Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
92
88%
Does it follow best practices?
Impact
93%
1.52xAverage score across 8 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that covers specific capabilities, includes abundant natural trigger terms, explicitly states both when to use and when not to use the skill, and clearly distinguishes itself from related skills. The only minor note is the use of second person ('Use this skill whenever the user wants...') which borders on instructional voice, but it primarily uses third-person-compatible imperative phrasing rather than 'I can' or 'You can use this' patterns, so the penalty is negligible.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, read, edit, manipulate Word documents, extract/reorganize content, insert/replace images, find-and-replace, work with tracked changes/comments, convert content into polished Word documents, and formatting elements like tables of contents, headings, page numbers, letterheads. | 3 / 3 |
Completeness | Clearly answers both 'what' (create, read, edit, manipulate .docx files with specific sub-tasks listed) and 'when' (explicit trigger terms and use-case scenarios provided, plus negative boundaries stating when NOT to use). The description opens with an explicit 'Use this skill whenever...' clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Word doc', 'word document', '.docx', 'report', 'memo', 'letter', 'template', plus formatting-related terms like 'tables of contents', 'headings', 'page numbers', 'letterheads'. These are highly natural user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around Word/.docx files. Explicitly excludes PDFs, spreadsheets, Google Docs, and general coding tasks, which directly reduces conflict risk with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-organized skill for DOCX manipulation, with excellent executable code examples covering both creation (docx-js) and editing (XML manipulation) workflows. The workflow clarity is strong with explicit validation steps and clear sequencing. The main weakness is that the document is quite long and could benefit from splitting detailed reference material (XML patterns, docx-js API examples) into separate files, and the critical rules section partially duplicates inline guidance.
Suggestions
Split the XML Reference section and detailed docx-js patterns into separate referenced files (e.g., XML_REFERENCE.md, DOCX_JS_PATTERNS.md) to reduce the main skill's token footprint
Remove or consolidate the 'Critical Rules for docx-js' summary section since most rules are already demonstrated in context within their respective code examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with useful code examples and tables, but it's quite long (~400+ lines) with some sections that could be more terse. The critical rules summary at the end of the 'Creating New Documents' section repeats information already shown in context above. However, it avoids explaining basic concepts Claude would know and most content earns its place as reference material. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides executable code examples, specific commands, and copy-paste ready snippets. The JavaScript examples for docx-js are complete with proper imports, the bash commands are specific, and the XML reference includes concrete patterns for tracked changes, comments, and images. | 3 / 3 |
Workflow Clarity | The editing workflow is clearly sequenced as 'Step 1: Unpack → Step 2: Edit XML → Step 3: Pack' with explicit validation built into the pack step. The creating workflow includes a validation step after creation. Auto-repair capabilities and their limitations are clearly documented, providing good error recovery guidance. | 3 / 3 |
Progressive Disclosure | The content is well-structured with a quick reference table at the top and clear section headers, but it's essentially a monolithic document. The extensive XML reference, all the docx-js patterns, and the editing guide could benefit from being split into separate referenced files. For a skill this long, inline content should be trimmed with pointers to detailed reference files. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (591 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
5128e18
Table of Contents
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.