docx

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.

1.52x

Quality

92%

Does it follow best practices?

Impact

93%

1.52x

Average score across 8 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-5

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

The body is highly actionable and workflow-safe: executable code everywhere, explicit validation with repair loops for XML manipulation, and correct script references. Its main weaknesses are duplicated warning text that inflates token cost and a monolithic structure that inlines a large API/XML reference that would be better split into separate reference files.

Suggestions

Move the docx-js feature catalog (~250 lines: styles, lists, tables, images, hyperlinks, footnotes, tab stops, columns, TOC, headers/footers) and the XML Reference (~130 lines: tracked changes, comments, image XML) into references/ files (e.g. references/docx-js.md and references/xml-patterns.md), keeping SKILL.md as an overview with clearly signaled one-level-deep links.

Consolidate the repeated table-width rules into a single 'Tables' section entry and have the Critical Rules list reference it once, removing the 'Always use DXA / never PERCENTAGE' and dual-width duplications stated 3-4 times each.

Tighten the multi-part landscape/table-width explanations by keeping one canonical code example per rule and dropping the redundant restatements in comments and bullet lists.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable code with minimal prose, but several warnings are repeated — the 'Always use DXA / never WidthType.PERCENTAGE' rule appears four times (tables section, width rules list, and Critical Rules) and the dual-width table rule is stated three times. Not 5: duplicated CRITICAL rules could be consolidated into one place; not 3: there is no padding or explanation of concepts Claude already knows.	4 / 5
Actionability	Guidance is copy-paste ready throughout: complete executable docx-js snippets for every feature, exact bash commands ('python scripts/office/unpack.py document.docx unpacked/'), a DXA unit conversion table, and exact XML patterns for tracked changes, comments, and images. Common cases are covered with specific, runnable examples.	5 / 5
Workflow Clarity	The editing workflow is explicitly sequenced ('Follow all 3 steps in order': unpack → edit XML → pack with validation and auto-repair), and the creation workflow includes a feedback loop: 'After creating the file, validate it. If validation fails, unpack, fix the XML, and repack.' Validation checkpoints for XML manipulation are explicit, satisfying the feedback-loop requirement.	5 / 5
Progressive Disclosure	The bundle provides working scripts (all referenced paths verified to exist) and the SKILL.md has good section structure with a Quick Reference navigation table, but roughly 450 of ~590 lines are an inline docx-js API catalog and XML reference that belong in one-level-deep reference files, and no references/ directory exists. Not 4: the content that should be split out is the majority of the file, which is more than 'minor organization gaps'; not 2: structure and navigation within the file are clear and existing references are correct and clearly signaled.	3 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 exemplary description: it enumerates concrete capabilities, provides extensive natural trigger terms including file extensions and deliverable synonyms, and clearly bounds when to use and not use the skill. Third-person voice is maintained and every clause adds triggering or scoping information rather than padding.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'create, read, edit, or manipulate Word documents', 'extracting or reorganizing content', 'inserting or replacing images', 'performing find-and-replace', 'working with tracked changes or comments' — with comprehensive coverage of the domain.	5 / 5
Completeness	It explicitly answers both what ('create, read, edit, or manipulate Word documents') and when ('Use this skill whenever...', 'Triggers include:', 'Also use when...') with concrete trigger phrases, plus a negative boundary ('Do NOT use for PDFs, spreadsheets, Google Docs').	5 / 5
Trigger Term Quality	It covers natural terms users would say — 'Word doc', 'word document', '.docx', 'report', 'memo', 'letter', 'template', 'tracked changes', 'comments' — including synonyms and the file extension, matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	It occupies a clear .docx niche with distinct triggers and explicitly excludes adjacent formats (PDFs, spreadsheets, Google Docs), minimizing conflict risk with sibling document skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 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
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/docx-2/SKILL.md
Commit: a16301c

Reviewed: 1 day 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.