CtrlK
BlogDocsLog inGet started
Tessl Logo

docx

Create, edit, inspect, render, review, compare, annotate, sanitize, and finalize professional Microsoft Word .docx documents. Use for new Word documents, source- or template-based reports, targeted edits that preserve an existing file, comments and tracked changes, document structure or metadata analysis, accessibility evidence, visual layout review, and controlled OOXML changes. Use only for .docx files, not legacy .doc, macro-enabled .docm, or live Microsoft Word control.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

The content is a tightly structured, executable workflow with strong validation feedback loops and clean progressive disclosure into real reference files. The only minor gap is a handful of prose sentences that could be tightened for token efficiency.

Suggestions

Tighten advisory sentences (e.g., 'Use judgment instead of converting the request into a universal checklist or collection of boolean permissions') to a short imperative to lift conciseness to the top anchor.

Consider moving the 'Choose presentation intentionally' prose into design-and-layout.md and keeping only a one-line pointer in the body.

The env-setup block uses {{SKILL_ROOT_SHELL}} and $INPUT_DOCX placeholders; a one-word note that these are resolved by the harness would prevent a copy-paste dead end.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no boilerplate about what .docx is), but a few guidance sentences such as the 'Use judgment instead of converting the request into a universal checklist' aside could be trimmed, keeping it just short of the fully lean anchor.

4 / 5

Actionability

Copy-paste-ready bash commands with exact paths and flags are given for every stage (inspect, scaffold, build, review, evaluate, deliver, fallback-patch), covering the common cases fully.

5 / 5

Workflow Clarity

A three-stage sequence is laid out with explicit validation feedback loops (review the document itself, re-review after each candidate revision, write an independent evaluator) and gating on destructive deliver/replace-source operations, matching the top anchor.

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with a dedicated 'Load references only when needed' section linking five one-line-scoped reference files that all exist on disk, plus separate scripts — well-signaled, one level deep, easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

100%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 exemplary: a comprehensive, third-person list of concrete actions paired with an explicit 'Use for…' trigger list and a boundary clause. Every dimension lands at the top anchor with no verbosity or over-claim.

DimensionReasoningScore

Specificity

Ten concrete verbs are named ("Create, edit, inspect, render, review, compare, annotate, sanitize, and finalize") covering the full lifecycle, matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly answers both what (the ten actions) and when ("Use for new Word documents, source- or template-based reports…") with concrete trigger phrases, and adds a boundary clause, matching the top anchor.

5 / 5

Trigger Term Quality

Covers natural user phrases plus synonyms and the file extension ("Microsoft Word .docx documents," "comments and tracked changes," "visual layout review," "OOXML"), satisfying the synonyms-and-extension anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply scoped to .docx and explicitly excludes .doc, .docm, and live Word control, giving a clear distinct trigger set with minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenBMB/PilotDeck
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.