/carbon-more
Continue a prior broad CARBON run with the next highest-value deferred candidates without repeating the initial pass.
Jay · Your AI test managerStart & investigateWhen to use it
A previous assessment left useful checks unexecuted.
Before you start
Keep the earlier run and project revision available. Ask for the next highest-risk gap rather than repeating already-covered happy paths. A prior pass does not automatically apply to changed code.
Try this in your coding agent.
/carbon-more Continue the last checkout assessment with the next highest-risk gap.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
Next gap in checkout evidence
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 next gap in checkout evidence. 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: Prior report: quantity covered; refresh untested → add item → refresh → inspect cart.
The next investigation follows the uncovered refresh path. Prior findings are reused, not counted as new tests.
Example report
Illustration
TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.
- Query intent
- Catalog / processing
- Visible result
Illustrated outcome
The next investigation follows the uncovered refresh path.
Evidence to inspect
Prior report: quantity covered; refresh untested → add item → refresh → inspect cart.
Still untested / not established
Prior findings are reused, not counted as new tests.
Ready. Read the full example or play its steps.
What a useful result contains
A bounded claim
For next gap in checkout evidence, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.
An inspectable trail
Prior report: quantity covered; refresh untested → add item → refresh → inspect cart. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.
The qualification
Prior findings are reused, not counted as new tests.
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 next gap in checkout evidence 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-more result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.Where to go next
/carbon-test →/carbon-full-report →Content checked against the local command definition: skills/carbon-more/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.