CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 well-structured with concrete commands and a thorough redlining workflow, but its two main workflows depend on mandatory-read files (docx-js.md, ooxml.md) and scripts (ooxml/scripts/unpack.py, pack.py) that are absent from the bundle, and the basic editing workflow lacks a validation checkpoint. This makes otherwise actionable guidance incomplete in practice.

Suggestions

Ship the referenced docx-js.md and ooxml.md files (or correct the references to point at the actual bundle, e.g. scripts/document.py for the Document library), since both creation and editing workflows mark them MANDATORY.

Fix the script paths: the bundle uses 'scripts/' and contains document.py/utilities.py but no unpack.py or pack.py — either add those scripts or point the unpack/pack commands at the real files.

Add an explicit validate-and-retry checkpoint to the 'Basic OOXML editing' workflow so destructive edits are checked before repacking, mirroring the redlining final-verification step.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but includes unnecessary repetition (batch-grouping options 'By section/By type/By proximity' are listed in both step 2 and step 4) and padding ('A .docx file is essentially a ZIP archive containing XML files...' repeats what Claude knows, plus a vague 'When to Use' line), keeping it at 'mostly efficient but could be tightened' rather than the lean 4.

3 / 5

Actionability

Concrete executable commands are present (pandoc, soffice, pdftoppm, a real tracked-changes XML example), but the two primary workflows gate their detail behind files that do not exist in the bundle ('docx-js.md', 'ooxml.md') and invoke scripts at a path that is absent ('ooxml/scripts/unpack.py', 'pack.py'), so key execution details are missing — incomplete rather than just minor gaps.

3 / 5

Workflow Clarity

The redlining workflow is well-sequenced with a final verification step (pandoc + grep checks) and grep-before-script guidance, but the 'Basic OOXML editing' workflow is a destructive operation with no validation checkpoint, triggering the destructive/batch cap that precedence-forces workflow clarity to 3.

3 / 5

Progressive Disclosure

Structure is good (clear decision tree, well-organized sections) and the references to docx-js.md/ooxml.md are clearly signaled and one level deep, but those referenced files do not exist in the actual bundle and the cited script paths ('ooxml/scripts/...') do not match the provided 'scripts/' directory, so navigation is broken rather than merely having minor gaps.

3 / 5

Total

12

/

20

Passed

Description

61%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 scopes the skill to .docx files and names concrete create/edit/analyze actions, but lacks an explicit 'Use when...' trigger clause and omits common synonyms like 'Word' and 'redlining'. It is competent but not comprehensive or maximally trigger-rich.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when creating, editing, or analyzing Word documents (.docx), including redlining/tracked changes.'

Include the synonym 'Word document' alongside '.docx' so the description matches how users naturally phrase requests.

Remove the generic 'different tools and workflows available for different tasks' filler in favor of a concrete capability list.

DimensionReasoningScore

Specificity

Names the .docx domain with three concrete actions ('create, edit, or analyze the contents of a .docx file'), but coverage is generic and padded with the vague 'different tools and workflows available for different tasks', so it stops at the 1-2-actions/comprehensive boundary rather than reaching the comprehensive 4.

3 / 5

Completeness

The 'what' is clear (create/edit/analyze .docx contents) but there is no explicit 'Use when...' trigger clause — the 'when' is only weakly implied by 'A user may ask you to...', so per the missing-trigger-guidance cap it cannot exceed 3.

3 / 5

Trigger Term Quality

Includes the natural file extension '.docx file' and the natural action verbs 'create, edit, or analyze', giving good keyword coverage; it does not reach 5 because common synonyms like 'Word document', 'redlining', and 'tracked changes' are missing.

4 / 5

Distinctiveness Conflict Risk

The .docx file type is a clear, distinct niche with low conflict risk; it stays at 4 rather than 5 because the broad 'analyze the contents' framing and 'different tools and workflows' phrasing leave minor overlap risk with related document-analysis skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.