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
85
81%
Does it follow best practices?
Impact
91%
1.62xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
77%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly enumerates capabilities and provides explicit trigger conditions via a numbered list. Its main weaknesses are the lack of 'Word' or 'Microsoft Word' as trigger terms (which users would naturally say) and the overly broad catch-all 'any other document tasks' which could cause conflicts with other document-related skills.
Suggestions
Add 'Word', 'Microsoft Word', '.doc', and 'Word document' as trigger terms since users commonly refer to these files by application name rather than just 'documents' or '.docx'.
Narrow the catch-all phrase 'any other document tasks' to something more specific like 'any other .docx document tasks' to reduce conflict risk with PDF, text, or other document-type skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: document creation, editing, analysis, tracked changes, comments, formatting preservation, and text extraction. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (document creation, editing, analysis, tracked changes, comments, formatting preservation, text extraction) and 'when' (explicit numbered trigger scenarios: creating new documents, modifying content, working with tracked changes, adding comments, plus a catch-all for other document tasks). | 3 / 3 |
Trigger Term Quality | Includes '.docx files', 'documents', 'tracked changes', 'comments', but misses common user variations like 'Word document', 'Word file', '.doc', 'Microsoft Word', or 'DOCX'. Users frequently refer to these by the application name rather than the generic term 'documents'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'documents' is quite broad and could overlap with PDF skills, plain text editing, or other document-related skills. While '.docx files' adds specificity, the phrase 'any other document tasks' at the end significantly broadens the scope and increases conflict risk. Adding 'Word' or 'Microsoft Word' would help distinguish it more clearly. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that effectively covers multiple DOCX workflows with clear decision routing, concrete commands, and proper validation steps. Its main weakness is some verbosity—explaining what .docx files are, repeating batch grouping guidance, and the triple repetition of the 'MANDATORY - READ ENTIRE FILE' instruction. Overall, it's a strong skill that provides actionable, well-organized guidance for document manipulation tasks.
Suggestions
Remove the explanation of what a .docx file is in the Overview section—Claude already knows this.
Consolidate the batch grouping guidance that appears in both steps 2 and 4 of the redlining workflow to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some unnecessary verbosity. The 'Overview' section explains what a .docx file is (Claude knows this). The repeated 'MANDATORY - READ ENTIRE FILE' instructions across multiple sections are redundant. The batching strategy in the redlining workflow is somewhat repetitive, with batch grouping suggestions appearing twice (steps 2 and 4). However, most content is actionable and relevant. | 2 / 3 |
Actionability | The skill provides concrete, executable commands throughout: specific pandoc commands with flags, Python script invocations with arguments, bash commands for conversion, and a detailed XML example showing good vs bad tracked change patterns. The decision tree clearly directs which workflow to use. Code examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps. The redlining workflow includes explicit validation checkpoints (step 6 with grep verification), feedback loops (batch-then-verify approach), and clear error recovery guidance. The editing workflow has unpack→edit→pack sequence. The decision tree at the top provides clear routing logic for different scenarios. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear overview with well-signaled one-level-deep references to docx-js.md and ooxml.md for detailed API documentation. Content is appropriately split: the SKILL.md covers workflow decisions and high-level steps, while detailed library usage is deferred to referenced files. Navigation is straightforward with the decision tree at the top. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
d065ead
- Reviewed
Table of Contents
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.