docx

Create, read, edit Word .docx documents and templates.

Quality

91%

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

100%

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

An exemplary body: dense actionable footguns, executable commands, a validated edit workflow with repair feedback loops, and detail correctly split into verified helper scripts rather than inlined.

Dimension	Reasoning	Score
Conciseness	The body is dense with domain-specific footguns and exact commands (page-size DXA values, ShadingType.CLEAR, w:delText) and avoids explaining concepts Claude already knows; it is comprehensive yet tight, matching the score-3 anchor of lean, every-token-earns-its-place content.	3 / 3
Actionability	It provides fully executable bash/Python commands and precise API values (e.g., `page: { size: { width: 12240, height: 15840 } }`, `cd unpacked && zip -Xr ../out.docx .`), matching the score-3 anchor of copy-paste-ready guidance.	3 / 3
Workflow Clarity	The editing workflow is an explicit sequence (unzip → strip symlinks → merge_runs → edit → zip → validate) with a validation checkpoint and a repair feedback loop (`--auto-repair`), and the Verification section is a checklist, matching the score-3 anchor for fragile XML operations.	3 / 3
Progressive Disclosure	SKILL.md is a well-sectioned overview that defers detail to real, verified bundle scripts (merge_runs.py, comment.py, accept_changes.py, office/validate.py, office/soffice.py), giving one-level-deep references with easy navigation as the score-3 anchor describes.	3 / 3
	Total	12 / 12 Passed

Description

82%

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 concise, concrete description with good trigger terms and a clear niche, but it omits an explicit "Use when..." trigger clause, which caps completeness.

Suggestions

Add a "Use when..." clause naming concrete triggers (e.g., reports, memos, letters, redlining, comments) to lift completeness from 2 to 3.

Optionally include the .dotx template extension as a trigger term so template-related requests route here.

Mirror a few of the body's natural phrasings ("report", "memo", "letter") into the description to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Create, read, edit Word .docx documents and templates" lists multiple concrete actions (create, read, edit) applied to specific objects (documents, templates), matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It answers "what" clearly but provides no "Use when..." trigger clause; per the judging guidelines a missing explicit trigger guidance caps completeness at 2, and it is not score 1 because the what is concrete.	2 / 3
Trigger Term Quality	It surfaces natural terms users say — "Word", ".docx", "documents", "templates" — giving good coverage rather than the sparse single-keyword case that defines score 2.	3 / 3
Distinctiveness Conflict Risk	The "Word .docx" niche is clearly bounded and unlikely to trigger for PDF, xlsx, or powerpoint skills, matching the score-3 anchor of a clear niche with distinct triggers.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/productivity/docx/SKILL.md
Commit: d0d116b

Reviewed: about 15 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.