word-document
Word Document Workflows
Tech Stack Target / Version: Word desktop or
python-docxautomation with current OOXML-compatible workflows.
Use this skill when .docx layout and document structure matter, not just the raw text.
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Current MCP Reality
Microsoft publicly documents a Word MCP server in the Microsoft 365 Agents Toolkit preview, but tool availability still depends on the host. In GitHub Copilot you may see Word-specific tools; in other clients they may be missing. If direct Word MCP access is unavailable, use the included local script workflow.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
- Creating or editing
.docxreports, memos, or structured deliverables - Applying headings, tables, images, or styles
- Reviewing or extracting document structure
- Preparing Word output before a later PDF conversion
Practical Workflow
- Confirm whether the client exposes Word MCP capabilities.
- Start with structure: title, headings, sections, tables.
- Apply styling consistently only after the structure is right.
- Validate comments, footnotes, and references before export.
- Use the local generator script when MCP access is unavailable.
MCP Fallback – Native Automation
When MCP is unavailable, use native automation: python-docx for .docx, direct OOXML inspection for unsupported structures, and PDF export checks when layout matters. Preserve styles, tables, headers, footers, comments, tracked-change expectations, and metadata, then reopen or parse the document before claiming success.
Anti-Patterns
- Writing for the author instead of the reader: It bakes in unstated context and leaves the actual audience unsure what to do next.
- Skipping concrete examples or commands: Abstract guidance is easy to approve and hard to apply correctly.
- Letting links, screenshots, or versions drift: Polished formatting does not help if the instructions are no longer true.
Verification Protocol
Before claiming "skill applied successfully":
- Pass/fail: The Word Document artifact type, target format, and required output fidelity are stated before editing.
- Pass/fail: MCP availability is checked and the native automation fallback path is named when MCP is absent.
- Pass/fail: The produced file or formula is opened, parsed, rendered, or otherwise validated locally.
- Pressure-test scenario: Apply the workflow to a file with formatting, metadata, or conversion edge cases and verify nothing important is lost.
- Success metric: Zero unverified document claims; the artifact itself is the evidence.
Document Checklist
- Heading hierarchy is clear
- Tables are readable and consistently styled
- Comments or review notes are intentional
- Placeholder text is removed
- The final document was re-opened or otherwise verified after generation
References & Resources
Documentation
- DOCX Formatting Reference - Practical formatting notes and document structure guidance
Scripts
- DOC Template Generator - Local fallback for generating Word-ready document structures
Examples
- Report Generation Example - Example report workflow for
.docxoutput
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, Codex, and Gemini CLI.
- GitHub Copilot: keep the folder in a Copilot-visible skill or plugin path, or wrap the workflow as project instructions if the host does not support portable skill folders directly.
- Claude Code: keep the folder in a local skills directory or a compatible plugin or marketplace source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/<skill-name>and restart Codex after major changes. - Gemini CLI: this repository generates a project command named
/skills:word-documentfrom this skill. Rebuild commands withpython scripts/export-gemini-skill.py word-documentand then run/commands reloadinside Gemini CLI.
MCP Availability And Fallback
Preferred MCP Server: Word Document MCP
- Fallback prompt: "Use the Word Document Workflows skill without MCP. Rely on the local
SKILL.md, bundled references or scripts, and manual verification. Show the exact commands, evidence, and final checks you used before concluding." - Use
python-docx, Word desktop, or document export scripts when the MCP surface is unavailable. - Re-open or render the document locally so formatting, comments, and pagination are verified before delivery.
Related Skills
- documentation-authoring: Use it when the workflow also needs drafting structured technical or product documents.
- documentation-patterns: Use it when the workflow also needs reusable documentation structures and templates.
- documentation-quality: Use it when the workflow also needs documentation review standards and quality gates.
- documentation-verification: Use it when the workflow also needs final documentation validation before publishing.
More from practicalswan/agent-skills
powerpoint-ppt
PowerPoint (.pptx) manipulation via MCP server. Use for creating slides, formatting presentations, managing placeholders, adding images, applying templates, or extracting text from .pptx files.
139serena-usage
Serena MCP for project memory and code navigation. Use when managing Serena memories, navigating symbols, performing intelligent refactoring, or maintaining context/continuity across AI agent sessions.
19powerbi-modeling
Power BI semantic models - DAX measures, star schemas, relationships, RLS, and performance tuning via MCP. Use when creating data models, writing DAX, or configuring table relationships in Power BI.
16stitch-design
Google Stitch design toolkit — DESIGN.md generation, screen-to-React conversion, shadcn/ui integration, prompt enhancement, and Remotion walkthroughs. Use when working with Stitch MCP design projects.
15php-development
PHP 8.0+ development — XAMPP, RESTful APIs, PDO/MySQL/MariaDB, and authentication. Use when building PHP backends, creating API endpoints, configuring XAMPP, or integrating PHP with databases.
14notion-docs
Notion workspace management via MCP - create databases, pages, comments, and knowledge bases. Use when building Notion documentation, organizing project wikis, or managing Notion content.
14