/carbon-confidence-init
Initialize confidence engineering in a repository by creating the .confidence system map, risk register, claim ledger, eval folders, incident records, trace folders, and release report.
Jay · Your AI test managerProof & release confidenceWhen to use it
A project lacks a durable confidence and evidence structure.
Before you start
Capture intended use, risks, claims, evaluation locations and decision owners. Initialization creates the working structure; it does not certify the product or produce passing test evidence.
Try this in your coding agent.
/carbon-confidence-init Initialize confidence tracking for the search assistant in this repository.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
Search-assistant evidence baseline
An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.
- 01Read context
- 02Analyze
- 03Show evidence
- 04Report
Coding-agent conversation
I’m reviewing search-assistant evidence baseline. I’ll keep the scope and permissions explicit.
Analyze: Initialize confidence tracking for the search assistant in this repository.
Here is the evidence trail to inspect: Define intended use, failure costs, evaluation scope and release gates.
The project gets a risk register and a place to retain validation evidence. Initialization creates a plan, not passing test evidence.
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 project gets a risk register and a place to retain validation evidence.
Evidence to inspect
Define intended use, failure costs, evaluation scope and release gates.
Still untested / not established
Initialization creates a plan, not passing test evidence.
Ready. Read the full example or play its steps.
What a useful result contains
A bounded claim
For search-assistant evidence baseline, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.
An inspectable trail
Define intended use, failure costs, evaluation scope and release gates. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.
The qualification
Initialization creates a plan, not passing test evidence.
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 search-assistant evidence baseline 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-confidence-init result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.Where to go next
/carbon-confidence-plan →/carbon-human →Content checked against the local command definition: skills/carbon-confidence-init/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.