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

1.28x

Quality

—

Does it follow best practices?

Impact

100%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with clear, validated workflows for each task type. It loses points on conciseness due to repeated instructions and tangential padding, and on progressive disclosure because the referenced reference/script files are absent from the bundle.

Suggestions

Deduplicate the 'MANDATORY - READ ENTIRE FILE' instruction and the batch-organization guidance, stating each once in a shared location.

Remove or trim the Chinese agent/MCP-enhancements section and the generic 'Code Style Guidelines', which restate knowledge Claude already has.

Ensure the referenced bundle files (docx-js.md, ooxml.md, AGENTS.md, ooxml/scripts/unpack.py, ooxml/scripts/pack.py) are actually present in the skill so the progressive-disclosure links resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and code, but carries unnecessary tokens: the 'MANDATORY - READ ENTIRE FILE' paragraph is repeated three times, batch-organization guidance is duplicated (steps 2 and 4), and the Chinese agent/MCP section plus generic 'Code Style Guidelines' add padding Claude already knows.	2 / 3
Actionability	Provides fully executable commands (pandoc, unpack.py/pack.py, soffice, pdftoppm) and a complete copy-paste-ready OOXML tracked-changes code example with GOOD/BAD contrast.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced, and the redlining workflow includes explicit validation checkpoints — 'Test each batch before moving', grep-before-script, and a final verification step (step 6) with grep checks confirming changes applied and no unintended edits.	3 / 3
Progressive Disclosure	The written structure is well-signaled and one-level-deep (SKILL.md overview pointing to docx-js.md, ooxml.md, AGENTS.md, and ooxml/scripts), but the referenced bundle files do not exist in the workspace, so the navigation is broken and references do not resolve to real files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is strong: it states concrete capabilities, provides natural trigger terms, and includes an explicit 'when to use' clause tied to .docx files. Voice is appropriately third person ('When Claude needs...').

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction' — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (creation/editing/analysis/tracked changes/comments/formatting/extraction) and 'when' via the explicit trigger 'When Claude needs to work with professional documents (.docx files) for: ...'.	3 / 3
Trigger Term Quality	Includes natural terms a user would say — '.docx files', 'tracked changes', 'comments', 'creating new documents', 'modifying content' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped to '.docx files' with task-specific triggers, giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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: 4 missing	Warning

	Total	15 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: 8271354

Reviewed: about 16 hours 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.