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.

Quality

96%

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

Quality

Content

92%

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

A dense, highly actionable skill body with clear sequenced workflows and validation feedback loops for document manipulation. Its main weakness is progressive disclosure: the XML and docx-js reference material is monolithically inline rather than factored into separate reference files.

Suggestions

Move the 'XML 参考' section (revisions, comments, image markup) into a separate references/ file such as OOXML_REFERENCE.md, keeping only a concise pointer and the most common patterns inline.

Extract the 'docx-js 关键规则' recap and detailed docx-js snippets into a references/DOCX_JS_GUIDE.md, leaving a minimal quick-start example plus the critical gotchas in SKILL.md.

For the inline callouts that duplicate the recap list, pick one location (either inline '关键:' notes or the summary list) to remove the redundancy and tighten token use.

Dimension	Reasoning	Score
Conciseness	Instruction-dense throughout with minimal concept padding; it avoids explaining basics Claude already knows and leans on copy-paste code plus terse '关键' callouts, with the recap 'docx-js 关键规则' serving as a justified checklist rather than filler.	3 / 3
Actionability	Provides complete, executable JavaScript, bash commands with exact script paths, and copy-paste XML snippets for revisions, comments, and images — fully actionable rather than descriptive.	3 / 3
Workflow Clarity	Editing is laid out as an explicit numbered 3-step process with a validate.py checkpoint, and creation states '如果验证失败，解压、修复 XML 并重新打包', giving a clear validate→fix→repack feedback loop for fragile document operations.	3 / 3
Progressive Disclosure	Sections are well-organized and script references (unpack.py, pack.py, validate.py, comment.py) are one-level-deep and signaled, but the XML reference and docx-js pattern guide are inline in one large file rather than split into separate reference docs — content that could be separate remains inline.	2 / 3
	Total	11 / 12 Passed

Description

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.

A strong, third-person description with concrete capabilities, natural trigger terms, and explicit use-when guidance including negative scope. It cleanly answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions — '创建、读取、编辑或处理', generating '目录、标题、页码、信头', '提取或重组', '插入或替换图片', '查找替换', '处理修订或批注' — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	Opens with an explicit use-when clause ('当用户需要…使用此技能') and details both what it does and when to trigger it, plus scope exclusions — clearly answering both what AND when.	3 / 3
Trigger Term Quality	Uses natural user terms ('Word 文档', '.docx', '报告', '备忘录', '信函', '模板') and explicit negative triggers ('不要用于 PDF、电子表格、Google Docs'), giving good coverage of phrases users would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Word/.docx with explicit exclusions (PDF, spreadsheets, Google Docs, general programming), giving a clear niche unlikely to conflict with adjacent skills.	3 / 3
	Total	12 / 12 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
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 6 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/docx-en/SKILL.md
Commit: 734c8b9

Reviewed: 3 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.