CARBON — Engineering ConfidenceUser Guide
CHAPTER 03 / 60 Core + Pro

/full

Run CARBON's comprehensive, resumable testing campaign with Jay, parallel specialists, broad risk-ranked coverage, verified and triaged findings, and a live report.

Jay · Your AI test managerStart & investigate

When to use it

You need a coordinated campaign rather than a bounded first look.

Before you start

Identify the project and optional time limit. Two separate confirmations precede testing. Check the campaign checkpoints, blocked environments and cumulative evidence, then resume deliberately if interrupted.

Try this in your coding agent.

/full Run a testing campaign for the cart and checkout flows in this project.

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

Cart-to-checkout campaign

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

  1. 01Scope
  2. 02Map journeys
  3. 03Assign agents
  4. 04Execute
  5. 05Regressions
  6. 06Report

Coding-agent conversation

Scope

I’m reviewing cart-to-checkout campaign. I’ll keep the scope and permissions explicit.

Map journeys

I’m mapping menu → customization → cart → checkout → confirmation, including recovery paths.

Assign agents

Priya handles cart state, Hassan follows checkout, and Arjun compares totals across boundaries.

Execute

The sample journey changes a quantity, removes a discounted item, and retries the checkout boundary.

Regressions

Here is the evidence trail to inspect: Risk map → cart checks → browser journey → reproduction → report.

Report

The campaign links a cart defect to a proposed regression test. Unavailable browsers remain marked untested.

CARBON

Example report

Illustration
Follow the cart state
Follow the cart state — TestBucks teaching screen

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

  1. Cart input
  2. Totals & state
  3. Checkout evidence

Illustrated outcome

The campaign links a cart defect to a proposed regression test.

Evidence to inspect

Risk map → cart checks → browser journey → reproduction → report.

Still untested / not established

Unavailable browsers remain marked untested.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For cart-to-checkout campaign, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Risk map → cart checks → browser journey → reproduction → report. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

Unavailable browsers remain marked untested.

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 cart-to-checkout campaign 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 /full result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon-full-report →/carbon-tests →

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