Name: docx-official
Rating: 60.8 (1 reviews)
Author: administrakt0r

docx-official

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/docx-official/SKILL.md

The canonical home for this skill is docx-official in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

78%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.

The content is highly actionable with executable commands and a well-sequenced redlining workflow, but it suffers from a bundle/reference mismatch where the files it points to are absent and the bundle files it ships are not navigated to.

Suggestions

Reconcile referenced paths with the actual bundle: either ship docx-js.md, ooxml.md, and ooxml/scripts/unpack.py & pack.py, or update the body links to point at the real scripts/document.py and scripts/utilities.py.

Add an explicit validation feedback loop to the basic editing workflow (e.g., a validate step between editing and packing, with fix-and-retry on failure) to match the redline workflow's rigor.

De-duplicate the batching guidance so the by-section/type/proximity organization appears once rather than repeated across steps 2 and 4.

Dimension	Reasoning	Score
Conciseness	Largely lean and actionable with copy-paste commands, but has minor redundancy — the Overview repeats the frontmatter description verbatim and the batching guidance (by section/type/proximity) is listed twice in steps 2 and 4.	4 / 5
Actionability	Every workflow ships copy-paste-ready commands (pandoc, unpack.py, pack.py, soffice, pdftoppm) plus a concrete tracked-changes XML example covering the common read/create/edit/redline/convert cases.	5 / 5
Workflow Clarity	The redlining workflow has a clear 6-step sequence with a final verification step and per-batch testing, but the basic editing workflow lacks an explicit pre-pack validation step and the redline feedback loop (verify-fail -> fix -> redo) is only implicit.	4 / 5
Progressive Disclosure	The body is structured as an overview with clearly signaled one-level-deep references, but the referenced paths (docx-js.md, ooxml.md, ooxml/scripts/unpack.py, ooxml/scripts/pack.py) do not exist in the provided bundle, and the actual bundle files (scripts/document.py, scripts/utilities.py, scripts/templates/*) are never referenced from the body.	3 / 5
	Total	16 / 20 Passed

Description

66%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.

The description clearly conveys what the skill does across several concrete .docx actions and is reasonably distinct, but it lacks an explicit "Use when..." trigger clause, leaving the activation conditions only weakly implied.

Suggestions

Add an explicit "Use when..." clause naming the trigger situations (e.g., "Use when a user asks to create, edit, review with tracked changes, or analyze a Word/.docx document").

Include natural synonyms like "Word document" or "Microsoft Word" alongside ".docx" to broaden trigger-term coverage.

Mention distinctive sub-capabilities (tracked changes/redlining, comments, format conversion) to sharpen the what and reduce overlap with generic document skills.

Dimension	Reasoning	Score
Specificity	Names the .docx domain and several concrete actions — "create, edit, or analyze the contents" plus "read or edit" — listing several specific actions with only minor coverage gaps (no mention of sub-tasks like tracked changes or comments).	4 / 5
Completeness	Has a clear "what" (create/edit/analyze .docx contents) but the "when" is only weakly implied via "A user may ask you to" with no explicit "Use when..." trigger clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users say ("create, edit, or analyze", ".docx file") with good coverage, but omits common synonyms like "Word document" or "Microsoft Word".	4 / 5
Distinctiveness Conflict Risk	The .docx niche is mostly distinct with minimal conflict risk, though the broad create/edit/analyze verbs allow minor overlap with related document or PDF skills.	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/docx-official/SKILL.md
Commit: 57c135b

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.