docx

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

1.28x

Quality

88%

Does it follow best practices?

Impact

100%

1.28x

Average score across 5 eval scenarios

Securityby

Medium

Suggest reviewing before use

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.

The body is highly actionable with clear, validated workflows and good progressive-disclosure intent. Its main weaknesses are minor verbosity/repetition in the redlining section and several referenced bundle paths (docx-js.md, ooxml.md, ooxml/scripts/unpack.py|pack.py) that are missing from the actual bundle.

Suggestions

Tighten the redlining section: the "Batching Strategy" and step-4 "Suggested batch groupings" overlap — merge them into a single concise batching note to reduce token cost.

Fix or restore the referenced bundle paths (docx-js.md, ooxml.md, and ooxml/scripts/unpack.py|pack.py) so the one-level-deep references resolve, which would move progressive_disclosure to the top anchor.

Drop or trim the "A .docx file is essentially a ZIP archive containing XML files..." sentence, since it explains a concept Claude already knows.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-driven, but includes mild background ("A .docx file is essentially a ZIP archive...") and repeats batching guidance twice in the redlining section, so it could be tightened.	2 / 3
Actionability	Provides concrete, executable commands (pandoc, unpack.py, pack.py, soffice, pdftoppm) and a real XML edit example, with copy-paste-ready syntax and options — matching the fully-executable top anchor.	3 / 3
Workflow Clarity	A decision tree routes tasks to sequenced workflows, and the redlining workflow includes explicit batching plus a final verification step with grep-based validation, providing the feedback loop the top anchor rewards.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing one level deep to docx-js.md and ooxml.md, but those referenced files are absent from the bundle and the ooxml/scripts/ paths for unpack.py/pack.py do not exist at the referenced location, so navigation is signaled but partially broken.	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.

The description is concise, specific, and complete: it lists concrete capabilities and gives explicit "when to use" triggers scoped to .docx files. It reads in third person and avoids vague fluff, matching the strongest rubric anchors across all dimensions.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "document creation, editing, and analysis" plus "tracked changes, comments, formatting preservation, and text extraction" — matching the top anchor that lists several specific actions.	3 / 3
Completeness	Explicitly answers both what (the listed capabilities) and when ("When Claude needs to work with professional documents (.docx files) for: (1)...(4)"), matching the anchor with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say — ".docx files", "professional documents", "tracked changes", "comments" — with enough variation to match the top anchor; not merely jargon or a single keyword.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to .docx with a clear niche (tracked changes, comments, formatting preservation) and distinct triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: ThinkInAIXYZ/deepchat
Path: resources/skills/docx/SKILL.md
Commit: b8dbc89

Reviewed: about 7 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.