agentleFS
rmusser01rmusser01/tldw-stuff/skills/chatbook/chatbook-docx/SKILL.md

chatbook-docx

Skill2 starsChanged 2 months agoApache-2.0View on GitHub

Create, edit and review Word .docx documents from supplied material or Chatbook notes, preserving document structure and checking the delivered file.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Use supplied material first.

    line 13
  2. Distinctive:

    Use the working example for a small heading/table report, and editing and review guidance when modifying an existing document.

    line 31
  3. Very specific:

    Use an authorized local Python execution capability with python-docx.

    line 38
  4. Distinctive:

    When execution is unavailable, return the drafted content and proposed filename.

    line 40
  5. Distinctive:

    Use named paragraph styles for headings, body and lists so the document remains navigable.

    line 47
  6. Very specific:

    When a renderer and image inspection are available, export a PDF into a fresh output directory, inspect every page, and fix clipped tables, …

    line 58

≈ “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

Word documents

Produce an editable .docx that carries the user's content and intended structure. Use supplied material first. If the user selects Chatbook notes or retrieved sources, obtain their full relevant content through available authorized tools; search snippets alone are insufficient for an attributed report. Keep source IDs, links and dates with the claims they support. Missing owners or dates stay unresolved.

Choose the operation

  • New document: establish the audience and purpose from the request. Draft the argument or outline, then implement with python-docx. A short brief usually needs a recommendation, supporting evidence, alternatives and next actions; use the user's structure when supplied.
  • Existing document: inspect headings, tables, sections, headers, footers and the specific text to change before editing. Keep its styles and page setup. Save a separate output unless the user requested replacement.
  • Review: separate proposed edits from source text. Native comments are an option with python-docx 1.2+. Tracked revisions need a tool that actually supports them; a rewritten paragraph is not a tracked change.

Use the working example for a small heading/table report, and editing and review guidance when modifying an existing document. The example contains fictional data: replace it for real work. Resolve bundled paths from this skill's directory, not the workspace directory.

Execute in the available environment

Use an authorized local Python execution capability with python-docx. Do not assume a tool named terminal, a package installer, or filesystem access exists. When execution is unavailable, return the drafted content and proposed filename; do not claim an attachment was created. Local file creation needs no external account. Network access is only needed for requested sources or dependency setup. Importing the skill does not install dependencies or authorize execution.

Compose and check

Use named paragraph styles for headings, body and lists so the document remains navigable. Set sensible margins and a consistent type scale; reuse a supplied brand template. Use tables for comparable records, explicit units for measurements, and captions/source text for evidence. Keep headings with the following paragraph; avoid blank-line padding and unnecessary forced page breaks.

Reopen the output with python-docx and compare the required sections, table records, numbers and changed text with the source. After edits, check retained formatting and content outside the changed passage. This verifies structure and content, not pagination.

When a renderer and image inspection are available, export a PDF into a fresh output directory, inspect every page, and fix clipped tables, orphan headings, font substitutions and excessive whitespace. LibreOffice can render .docx; python-docx cannot. Page-number and contents fields require a document engine to update their results. If rendering is unavailable, report the precise unchecked layout aspects instead of declaring visual approval.

Deliver the actual .docx path, a brief account of the change and any unresolved source or verification limits. Exporting a file does not publish it or update Chatbook notes automatically.

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.