docx

Create, read, edit, template, and review Word .docx files.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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.

An exemplary skill body: fully executable commands, a complete quick-reference table, an explicit validation loop, and clean offloading of deep XML detail to a one-level-deep reference. The only flaw is mild redundancy between the How-to-Run examples and the Quick Reference table.

Suggestions

Drop or shrink the "How to Run" example block since the Quick Reference table already shows every script invocation with full arguments.

Consider moving the longer Pitfall entries (e.g. revision coverage, field codes) into references/revisions-and-comments.md if token budget matters, keeping only one-line pointers here.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — no padding, no explanations of what docx or python-docx are, and every Pitfall is non-obvious domain knowledge. It misses 5 only because the "How to Run" bash block substantially duplicates the Quick Reference table that immediately follows it, a minor trim candidate.	4 / 5
Actionability	Every entry is a complete, copy-paste-ready CLI invocation (e.g. `docx_edit.py set-cell f.docx --table 0 --row 1 --col 2 --text X`), the create-spec format is enumerated field by field, and even the PDF fallback gives the exact `soffice --headless` command plus an availability check. Fully executable with the common cases covered.	5 / 5
Workflow Clarity	The numbered Procedure ends with "Verify (always)" and is backed by a dedicated Verification section with concrete expected outcomes (revisions list returns `[]`, `--strict` or `unfilled_tokens == []`, validate exits 0). Despite involving batch/XML manipulation, explicit validation and feedback loops are present, so the workflow-clarity cap does not apply.	5 / 5
Progressive Disclosure	SKILL.md stays an overview plus quick reference; raw WordprocessingML detail is split into the clearly signaled, one-level-deep references/revisions-and-comments.md (verified present), and full spec documentation is delegated to the top of scripts/docx_create.py. Content is appropriately split and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

70%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.

A concise, third-person description that names the domain and concrete actions with a distinct trigger surface. Its main weakness is the absence of any 'Use when...' trigger guidance, which both caps completeness and thins the natural-language trigger terms.

Suggestions

Append a trigger clause, e.g. "Use when the user asks for a Word document, mentions .docx files, tracked changes, or document comments, or needs to fill a .docx template."

Surface the differentiating capabilities (tracked-change accept/reject, comment management, {{token}} templating) in the description itself so specificity and trigger coverage reflect what the skill actually does.

Add natural synonyms such as "Word documents" or "Microsoft Word" alongside "Word .docx files".

Dimension	Reasoning	Score
Specificity	"Create, read, edit, template, and review Word .docx files" names the domain plus five concrete actions, matching the anchor for several specific actions with minor gaps. It falls short of 5 because higher-value capabilities (tracked changes, comments, {{token}} templating) are not surfaced, and beats 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	The "what" is clear (create/read/edit/template/review .docx), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the what-half is fully explicit, not vague.	3 / 5
Trigger Term Quality	"Word .docx files" covers the product name and the file extension users naturally mention. Good keyword coverage, but common phrasings like "Word documents" or "Microsoft Word" are missing, so it does not reach the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	"Word .docx files" carves a clear niche with distinct triggers and minimal conflict risk against sibling document/spreadsheet/presentation skills. It clearly matches the top anchor rather than the minor-overlap anchor at 4.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/productivity/docx/SKILL.md
Commit: 68fa7e9

Reviewed: 3 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.