agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/amplifier-bundle-work/skills/documents/SKILL.md

documents

Skill0 starsChanged 27 days agoMITView on GitHub

Create, edit, review, comment on, or redline Word DOCX documents. Use for reports, memos, letters, and Google Docs-bound files; render and inspect before delivery.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 0

    Distinctive

    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:

    Read ${SKILL_DIR}/../_shared/artifacts.md for environment, rendering, and delivery.

    line 10
  2. Very specific:

    Create or edit DOCX with python-docx.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 11 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

Documents

Read ${SKILL_DIR}/../_shared/artifacts.md for environment, rendering, and delivery. This is an original portable implementation, not the restricted OpenAI package.

  1. Establish the intended reader, decision or purpose, requested format, and source facts. For an existing file, inspect paragraphs, styles, tables, sections, comments, and relationships before choosing the edit strategy.
  2. Create or edit DOCX with python-docx. Use semantic Title and heading styles, explicit page margins and paragraph spacing, consistent typography, and table widths that fit the page. Use actual page breaks only where structurally needed. Keep headings with following text and repeat table headers.
  3. Preserve the reference's structure when a template is supplied. Replace placeholders in a copy; do not flatten formatted runs or remove hyperlinks, bookmarks, fields, numbering, headers, or footers as a side effect.
  4. For comments, use the installed library's documented comment API, anchor to the intended runs, and use the user-provided author or a neutral label. For tracked changes, do not substitute plain text replacement: use a capable Office adapter or inspect and edit OOXML w:ins/w:del, revision IDs, dates, and author metadata on a copy. Verify accepting/rejecting changes in the intended engine; report this feature as unverified if it cannot be tested.
  5. Reopen the saved DOCX and check text, tables, headers, links, and requested changes. Render with the shared helper, inspect all pages, and iterate.
  6. Return the DOCX. Import to a native Google Doc only through a real connector when requested, and report the resulting URL after verifying the operation.

Completion requires a saved, readable file with verified content and a visually reviewed layout. Separate native tracked-change or cloud acceptance from local file checks; never claim them based on XML inspection alone.

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.

Check your setup, free