CARBON — Engineering ConfidenceUser Guide
CHAPTER 14 / 60 Pro

/carbon-usability

Run focused CARBON Usability testing and generate a branded usability report.

Mia · UsabilityExperience & accessibility

When to use it

You want to know whether a person can find and complete a task.

Before you start

State the user knowledge level and task. Inspect discoverability, wording, feedback and recovery. Simulated judgments complement rather than replace research with real people.

Try this in your coding agent.

/carbon-usability Evaluate whether a first-time user can find and use password reset.

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

First-time password recovery

An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.

  1. 01Read context
  2. 02Investigate
  3. 03Show evidence
  4. 04Report

Coding-agent conversation

Read context

I’m reviewing first-time password recovery. I’ll keep the scope and permissions explicit.

Investigate

Follow the weakest evidence link and record what remains blocked.

Show evidence

Here is the evidence trail to inspect: First-time task: recover access → inspect error, link wording and placement.

Report

The recovery link is hard to find after a failed sign-in. An AI review does not replace a human usability study.

CARBON

Example report

Illustration
Inspect the identity boundary
Inspect the identity boundary — TestBucks teaching screen

TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.

  1. User action
  2. Identity / validation
  3. Allowed outcome

Illustrated outcome

The recovery link is hard to find after a failed sign-in.

Evidence to inspect

First-time task: recover access → inspect error, link wording and placement.

Still untested / not established

An AI review does not replace a human usability study.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For first-time password recovery, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

First-time task: recover access → inspect error, link wording and placement. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

An AI review does not replace a human usability study.

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

  1. Replace first-time password recovery with a real feature, path or decision in your project.
  2. State the expected rule and its source. Include safe fixtures, constraints and a budget where appropriate.
  3. Ask for exact evidence and remaining gaps. Approve consequential actions separately.
/jay Review the /carbon-usability result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon-ux →/carbon-content →

Content checked against the local command definition: skills/carbon-usability/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.