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

94%

Does it follow best practices?

Impact

93%

1.52x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is docx in anthropics/skills

Quality

Content

88%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.

A thorough, highly actionable skill body with executable code and an explicit validation-gated editing workflow. Its main weakness is mild verbosity from repeated rules and inlined reference material that could be split into separate files.

Suggestions

Consolidate the table-width guidance into one location; the rule appears in the Tables section, a width-calculation block, a width-rules list, and the Critical Rules list—deduplicate to trim tokens.

Move the large docx-js API and XML reference into a separate reference file (e.g. references/docx-js-api.md) and link to it from SKILL.md to improve progressive disclosure.

Consider extracting the per-feature code snippets (lists, tables, images, hyperlinks, footnotes, tab stops, columns, TOC, headers/footers) into a cookbook reference, keeping only a quick-start example inline.

Dimension	Reasoning	Score
Conciseness	Efficient and assumes Claude's competence with OOXML basics, but some rules repeat (table-width guidance appears in the Tables section, a width-calculation block, the width-rules list, and the Critical Rules list), which could be trimmed. It is noticeably above the 'mostly efficient' anchor but not fully lean.	4 / 5
Actionability	Provides copy-paste-ready, fully executable JavaScript, bash, and XML throughout, with specific commands and examples covering the common cases (lists, tables, images, hyperlinks, footnotes, tracked changes, comments).	5 / 5
Workflow Clarity	The editing workflow is an explicit sequenced 3-step process (unpack → edit XML → pack) with a validation step ('python scripts/office/validate.py'), feedback loop ('If validation fails, unpack, fix the XML, and repack'), and documented auto-repair behavior—satisfying the feedback-loop requirement for document manipulation.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep references to real bundle scripts (unpack.py, pack.py, validate.py, soffice.py, accept_changes.py, comment.py), but the large docx-js API and XML reference is inlined in SKILL.md rather than split into separate reference files, leaving minor organization gaps.	4 / 5
	Total	18 / 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.

A strong, comprehensive description that explicitly states capabilities, lists natural trigger terms, and disambiguates from adjacent skills via an explicit exclusion clause. Both 'what' and 'when' are answered with concrete phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—create, read, edit, manipulate, extract, reorganize, insert/replace images, find-and-replace, tracked changes, comments, and conversion—giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (create/read/edit/manipulate Word documents) and 'when' with concrete trigger clauses ('Use this skill whenever', 'Triggers include', 'Also use when', 'If the user asks for').	5 / 5
Trigger Term Quality	Covers natural user phrasings ('Word doc', 'word document', '.docx', 'report', 'memo', 'letter', 'template') plus synonyms and the file extension, matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	The explicit exclusion clause ('Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks') carves a clear niche with minimal conflict risk against neighboring 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: ZHangZHengEric/Sage
Path: app/skills/docx/SKILL.md
Commit: 996fe90

Reviewed: ~19 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.