docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', 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 or .dotx 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.

1.40x

Quality

93%

Does it follow best practices?

Impact

93%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 high-quality, expert-level skill body: dense with non-obvious footguns, fully executable commands, a validated editing workflow, and appropriate offloading of complexity into real bundled scripts. The only dents are a slightly discursive tracked-changes failure-mode discussion and an implicit rather than explicit error-recovery loop.

Suggestions

Tighten the tracked-changes section: the pandoc-vs-accept_changes.py spacer-paragraph exception can be condensed (or moved to a reference) without losing the core gotcha that emptied paragraphs read as stray bullets.

Make the validation feedback loop explicit — after `validate.py out.docx --original doc.docx`, add 'If errors are reported, fix word/document.xml and re-run validate before delivering,' mirroring the anchor-5 validate→fix→retry pattern.

Sharpen the verify-output step by naming what to inspect (e.g., broken table shading, missing TOC entries, stray empty bullets from paragraph deletions) so the render-and-look check is actionable rather than open-ended.

Dimension	Reasoning	Score
Conciseness	Lean and information-dense throughout — the docx-js footguns and OOXML schema ordering are non-obvious knowledge Claude lacks, so the tokens earn their place. A few asides (the pandoc-vs-accept_changes spacer-paragraph exception) could be trimmed without losing the core gotcha, keeping it just shy of a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout — `python scripts/office/soffice.py --headless --convert-to pdf`, `unzip -q ... -d unpacked/`, `find unpacked -type l -delete`, exact DXA dimensions (12240/15840), and concrete comment.py invocations cover the common cases.	5 / 5
Workflow Clarity	The editing workflow is a clear sequenced procedure (unzip → strip symlinks → merge_runs → edit XML → repack → validate) with a validation checkpoint (`validate.py ... --original`) and a render-and-look verification step, satisfying the destructive-operation cap. The error-recovery loop (fix-and-re-validate) is implicit rather than spelled out, which is the minor gap below a 5.	4 / 5
Progressive Disclosure	SKILL.md is a focused overview of gotchas and usage; the heavy logic lives one level deep in real, correctly-referenced scripts (merge_runs.py, validate.py, accept_changes.py, comment.py, soffice.py — all present in ./scripts/). Sections are well-organized and navigation is easy.	5 / 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.

An exemplary description: concrete actions, comprehensive natural trigger terms with synonyms and extensions, explicit what-and-when guidance, and a clear negative boundary. Voice is third-person about the user ("the user wants"), matching the accepted good-example pattern.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "create, read, edit, or manipulate", "extracting or reorganizing content", "inserting or replacing images", "find-and-replace", "tracked changes or comments", "converting content into a polished Word document" — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both what ("create, read, edit, or manipulate Word documents") and when ("Use this skill whenever...", "Triggers include...", "Also use when...", "If the user asks for...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and extensions: "Word doc", "word document", ".docx", ".dotx", plus deliverable nouns "report", "memo", "letter", "template" — exactly the phrases a user would say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (.docx/.dotx) with an explicit exclusion clause — "Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks" — minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: anthropics/skills
Path: skills/docx/SKILL.md
Commit: 3b3fad9

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.