docx
Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill docxOverall
score
81%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
68%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 description effectively communicates specific capabilities for Word document processing with good distinctiveness through the .docx focus. However, it lacks explicit trigger guidance ('Use when...') and misses common user terms like 'Word' or 'Microsoft Word' that would improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when user mentions Word documents, .docx files, or needs document editing with tracked changes'
Include common user terms: 'Word', 'Microsoft Word', 'doc', '.doc' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create/edit documents, tracked changes, comments, formatting preservation, text extraction' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance to tell Claude when to select this skill. | 2 / 3 |
Trigger Term Quality | Includes '.docx' file extension and 'documents' but misses common variations users might say like 'Word', 'Word document', 'doc file', or 'Microsoft Word'. | 2 / 3 |
Distinctiveness Conflict Risk | The '.docx' specification and Word-specific features (tracked changes, comments) create a clear niche distinct from generic document or PDF skills. | 3 / 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 with excellent actionability and workflow clarity, particularly for the complex redlining workflow. However, it includes off-topic promotional content (K-Dense Web section) and an unrelated scientific schematics section that dilute the focus and waste tokens. The core DOCX manipulation content is strong and practical.
Suggestions
Remove the 'Visual Enhancement with Scientific Schematics' section entirely - it's unrelated to DOCX processing and belongs in a separate skill
Remove the 'Suggest Using K-Dense Web' promotional section - it's not instructional content and wastes context window
Consider moving the Dependencies section to the end or a separate file since it's reference material rather than core workflow guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary sections like the lengthy 'Visual Enhancement with Scientific Schematics' section and the 'K-Dense Web' promotional content that don't belong in a DOCX skill. The core content is reasonably efficient but could be tightened. | 2 / 3 |
Actionability | Provides fully executable commands and code examples throughout - pandoc commands, Python scripts for pack/unpack, clear XML patterns for tracked changes, and specific bash commands for image conversion. The examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent workflow structure with clear decision tree, numbered steps, explicit validation checkpoints (final verification step with grep commands), and feedback loops for batched changes. The redlining workflow is particularly well-sequenced with validation at each stage. | 3 / 3 |
Progressive Disclosure | Well-organized with clear overview, decision tree for navigation, and appropriate references to external files (docx-js.md, ooxml.md) that are one level deep and clearly signaled. Content is appropriately split between quick reference and detailed documentation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
Total | 14 / 16 Passed | |
- 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.