gui-automation

Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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.

A well-structured, highly actionable skill body with a clear verify-driven workflow and good progressive disclosure. The main trim opportunity is the inline Quick Reference table, which overlaps with the dedicated reference file.

Suggestions

Shorten the inline Quick Reference table to the most-used commands and defer the full list to references/command-reference.md to reduce token duplication.

Dimension	Reasoning	Score
Conciseness	Largely lean and command-forward with minimal prose, but the 20-row Quick Reference table duplicates much of references/command-reference.md that already exists, so it could be trimmed; fits anchor 4 rather than 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands across many concrete scenarios (click, form fill, upload, zoom, drag, fuzz); matches the anchor-5 example.	5 / 5
Workflow Clarity	Explicit 'Look → Act → Verify' loop with re-screenshot validation checkpoints and stale-coordinate guidance forms a clear feedback loop; matches the anchor-5 example.	5 / 5
Progressive Disclosure	Well-organized sections with a single clearly-signaled, one-level-deep reference (references/command-reference.md) for full argument syntax; tutorial inline, bulk syntax external; matches the anchor-5 example.	5 / 5
	Total	19 / 20 Passed

Description

95%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.

A strong, specific description with explicit trigger guidance and a clear, distinctive niche. The only weakness is the second-person voice ('you need to'), which costs it the top specificity anchor per the rubric's voice rule.

Suggestions

Rephrase in third person to avoid the voice penalty, e.g. 'Use when visually interacting with a GUI' or 'Use when the user needs to visually interact with a GUI'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA'), which is comprehensive, but the second-person phrasing 'Use when you need to' triggers the voice penalty, reducing the score by 1 from the anchor-5 match.	4 / 5
Completeness	Explicitly answers both 'what' (visually interact with a GUI) and 'when' via a concrete 'Use when you need to...' trigger clause; matches the anchor-5 example.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would actually say — 'test buttons', 'fill forms', 'take screenshots', 'fuzz web pages', 'automate user flows', 'end-to-end QA' — with synonym coverage; matches the anchor-5 example.	5 / 5
Distinctiveness Conflict Risk	Clear niche — visual GUI interaction explicitly contrasted with shell/API — with distinct triggers and minimal overlap risk; matches the anchor-5 example.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: trycua/cua
Path: skills/gui-automation/SKILL.md
Commit: 359fad5

Reviewed: 4 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.