What does "turn checks up to 11" mean?

It refers to aggressive defaults: strict linting, high coverage targets, and thorough test validation to quickly surface quality gaps.

Can thresholds be customized per project?

Yes. Coverage thresholds are configurable per project to align with specific quality goals.

Which tools are allowed and what are their roles?

Read inspects test files and reports; Bash runs tests, lint, and coverage; Grep finds untested code paths; Glob verifies test file naming; Write generates coverage reports and test suggestions.

test-enforcement

Scanned

npx machina-cli add skill a5c-ai/babysitter/test-enforcement --openclaw

Files (1)

SKILL.md

1.1 KB

Test Enforcement

Capabilities

Validates automated tests, checks coverage against thresholds, and reports quality metrics. Implements Maestro's "turn checks up to 11" philosophy with aggressive lint and test defaults.

Tool Use Instructions

Use Bash to run test suites, lint, and coverage commands
Use Read to examine test files and coverage reports
Use Grep to find untested code paths and missing test files
Use Glob to verify test file naming conventions
Use Write to generate coverage reports and test suggestions

Process Integration

Used across all Maestro processes for test verification
Used in maestro-maintenance.js (Coverage gap analysis)
Agents: Test Engineer, Coder (test writing)
Enforces: unit tests, integration tests, lint, format
Coverage thresholds configurable per project
"Turn checks up to 11" default behavior

Source

git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/maestro/skills/test-enforcement/SKILL.md

View on GitHub

Overview

Automates validation of automated tests, checks coverage against configurable thresholds, and reports quality metrics. It embodies Maestro's 'turn checks up to 11' philosophy with aggressive lint and test defaults and is used across Maestro processes, including maestro-maintenance.js for coverage gap analysis.

How This Skill Works

Technically, it uses Bash to run test suites, lint, and coverage commands; Read to examine test files and coverage reports; Grep to find untested code paths; Glob to verify test file naming conventions; Write to generate coverage reports and test suggestions.

When to Use It

Before merging code to ensure unit and integration tests exist and meet coverage thresholds.
In CI to enforce unit tests, integration tests, lint, and format across all projects.
For coverage gap analysis as part of maestro-maintenance.js workflows.
When adding a new feature that requires new tests and updated coverage.
When teams want to apply Maestro's aggressive default checks to surface quality gaps quickly.

Quick Start

Step 1: Run the enforcement with Bash to execute tests, lint, and coverage.
Step 2: Inspect test files and coverage reports using Read to locate gaps.
Step 3: Use Write to generate coverage reports and test suggestions, implement fixes, and re-run.

Best Practices

Configure coverage thresholds per project to reflect real goals.
Use Glob to enforce consistent test file naming conventions.
Run tests with coverage and lint checks in automated pipelines and record results with Write.
Regularly review coverage reports and test suggestions gathered by Read.
Keep test suites and lint rules aligned with the aggressive default behavior.

Example Use Cases

CI pipeline blocks a PR due to missing tests or insufficient coverage.
Coverage gap analysis in maestro-maintenance.js highlights untested branches.
Aggressive defaults surface flaky tests that require stabilization.
Test Engineer adds new tests to cover a recently implemented feature.
Maintenance run surfaces gaps and generates actionable fixes.

Frequently Asked Questions

Add this skill to your agents