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

88%

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

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

Quality

Content

77%

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

A strong, highly actionable skill body with excellent workflow sequencing and validation loops for fragile XML manipulation. Its main weakness is conciseness and progressive disclosure: a large inline reference with a redundant recap section that could be split into separate reference files.

Suggestions

Split the 'Creating New Documents' docx-js API patterns and the 'XML Reference' into separate reference files (e.g. docx-js.md, xml-reference.md) and link to them from SKILL.md to reduce inline token load and improve progressive disclosure.

Remove the 'Critical Rules for docx-js' recap section or convert it to a checklist pointer, since each rule is already stated inline next to its relevant example — the duplication inflates tokens.

Consolidate the table-width guidance (stated three times: in the Table example, the width-calculation block, and the Width rules list) into a single authoritative statement to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no concept-explaining fluff, but a 'Critical Rules for docx-js' recap repeats rules already given inline (dual table widths, PageBreak in Paragraph, DXA widths), and the full docx-js API usage plus XML reference could be split out to save tokens.	2 / 3
Actionability	Fully executable, copy-paste-ready code (docx-js Document/Table/ImageRun with all required fields), concrete commands (unpack.py/pack.py/validate.py/pandoc), and complete XML snippets for tracked changes and comments.	3 / 3
Workflow Clarity	The edit flow is explicitly sequenced ('Follow all 3 steps in order': Unpack → Edit → Pack) with an auto-repair validation checkpoint, and the creation flow has a validate→fix→repack feedback loop, matching the XML-manipulation rubric requirement.	3 / 3
Progressive Disclosure	Bundle scripts are real and referenced by correct paths, but everything (full docx-js API usage, complete XML reference) lives inline in a ~580-line SKILL.md with no one-level-deep reference .md files or clearly signaled navigation, so content that should be separate is inline.	2 / 3
	Total	10 / 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.

An exemplary description: concrete capabilities, natural trigger terms, explicit when-to-use guidance, and negative triggers that prevent scope conflict. It answers both 'what' and 'when' without verbosity.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'create, read, edit, or manipulate', 'extracting or reorganizing content', 'inserting or replacing images', 'find-and-replace', 'tracked changes or comments' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (create/read/edit/manipulate .docx) and when via 'Use this skill whenever...' and 'Triggers include:' and 'If the user asks for... use this skill' clauses.	3 / 3
Trigger Term Quality	Covers natural user terms including 'Word doc', 'word document', '.docx', plus deliverable names 'report', 'memo', 'letter', 'template', giving good coverage of what users would actually say.	3 / 3
Distinctiveness Conflict Risk	Clear Word/.docx niche reinforced by an explicit negative trigger ('Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks'), making conflict with other skills unlikely.	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
skill_md_line_count	SKILL.md is long (592 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: K-Dense-AI/scientific-agent-skills
Path: skills/docx/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.