/carbon-ux
Run focused CARBON UX testing and generate a branded ux report.
Mia · UsabilityExperience & accessibilityWhen to use it
A sequence works technically but feels confusing or untrustworthy.
Before you start
Describe the user goal and follow the entire journey, including waiting and recovery. Separate observed friction from hypotheses about abandonment or satisfaction.
Try this in your coding agent.
/carbon-ux Review the checkout journey for confusing steps and missing feedback.Replace sample paths with your project. Slash names are shorthand; your host may use a plugin prefix or a skill picker. Invocation help →
ILLUSTRATIVE WALKTHROUGH
Checkout feedback
An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.
- 01Read context
- 02Investigate
- 03Show evidence
- 04Report
Coding-agent conversation
I’m reviewing checkout feedback. I’ll keep the scope and permissions explicit.
Follow the weakest evidence link and record what remains blocked.
Here is the evidence trail to inspect: Submit → waiting state has no progress message → repeated action becomes likely.
A slow response leaves users unsure whether the order was submitted. Behavioral impact is a hypothesis until studied with users.
Example report
Illustration
TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.
- Failed request
- Preserved state
- Safe retry
Illustrated outcome
A slow response leaves users unsure whether the order was submitted.
Evidence to inspect
Submit → waiting state has no progress message → repeated action becomes likely.
Still untested / not established
Behavioral impact is a hypothesis until studied with users.
Ready. Read the full example or play its steps.
What a useful result contains
A bounded claim
For checkout feedback, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.
An inspectable trail
Submit → waiting state has no progress message → repeated action becomes likely. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.
The qualification
Behavioral impact is a hypothesis until studied with users.
The next decision
Decide whether the evidence calls for a focused check, a reviewed fix or more context. Do not convert a plausible example into a verified finding.
Adapt the example to your project
- Replace checkout feedback with a real feature, path or decision in your project.
- State the expected rule and its source. Include safe fixtures, constraints and a budget where appropriate.
- Ask for exact evidence and remaining gaps. Approve consequential actions separately.
/jay Review the /carbon-ux result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.Where to go next
/carbon-usability →/carbon-personas →Content checked against the local command definition: skills/carbon-ux/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.