agentleFS
TrustPagerTrustPager/Business_Operating_System/skills/compare-documents/SKILL.md

Compare Documents

Skill8 starsChanged 5 months agoMITView on GitHub

Compare two documents and show what actually changed. Converts both files (PDF, Word, etc.) to Markdown with the standard MarkItDown tool, then reports the meaningful differences in plain language — added, removed, changed — calling out moved figures and clauses. For contract versions, revised quotes, updated terms/policies. Built on knowledge/document-tools-method.md.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If either converts empty, say so and stop — you can't compare what you can't read.

    line 32

≈ “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

Compare Documents

"What changed between these two versions" is a constant question for anything contractual. This converts both and reports the differences that matter, not a character-level diff.

Step 1 — Convert both files

python ~/.claude/bos-run.py tool markitdown_convert "<file-A>"
python ~/.claude/bos-run.py tool markitdown_convert "<file-B>"

(The ~/.claude/bos-run.py launcher resolves the install location for you. If it is missing, run python tools/setup.py once from the BOS directory to create it.)

If either converts empty, say so and stop — you can't compare what you can't read.

Step 2 — Compare meaningfully

Work from both Markdown versions. Report differences grouped as:

  • Added — content in B that isn't in A.
  • Removed — content in A that's gone in B.
  • Changed — content present in both but different, especially numbers, dates, names, and clauses (e.g. "Fee: $2,000 → $2,500", "Term: 24 → 36 months", "added a termination-for-convenience clause").

Lead with the changes that carry weight (money, obligations, dates, parties), not formatting noise. Ignore pure layout/whitespace differences unless asked.

Step 3 — Report in plain language

Comparing "Quote-v1.pdf" → "Quote-v2.pdf":

Changed
  • Total: $12,400 → $13,900
  • Delivery: 4 weeks → 6 weeks
Added
  • New clause: 20% deposit on acceptance
Removed
  • The "price held for 30 days" line is gone

End with one line on the net effect if it's clear ("v2 is $1,500 dearer, slower, and adds a deposit"). Don't editorialise beyond what the documents show.

Hard rules

  • ❌ Don't compare unreadable conversions — flag and stop.
  • ❌ Don't drown the real changes in formatting/whitespace noise.
  • ❌ Don't misreport a figure — quote both sides (old → new) so it's checkable.
  • ✅ Always convert through tools/markitdown_convert.py.
  • ✅ Lead with money / dates / obligations / parties; those are what matter.

Output shape

Grouped Added / Removed / Changed differences in plain language, figures shown old → new, and a one-line net effect if clear.

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.