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

70%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/docx/SKILL.md

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.

The description is well-structured with clear capabilities and explicit trigger conditions using a numbered list format. Its main weaknesses are the absence of the most common user trigger terms ('Word', 'Microsoft Word', '.doc') and the overly broad catch-all phrase 'any other document tasks' which could cause conflicts with other document-handling skills. Additionally, 'GLM' is used instead of 'Claude', which may be a naming inconsistency.

Suggestions

Add common user trigger terms like 'Word', 'Microsoft Word', 'Word document', and '.doc' since these are the most natural terms users would use when requesting this skill.

Replace the vague catch-all 'any other document tasks' with more specific scenarios or remove it to reduce conflict risk with other document-related 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' with explicit triggers ('When GLM needs to work with professional documents (.docx files) for:' followed by numbered scenarios).	3 / 3
Trigger Term Quality	Includes some good keywords like '.docx files', 'tracked changes', 'comments', 'documents', but misses common user variations like 'Word', 'Word document', 'Microsoft Word', '.doc', which are the most natural terms users would say.	2 / 3
Distinctiveness Conflict Risk	Reasonably specific to .docx files, but the broad phrase 'any other document tasks' and generic terms like 'document creation' and 'editing content' could overlap with other document-related skills (e.g., PDF, plain text, or general file editing skills). Missing 'Word' as a trigger term also reduces distinctiveness.	2 / 3
	Total	10 / 12 Passed

Implementation

62%

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

The skill provides highly actionable, well-structured workflows with clear decision trees and validation steps, making it strong on actionability and workflow clarity. However, it is significantly bloated with verbose design specifications (color palettes with marketing copy), redundant explanations of basic concepts, and inline content that should be in separate reference files. The token efficiency is poor - the color palettes, Chinese quote escaping examples, and dual comment methods with extensive 'when to use' comparisons consume substantial tokens that could be dramatically reduced.

Suggestions

Move the color palette definitions to a separate reference file (e.g., COLOR_PALETTES.md) and reference it with a single line, reducing the main skill by ~40 lines of design specifications.

Remove explanatory text Claude already knows, such as 'A .docx file is essentially a ZIP archive containing XML files', 'Comments (批注) allow you to add annotations to documents without modifying the actual content', and marketing descriptions of color palettes like 'premium cashmere' and 'electric undertone'.

Consolidate the 'when to use OOXML vs python-docx' comparison into a 2-line decision rule instead of two separate bullet-point lists that repeat similar information.

Move the detailed Chinese quote escaping examples and font configuration to a separate troubleshooting or reference file, keeping only a one-line reminder in the main skill.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines. It includes extensive color palette definitions with marketing descriptions ('premium cashmere', 'electric undertone'), explains concepts Claude already knows (what a .docx file is, what comments/批注 are), provides redundant 'when to use' comparison sections, and includes design philosophy that inflates token count significantly without proportional value.	1 / 3
Actionability	The skill provides fully executable code examples throughout - bash commands for pandoc/soffice, Python scripts for comments and OOXML manipulation, JavaScript examples for docx-js, and specific command-line invocations for scripts. The code is copy-paste ready with concrete parameters and real library APIs.	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 includes explicit guidance on batch sizes and debugging approach.	3 / 3
Progressive Disclosure	The skill references external files (docx-js.md, ooxml.md) appropriately with one-level-deep links, which is good. However, the main SKILL.md itself is monolithic with extensive inline content (color palettes, multiple code examples for comments, detailed formatting rules) that could be split into separate reference files. The color palette section alone is a large block that should be in a separate file.	2 / 3
	Total	9 / 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
Commit: 07048a9

Reviewed: 2 days 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.