CtrlK
BlogDocsLog inGet started
Tessl Logo

officecli-docx

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 and workflow-rich, with executable commands throughout and strong validation/feedback loops. Its main weakness is progressive disclosure: a large single-file body with no bundle files inlines recipes and appendices that a leaner design would split into separate references.

Suggestions

Move the report-level recipes (a)-(f) and the raw-set XML appendix into separate reference files (e.g. references/RECIPES.md, references/RAW-SET-XML.md) and link to them from SKILL.md, keeping the main file as an overview.

Extract the advanced/specialty topics (equations, comments/tracked changes, watermark) into references/ADVANCED.md and keep only a one-line pointer plus the 'skip if writing a report' gate inline.

Trim incidental color-commentary sentences (e.g. 'Ninety percent of a build is…') to tighten conciseness without losing the load-bearing rules.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — the Mental Model explains the ZIP-of-XML structure in one tight paragraph rather than padding what a docx is, and almost every line is a command, rule, or pitfall. It is not 5 because at ~558 lines there are a few trimmable color-commentary passages and the absolute volume is large for a context window.

4 / 5

Actionability

Packed with copy-paste-ready, fully executable `officecli` commands with real paths and prop values — Quick Start, Reading & Analysis, the Creating & Editing subsections, recipes (a)-(f), and the Delivery Gate bash script. Specific examples cover all common cases (paragraphs, tables, lists, fields, TOC, headers/footers, images, charts).

5 / 5

Workflow Clarity

The Common Workflow gives 6 numbered steps with explicit checkpoints ('After each structural op, get it back before stacking on top'), the QA section defines a fix-and-verify feedback loop ('done after one fix-and-verify cycle finds zero new issues'), and the Delivery Gate is a copy-paste script that REJECTs on failure. Clear sequence, explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

The file is well-sectioned and defers bulk reference material to `help docx <element>` and sibling skills, but it is a 558-line monolith with no bundle files (references/scripts/assets absent); the recipes, the raw-set XML appendix, and the advanced/specialty topics are inlined rather than split into separate reference files. Not 4 because the bulk detail is not actually split across files; not 2 because internal sectioning and the 'skip if you are writing a report' gate provide real structure.

3 / 5

Total

17

/

20

Passed

Description

96%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 is excellent: it explicitly states what the skill does and when to trigger it, with concrete trigger phrases, file extensions, and synonyms. The only weakness is the broad generic triggers ('document', 'report') that introduce minor conflict risk with other document skills.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text… editing, modifying, or updating… tracked changes, comments, headers/footers, or tables of contents' — giving comprehensive coverage of the docx domain. It does not fall to 4 because the action list is broad rather than having only minor gaps.

5 / 5

Completeness

Explicitly answers WHAT (the enumerated docx actions) and WHEN with concrete trigger phrases — 'Use this skill any time a .docx file is involved' and 'Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.' Both clauses are present and concrete, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Covers natural terms plus synonyms and the file extension: '.docx file', 'Word doc', '.docx filename', alongside 'document', 'report', 'letter', 'memo'. Matches the anchor 5 example (PDF files, PDFs, forms, .pdf) in including both synonyms and the extension.

5 / 5

Distinctiveness Conflict Risk

Clearly niche (.docx / Word) with distinct triggers like '.docx filename' and 'Word doc', but the generic triggers 'document' and 'report' could fire for non-docx contexts, creating minor overlap with other document-handling skills. Not 5 because of that overlap risk; not 3 because the dominant triggers are highly specific.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (563 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
iOfficeAI/OfficeCLI
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.