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

83%

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

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced skill with executable code and validation feedback loops throughout. The main weaknesses are duplicated content between the feature sections and the 'Critical Rules' summary, and a monolithic structure that keeps large reference material inline instead of splitting it into referenced files.

Suggestions

Dedupe the 'Critical Rules for docx-js' section: keep only net-new gotchas (e.g. 'Never use \n', 'Never use tables as dividers') and point back to the relevant section for items already shown with code, to tighten conciseness.

Split the large docx-js API reference and/or XML Reference into a separate referenced file (e.g. DOCX_JS_REFERENCE.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive disclosure.

Reference the existing scripts/templates/*.xml bundle files (comments.xml, commentsExtended.xml, etc.) from the Comments section, or remove them from the bundle if unused, so the bundle structure is fully navigable.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with terse 'CRITICAL' annotations and no concept tutorials, but the 'Critical Rules for docx-js' section restates points already shown with code above (page size, landscape, unicode bullets, dual table widths, ShadingType, PageBreak, ImageRun type), so it could be tightened.	2 / 3
Actionability	Fully executable bash, JavaScript, and XML snippets throughout, with specific copy-paste-ready examples for every feature (tables, images, hyperlinks, footnotes, TOC, tracked changes, comments).	3 / 3
Workflow Clarity	Editing is an ordered 3-step sequence ('Follow all 3 steps in order') with explicit validation (validate.py after creation; pack.py validates with auto-repair) and a feedback loop ('If validation fails, unpack, fix the XML, and repack').	3 / 3
Progressive Disclosure	Sections and a Quick Reference table give good navigation and script references are one-level deep and clearly signaled, but the document is monolithic (~585 lines) with the full docx-js API reference and XML reference inline rather than split into separate files; the existing scripts/templates/*.xml bundle files are not referenced.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, specific description with excellent trigger-term coverage, complete what/when guidance, and explicit negative triggers that minimize conflict risk. The only issue is the second-person imperative opening ('Use this skill whenever...') rather than third-person voice.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('create, read, edit, or manipulate Word documents', 'inserting or replacing images', 'find-and-replace', 'tracked changes or comments', 'converting content into a polished Word document') which is a 3, but opens with the imperative 'Use this skill whenever...' (second-person address) instead of third-person voice, triggering the -1 voice penalty.	2 / 3
Completeness	Explicitly answers both what (create/read/edit/manipulate, extract, images, find-and-replace, tracked changes, comments, convert) and when ('whenever the user wants to', 'Triggers include', 'Also use when', 'If the user asks for a report...'), with explicit negative triggers.	3 / 3
Trigger Term Quality	Strong coverage of natural user terms: 'Word doc', 'word document', '.docx', 'report', 'memo', 'letter', 'template', plus 'tracked changes', 'comments', and 'find-and-replace'.	3 / 3
Distinctiveness Conflict Risk	Clear .docx niche with distinct triggers and an explicit exclusion clause ('Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks'), making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 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 (591 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 4 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: nextlevelbuilder/goclaw
Path: skills/docx/SKILL.md
Commit: e71d6a5

Reviewed: 10 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.