docx

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM 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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/docx/SKILL.md

Quality

Content

62%

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

The skill excels at actionability and workflow clarity with concrete commands, executable code, clear decision trees, and validation checkpoints throughout. However, it is severely undermined by poor conciseness—extensive inline design specifications (color palettes with marketing copy, typography rules, Chinese font configuration) that should be in separate reference files. The progressive disclosure is partially effective with external file references but fails by inlining too much detailed content that belongs in supporting documents.

Suggestions

Move the entire color palette section, typography rules, table styling specifications, and Chinese quote escaping rules into a separate STYLING.md or DESIGN_GUIDE.md file, and reference it with a single line from SKILL.md.

Remove marketing language from color palette descriptions (e.g., 'premium cashmere', 'electric undertone', 'visual penetration') — these waste tokens and provide no actionable value to Claude.

Trim the overview paragraph explaining what a .docx file is ('A .docx file is essentially a ZIP archive containing XML files...') — Claude already knows this.

Consolidate the Comments section by removing the 'Common patterns' code block which largely duplicates the initial example with minor variations.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose with significant unnecessary content. The color palette section (~40 lines) with marketing descriptions like 'premium cashmere' and 'electric undertone' is wasteful. Design requirements, Chinese font configuration, and extensive styling rules bloat the file. Many sections explain things Claude already knows (what comments are, what .docx files are). The document is well over 300 lines when much could be trimmed or moved to referenced files.	1 / 3
Actionability	The skill provides concrete, executable commands and code throughout: specific bash commands for pandoc/soffice/pdftoppm, complete Python code blocks for python-docx comments, JavaScript examples for docx-js with correct/incorrect patterns, and specific script invocations with arguments. Code is copy-paste ready with real parameters.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced with numbered steps and explicit validation checkpoints. The redlining workflow includes a final verification step with grep commands to confirm changes. The decision tree at the top clearly routes users to the correct workflow. Batching strategy with size guidance (3-10 changes) and the 'only when valid' pattern in the editing workflow demonstrate strong feedback loops.	3 / 3
Progressive Disclosure	The skill references external files (docx-js.md, ooxml.md, scripts) appropriately with one-level-deep links, which is good. However, the massive inline color palette section, detailed styling rules, Chinese quote escaping examples, and TOC placeholder details should be in separate reference files. The SKILL.md tries to be both an overview and a detailed reference, resulting in a bloated main file that undermines the progressive disclosure pattern.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 strong description that clearly enumerates capabilities and provides explicit trigger conditions with numbered use cases. Its main weakness is the use of 'GLM' instead of 'Claude' and the absence of key trigger terms like 'Word', 'Microsoft Word', or '.doc' that users would naturally use when requesting document work.

Suggestions

Add common user trigger terms like 'Word', 'Microsoft Word', '.doc', and 'word document' to improve keyword coverage for natural user queries.

Replace 'GLM' with 'Claude' or remove the agent reference entirely to match standard skill description conventions.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: document creation, editing, analysis, tracked changes, comments, formatting preservation, and text extraction. These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (document creation, editing, analysis, tracked changes, comments, formatting, text extraction) and 'when' with explicit triggers ('When GLM needs to work with professional documents (.docx files) for...' followed by numbered use cases).	3 / 3
Trigger Term Quality	Includes some good keywords like '.docx files', 'documents', 'tracked changes', 'comments', but misses common user variations like 'Word', 'Microsoft Word', '.doc', 'word processing'. The term 'GLM' instead of 'Claude' is unusual and may not match user queries.	2 / 3
Distinctiveness Conflict Risk	Clearly scoped to .docx files with specific document-related triggers like tracked changes, comments, and formatting preservation. This is distinct enough to avoid conflicts with PDF, spreadsheet, or presentation skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jjyaoao/HelloAgents
Path: skills/docx/SKILL.md
Commit: 5432566

Reviewed: about 14 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.