agentleFS
jordan-partstradejordan-partstrade/trade-agent-skills/skills/xlsx-edit/SKILL.md

xlsx-edit

Skill0 starsChanged 47 days agoMITView on GitHub

Make small, hash-bound changes to existing literal XLSX cells while preserving unrelated archive members, pictures and formula expressions. Use for local quantity or text corrections without rebuilding an existing workbook.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Run python scripts/edit_xlsx.py inspect SOURCE.xlsx --cell "Sheet Name" E6.

    line 9
  2. Very specific:

    Run python scripts/edit_xlsx.py apply SOURCE.xlsx PATCH.json --output NEW.xlsx.

    line 11

≈ “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

Bounded spreadsheet edits

  1. Inspect the source and choose existing, nonformula cells. Structural changes (rows, merges, sheet names, drawings) require a different spreadsheet editor and its own preservation check.
  2. Run python scripts/edit_xlsx.py inspect SOURCE.xlsx --cell "Sheet Name" E6. Repeat --cell SHEET CELL for more cells. This returns the source SHA-256 and current expected values.
  3. Make a JSON patch with exactly source_sha256 and a nonempty changes list. Each change is {sheet,cell,expected,value}. Keep the reported expected unchanged; add the intended value (string, number, boolean or null). A whole-cell text replacement intentionally replaces any existing rich-text runs in that cell.
  4. Run python scripts/edit_xlsx.py apply SOURCE.xlsx PATCH.json --output NEW.xlsx. Output must be a new, different filename. Source hash, expected values, duplicate cells and unsupported cells are checked before publication.
  5. Inspect the edited values and images. All formula expressions are retained, but every worksheet formula cache is cleared and workbook recalculation is requested, because changing an input can invalidate distant totals. Open with a spreadsheet application, recalculate and save before using formula results or running quote-audit. Never treat an empty cache as a zero total.

Only XLSX cell values are supported, without external dependencies. Signed/encrypted/duplicate-entry files and packages over 512 MiB unpacked are rejected. Unrelated ZIP-member contents are verified byte-for-byte; ZIP compression bytes may differ. A preserved image can still contain private information. The output filesystem must support hard links. There is no claim that arbitrary structural changes, macros or protected workbooks are supported.

Repository demo: generate examples/multi-quote.json, then use examples/make_demo_edit.py to create the quantity-change patch.

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.