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.

Highly actionable, concise, and well-sequenced content with strong validation feedback loops for the editing workflow. The main weakness is progressive disclosure: most reference-grade detail is kept inline rather than split into clearly signaled separate files.

Suggestions

Move the detailed XML Reference (tracked changes, comments, images) into a separate REFERENCES.md or xml.md and link to it one level deep from SKILL.md, keeping the body as an overview.

Consider extracting the full docx-js API recipes (Styles, Lists, Tables, Headers/Footers) into a dedicated docx-js.md reference so the main skill body stays scannable.

Add a short 'Bundle contents' map listing the scripts/templates and what each is for, so Claude can navigate the provided files without scanning the directory.

Dimension	Reasoning	Score
Conciseness	Lean and dense — jumps straight to executable code and tables without explaining what .docx files are or how docx-js works; every section earns its tokens. Not quite below 3 because it avoids concept padding Claude already knows.	3 / 3
Actionability	Provides copy-paste-ready, complete code and shell commands throughout (Setup, Tables, Images, Tracked Changes XML) with specific parameter values like DXA widths and EMU units, rather than pseudocode.	3 / 3
Workflow Clarity	The editing flow is a clearly numbered 3-step sequence (Unpack → Edit XML → Pack) with an explicit validation checkpoint via pack.py's auto-repair and validate.py, plus an "if validation fails, unpack, fix the XML, and repack" feedback loop appropriate for document manipulation.	3 / 3
Progressive Disclosure	Well-organized into clear sections and references real bundle files (scripts/office/, scripts/comment.py, scripts/templates/), but nearly all detail lives inline in this single ~480-line file rather than being split into one-level-deep reference files; the XML Reference in particular could be externalized. It is not a monolithic wall of text, so it stays above 1, but lacks the signaled external references that earn a 3.	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, comprehensive description that names concrete capabilities, lists natural trigger terms, answers both what and when explicitly, and draws a clear boundary against neighboring skills. No meaningful weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "create, read, edit, or manipulate Word documents", "inserting or replacing images", "performing find-and-replace", and "working with tracked changes or comments".	3 / 3
Completeness	Explicitly answers both what (create/read/edit/manipulate .docx and enumerated sub-tasks) and when ("Use this skill whenever..." with a concrete "Triggers include" list), so it exceeds the 2-cap that would apply to a missing when-clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — "Word doc", "word document", ".docx", "report", "memo", "letter", "template" — across phrasings a user would naturally use.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to .docx and explicitly excludes PDFs, spreadsheets, Google Docs, and general coding tasks, making conflicts with adjacent skills unlikely.	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
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: eigent-ai/eigent
Path: resources/example-skills/docx/SKILL.md
Commit: 9d0a169

Reviewed: about 10 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.