agentleFS
jordan-partstradejordan-partstrade/trade-agent-skills/skills/quote-audit/SKILL.md

quote-audit

Skill0 starsChanged 47 days agoMITView on GitHub

Check an XLSX quotation read-only for mapped line arithmetic and totals, hidden content, unfinished labels and possible internal-cost fields. Use before sharing a quote or comparing an unchanged table layout with an earlier version.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Run python scripts/audit_quote.py FILE.xlsx LAYOUT.json [--previous OLD.xlsx].

    line 10

≈ “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

Quote audit

  1. Inspect the actual workbook and define an explicit layout. No guessing column meanings. tables is a nonempty list of {sheet,start_row,end_row,id,quality?,quantity,unit_price,amount}; column values are uppercase letters. Include every intended item row and an option label column when IDs repeat for different qualities.
  2. Optional totals: {sheet,cell,sources} where sources is a list of [sheet,range] pairs of numeric cells. Include goods, freight and grand-total relationships separately. Do not include subtotals twice.
  3. Run python scripts/audit_quote.py FILE.xlsx LAYOUT.json [--previous OLD.xlsx]. Requires openpyxl. Previous comparison requires the same row/sheet layout and uses item ID plus quality, not only row position.
  4. Exit 0 means these configured arithmetic checks passed; exit 1 means findings; exit 2 means invalid input. Inspect errors, warnings, price_changes, and the reported coverage. Unit prices must have no more than two decimals. Price changes are reported for review, never automatically accepted or forbidden.

Formula results need a current cache saved by a spreadsheet application. Missing caches fail; the script does not evaluate formulas or save/rewrite the workbook. Hidden sheets/rows/columns, Excel error cells, TBD/TODO labels and common internal-price words are flagged across loaded sheets. External/structured formulas produce warnings. This is not a complete personal-information detector: inspect comments, embedded images, document properties and all customer-facing content manually. A pass does not verify fitment, agreed prices or shipping terms.

Repository example: examples/quote-layout.json matches the unchanged output of examples/multi-quote.json.

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.