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.

55

Quality

63%

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/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

67%Scale 1-5

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

This is a well-structured skill that effectively covers multiple DOCX workflows with a clear decision tree for routing. Its main strengths are the comprehensive redlining workflow with validation steps and the good use of progressive disclosure to external reference files. Weaknesses include some redundancy in batch organization guidance, repeated mandatory reading instructions, and the basic editing workflow lacking explicit validation before delivery.

Suggestions

Remove the duplicate batch organization guidance (appears in both steps 2 and 4 of the redlining workflow) and consolidate into one location

Add an explicit validation/verification step to the basic 'Editing an existing Word document' workflow (e.g., convert back to markdown and verify changes)

Remove the vacuous 'When to Use' section which adds no value beyond restating the overview

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but has some unnecessary verbosity. The repeated 'MANDATORY - READ ENTIRE FILE' instructions appear three times with nearly identical wording. The decision tree section and batch organization guidance contain some redundancy (batch groupings are explained twice in steps 2 and 4). The 'When to Use' section is vacuous. However, it avoids explaining basic concepts Claude already knows.

3 / 5

Actionability

The skill provides concrete, executable commands throughout (pandoc, unpack/pack scripts, soffice, pdftoppm) with specific flags and arguments. The redlining workflow includes a good XML example showing correct vs incorrect tracked changes. However, the actual Document library API usage is deferred to external files (ooxml.md, docx-js.md), so the skill itself lacks complete executable code for the core editing operations.

4 / 5

Workflow Clarity

The workflows are clearly sequenced with numbered steps. The redlining workflow includes a final verification step with specific grep commands to validate changes. The batching strategy includes validation between batches. However, the basic editing workflow (non-redlining) lacks explicit validation steps between pack and delivery - there's no 'verify the output' step. The decision tree at the top is a helpful routing mechanism.

4 / 5

Progressive Disclosure

The skill appropriately references external files (ooxml.md, docx-js.md) for detailed API documentation and keeps the overview at a manageable level. References are clearly signaled with file names and approximate line counts. However, without bundle files provided to verify these references exist and are well-structured, and with some content that could be further split out (the full redlining workflow is quite long inline), it falls slightly short of a 5.

4 / 5

Total

15

/

20

Passed

Description

58%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 adequately identifies the domain (.docx files) and high-level actions but lacks specificity in concrete capabilities and misses common user-facing trigger terms like 'Word document'. The technical detail about ZIP/XML is useful for Claude's understanding but doesn't help with skill selection. The 'when' guidance is present but could be more explicit.

Suggestions

Add common synonyms and trigger terms: 'Word document', 'Word file', '.doc', 'Microsoft Word' to improve discoverability.

List more specific capabilities like 'extract text, modify formatting, insert tables, add images, update headers/footers' instead of just 'create, edit, or analyze'.

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user mentions Word documents, .docx files, or needs to create/modify formatted documents.'

DimensionReasoningScore

Specificity

Names the domain (.docx files) and lists general actions (create, edit, analyze), but doesn't specify concrete sub-actions like extracting tables, formatting text, or inserting images.

3 / 5

Completeness

Has a clear 'what' (create, edit, analyze .docx files) and an implicit 'when' ('A user may ask you to...'), though the 'when' clause could be more explicit with concrete trigger phrases.

4 / 5

Trigger Term Quality

Includes '.docx' and 'ZIP archive containing XML files' but misses natural user terms like 'Word document', 'Word file', '.doc', 'Microsoft Word', or 'document editing'.

3 / 5

Distinctiveness Conflict Risk

Specifies .docx files which helps distinguish it, but 'create, edit, or analyze' is broad and could overlap with general document skills. The mention of ZIP/XML internals adds some distinctiveness but isn't a user-facing trigger.

3 / 5

Total

13

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

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.