docx

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

2.16x

Quality

82%

Does it follow best practices?

Impact

93%

2.16x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

65%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.

A well-organized, actionable skill body with a clear decision tree and executable commands, weakened mainly by incomplete batch-validation feedback loops and references (docx-js.md, ooxml.md) that do not resolve within the provided bundle.

Suggestions

Add an explicit validate→fix→retry loop for the batch redlining workflow (e.g., re-run grep verification per batch and iterate until clean) to lift the destructive/batch workflow_clarity cap.

Either include docx-js.md and ooxml.md in the bundle or repoint the 'Document library' references to the actual bundled scripts/document.py so navigation resolves.

De-duplicate the batch-organization guidance (currently repeated in step 2 and step 4) and trim the 'Code Style Guidelines' section to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with a tight decision tree and copy-ready commands, but batch-organization guidance is duplicated between step 2 and step 4, and the 'Code Style Guidelines' section adds mild padding.	4 / 5
Actionability	Provides concrete, executable commands (pandoc, unpack.py/pack.py, soffice, pdftoppm) and a concrete BAD/GOOD redlining code example, with only the deeper Document-library API deferred to referenced files.	4 / 5
Workflow Clarity	Clear numbered sequences and a final grep-based verification step exist, but the batch redlining workflow's per-batch validation is only a vague 'Test each batch' with no explicit validate→fix→retry feedback loop, so the destructive/batch cap applies.	3 / 5
Progressive Disclosure	SKILL.md is well structured as an overview with clearly signaled one-level-deep references to docx-js.md and ooxml.md, but those referenced files are absent from the bundle and the bundled scripts/document.py library is not pointed to by a discoverable path.	3 / 5
	Total	14 / 20 Passed

Description

100%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, well-scoped description that states concrete capabilities and explicit trigger guidance with the .docx extension, closely matching the reference good examples for presentation/document skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creation, editing, and analysis', 'tracked changes, comments, formatting preservation, and text extraction' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (creation/editing/analysis with tracked changes, comments, formatting, extraction) and 'when' ('When Claude needs to work with professional documents (.docx files) for:' with an enumerated trigger list).	5 / 5
Trigger Term Quality	Covers natural user terms including 'professional documents (.docx files)', 'creating new documents', 'modifying', 'tracked changes', and 'comments', with the .docx extension present.	5 / 5
Distinctiveness Conflict Risk	Scoped to .docx professional documents with distinct triggers (tracked changes, comments, redlining), giving it a clear niche with minimal overlap risk against other document skills.	5 / 5
	Total	20 / 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: modelscope/ms-agent
Path: examples/skills/claude_skills/docx/SKILL.md
Commit: ea7da5c

Reviewed: 2 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.