turix-mac

Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./OpenCLaw_TuriX_skill/SKILL.md

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 body is genuinely actionable with concrete commands and a working helper script, but it is padded and redundant — the skills and monitoring material each appears twice with no split into reference files, and risky autonomous-UI workflows lack explicit validation checkpoints.

Suggestions

Merge the duplicate 'Skills System' and 'TuriX Skills System' sections and the two monitoring sections into single sections, removing the repeated hotkey and log-file references to cut length substantially.

Split the detailed skills-authoring and monitoring/debugging material into reference files (e.g. SKILLS.md, MONITORING.md) and link to them one level deep from SKILL.md, rather than inlining both copies.

Add an explicit validation/verification checkpoint to the run workflow (e.g., confirm screen-recording permission and conda env before launch, and verify the task outcome from the logs before reporting success) to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The 421-line body is noticeably verbose and padded: 'Skills System' and 'TuriX Skills System' sections overlap, 'Monitoring & Logs' and 'Monitoring and Debugging Guide' overlap, and the force-stop hotkey and log-file references are repeated several times, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	Provides concrete executable guidance such as 'skills/local/turix-mac/scripts/run_turix.sh "Open Chrome and go to github.com"', a python-docx code sample, and a troubleshooting table with real commands, matching 'mostly executable guidance; concrete code or commands with minor gaps' — held below 5 by placeholder paths like 'your_dir/TuriX-CUA'.	4 / 5
Workflow Clarity	Sequences are listed (run, monitor, debug) but the core run workflow lacks explicit validation checkpoints, and the document-creation workflow sends files via the GUI agent without a verify-before-send step, fitting 'steps listed but validation gaps' — the destructive/batch cap reinforces a max of 3 for this risky autonomous-UI skill.	3 / 5
Progressive Disclosure	The single referenced bundle file (scripts/run_turix.sh) is real and correctly pointed to, but the body is a monolithic wall of text with duplicated top-level sections ('Skills System' appears twice, 'Monitoring' appears twice) and no one-level-deep references to split out the large skills/monitoring detail, fitting 'some structure but could be better organized'.	3 / 5
	Total	12 / 20 Passed

Description

78%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 strong: it states what the skill does and when to use it with concrete trigger phrases and a distinct macOS-visual-automation niche. The main gap is that its action list and trigger-term coverage are good but not exhaustive.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions ('opening apps, clicking buttons, or navigating UIs that don't have a CLI or API'), placing it at the 'lists several specific actions; minor gaps' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Computer Use Agent (CUA) for macOS automation using TuriX') and 'when' ('Use when you need to perform visual tasks on the desktop'), fitting the 'has both what and when; when could be more explicit or specific' anchor.	4 / 5
Trigger Term Quality	Includes natural user phrasing like 'visual tasks on the desktop', 'opening apps', and 'clicking buttons', matching 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym/extension coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The 'macOS automation using TuriX' niche with visual-desktop-UI triggers is clearly distinct from other skills and carries minimal conflict risk, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	17 / 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: TurixAI/TuriX-CUA
Path: OpenCLaw_TuriX_skill/SKILL.md
Commit: fe00c49

Reviewed: 23 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.