docx

Word document processing. Format: .docx (ZIP/XML structure). Capabilities: create documents, edit content, tracked changes, comments, formatting preservation, text extraction, styles, headers/footers, tables, images. Actions: create, edit, analyze, extract from Word documents. Keywords: Word, docx, document, tracked changes, comments, formatting, styles, headers, footers, tables, images, paragraphs, text extraction, template, mail merge, revision history, document comparison. Use when: creating Word documents, editing docx files, working with tracked changes, adding comments, extracting document content, preserving document formatting.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/document-skills/docx/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with concrete commands and a useful tracked-changes example, but it is undermined by broken references to missing docx-js.md/ooxml.md files, absent per-batch validation in destructive workflows, and several redundant or concept-explaining passages.

Suggestions

Resolve the broken references: either add docx-js.md and ooxml.md to the bundle or repoint the MANDATORY-read instructions to the actual bundled scripts/document.py and scripts/utilities.py API.

Add an explicit per-batch validation feedback loop (e.g., a validate.py step between editing and packing) to the editing and redlining workflows so destructive/batch XML changes are checked before output.

Trim redundancy — remove the duplicate batch-grouping lists (steps 2 and 4), the 'ZIP archive' concept explanation, and the generic Code Style Guidelines section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with headers and code blocks, but includes unnecessary explanation Claude already knows ('A .docx file is essentially a ZIP archive containing XML files...'), a generic 'Code Style Guidelines' section, and duplicated batch-grouping guidance in steps 2 and 4, fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides many concrete executable commands (pandoc, unpack/pack, soffice, pdftoppm) and a GOOD/BAD code example, but the MANDATORY reads point to docx-js.md and ooxml.md which are absent from the bundle and the actual bundled scripts/document.py library is never linked, leaving key API details missing.	3 / 5
Workflow Clarity	Steps are clearly sequenced with a final verification step in the redlining workflow, but the basic OOXML editing workflow has no validation before packing and the batch redlining workflow lacks a per-batch validate→fix→retry feedback loop; per the rubric cap, batch/destructive XML manipulation without validation cannot exceed 3.	3 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level pointers ('Read [ooxml.md](ooxml.md)'), but against the actual bundle those referenced files do not exist and the real bundled library (scripts/document.py, scripts/utilities.py, scripts/templates/) is never surfaced, so navigation does not actually resolve.	3 / 5
	Total	12 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, explicit description that clearly states capabilities and provides a concrete 'Use when' trigger list with good keyword/extension coverage. Its main weakness is verbosity: the Capabilities, Actions, and Keywords sections largely restate one another.

Suggestions

Collapse the redundant Capabilities/Actions/Keywords sections into a single concise capability list to reduce padding without losing trigger coverage.

Soften the generic 'document' keyword density to further reduce overlap with sibling document-format skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions with comprehensive coverage — 'create documents, edit content, tracked changes, comments, formatting preservation, text extraction, styles, headers/footers, tables, images' — matching the anchor for multiple specific actions.	5 / 5
Completeness	Explicitly answers both what (Capabilities/Actions) and when via a concrete 'Use when: creating Word documents, editing docx files, working with tracked changes, adding comments, extracting document content, preserving document formatting' clause.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and the file extension: 'Word, docx, document' plus '.docx', 'tracked changes', 'mail merge', 'revision history', matching the anchor for full synonym and extension coverage.	5 / 5
Distinctiveness Conflict Risk	Clear Word/.docx niche with distinct triggers ('Word', 'docx', '.docx', 'mail merge'), but the heavily repeated generic term 'document' creates minor overlap risk with a sibling PDF/document skill, fitting the 'mostly distinct; minor overlap' anchor rather than minimal-conflict 5.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: samhvw8/dot-claude
Path: skills/document-skills/docx/SKILL.md
Commit: 28c7616

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.