skills.rest
gamingshadow608-star
gamingshadow608-starCOMMUNITY
Explore all skills by this author →
GitHub

testing-and-evals

Design and execute tests, evaluations, and runtime checks for code, prompts, and skills.

1|Updated Mar 12, 2026
Search Tags:#testing#quality assurance#code review#CI/CD#verification#evaluation
One-click install
npx skills add https://github.com/gamingshadow608-star/agent-building-skills --skill testing-and-evals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: testing-and-evals
Source: https://github.com/gamingshadow608-star/agent-building-skills/tree/main/testing-and-evals
Command: npx skills add https://github.com/gamingshadow608-star/agent-building-skills --skill testing-and-evals

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill ensures that all code, prompts, and skills meet mandatory quality and security standards by enforcing a rigorous testing and evaluation process before deployment.

Core Features & Use Cases

  • Mandatory Verification Gate: Acts as a critical checkpoint for any changes, preventing regressions and ensuring stability.
  • Automated Testing & Evals: Derives and runs repo-native verification commands, including unit tests, integration tests, and model-based evaluations.
  • Use Case: When a new feature is added to a codebase, this Skill will automatically run all relevant tests and evaluations, ensuring the new code doesn't break existing functionality and meets performance benchmarks before it can be merged.

Quick Start

Use the testing-and-evals skill to run all repo-native verification commands for the recent changes.

Frequently Asked Questions about testing-and-evals

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is a mandatory verification gate for code and prompts?▼

A mandatory verification gate acts as a critical checkpoint to run tests, evaluations, and runtime checks, preventing regressions and ensuring code quality before deployment.

How do I run automated tests and evaluations for recent codebase changes?▼

You can run automated tests by deriving and executing repo-native verification commands, which enforces a write-run-fix-rerun loop to validate recent changes against performance benchmarks.

How does a write-run-fix-rerun loop improve code quality?▼

The write-run-fix-rerun loop improves code quality by iteratively executing tests and evaluations, identifying failures, enforcing fixes, and rerunning verification until stability is achieved.

When do I need model-based evaluations and runtime checks for my code?▼

You need model-based evaluations and runtime checks when adding new features, ensuring new code does not break existing functionality and meets required performance benchmarks before merging.

Does verification testing require recording evidence before security review?▼

Yes, verification testing requires recording evidence from startup checks and eval harnesses before security review to ensure all code and prompts meet mandatory quality standards.

Related Skills

Explore More Software Engineering Skills→
paulmalmquistpaulmalmquist

winston-session-bootstrap

Initialize Winston repo-local sessions by loading startup context files and confirming repo root.

Community
Basic
jamesjlundinjamesjlundin
32

deploy-helper

Run pre-deploy checks and generate a deployment readiness report.

Community
Advanced
J03Fr0stJ03Fr0st

ci-cd-and-automation

Automate CI/CD pipeline setup with GitHub Actions and quality gates.

Community
Advanced
CDO-07-NewCDO-07-New

eval-harness

Define repeatable evaluation harnesses for Claude Code task outcomes.

Official
Intermediate