsheet/SKILL.md

spreadsheet

Skill0 starsChanged 4 months agoMITView on GitHub

Create, edit, analyze, or format spreadsheets (`.xlsx`, `.csv`, `.tsv`) with `openpyxl` and `pandas`, especially when formulas, references, and formatting must survive the change. Use when spreadsheet integrity matters more than ad hoc CSV hacking.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Do not use when: a trivial one-line CSV inspection is enough and workbook integrity does not matter.

    line 10
  2. Very specific:

    If a child lane is unavailable in the current run, continue here with the same split: use openpyxl for .xlsx structure-preserving work and …

    line 18
  3. Distinctive:

    If rendering dependencies are missing, the skill says so instead of pretending the layout was verified.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

Spreadsheet Skill

Metadata

  • Trigger when: the task involves real spreadsheet creation, editing, analysis, formatting, or visual validation.
  • Do not use when: a trivial one-line CSV inspection is enough and workbook integrity does not matter.

Skill Purpose

Stay as the stable entrypoint for spreadsheet work, then route into the narrowest correct lane: workbook-preserving .xlsx editing or tabular data analysis.

Instructions

  1. Classify the spreadsheet job first. If the task is .xlsx creation/editing with formulas or formatting preservation, prefer $spreadsheet-xlsx-edit. If the task is CSV/TSV or spreadsheet-backed analysis, aggregation, or reshaping, prefer $spreadsheet-tabular-analysis. Read the runnable examples under ~/.codex/skills/spreadsheet/references/examples/openpyxl only when you need a concrete pattern.
  2. If a child lane is unavailable in the current run, continue here with the same split: use openpyxl for .xlsx structure-preserving work and pandas for tabular analysis workflows. Keep filenames stable and outputs under a sensible path such as output/spreadsheet/.
  3. Validate the result. Check formulas, references, number/date formats, source citations when relevant, and render for visual review when layout matters and soffice plus pdftoppm are available.

Non-Negotiable Acceptance Criteria

  • Existing workbook formatting is preserved unless the user asked for redesign.
  • Derived values stay as formulas when formulas are the right source of truth.
  • Formatting and citation rules are explicit when the spreadsheet is financial or source-sensitive.
  • If rendering dependencies are missing, the skill says so instead of pretending the layout was verified.

Output

  • The final spreadsheet path or paths.
  • Any render artifact path used for visual validation.
  • A short note on formula handling, dependency installs, or validation caveats.
  • Next skill options (only if needed): $spreadsheet-xlsx-edit — create or edit .xlsx files while preserving formulas and formatting; $spreadsheet-tabular-analysis — analyze and reshape spreadsheet/CSV/TSV data with stable outputs.

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.