Does this skill work with unit and integration tests?

Yes, it specifically requires full test command output showing zero failures before any 'tests pass' claim can be made.

What is the core principle of this skill?

The core principle is 'Evidence Before Claims.' It forbids the AI from stating a task is finished until it has executed a command that proves the success and analyzed the output.

Why is this skill necessary for AI development?

It prevents 'hallucinated success' where an AI might assume code works because it looks correct. It forces actual execution to maintain trust and prevent shipping broken code.

How does it handle bug fixes?

It mandates a Red-Green cycle: the AI must run a test that fails to reproduce the bug, apply the fix, and then run the test again to verify the pass.

Verification Before Completion

Name: Verification Before Completion
Author: cipherstash

bycipherstash

•

Security & Testing

Enforces a rigorous verification workflow requiring command-based evidence before any task is marked as complete or successful.

About

This skill establishes a strict 'Evidence First' protocol for Claude, preventing premature or false claims of task completion. By mandating the execution of fresh verification commands—such as test suites, linters, and build scripts—it ensures that every success claim is backed by real-time output. It eliminates guesswork and 'should-work' assertions, fostering a high-trust environment where code changes are proven correct through objective verification before being committed, pushed, or merged.

Key Features

Implements a multi-step Gate Function for identifying and executing validation commands
Enforces Red-Green-Refactor cycles for bug fixes and regression testing
Mandates fresh verification evidence before any completion claims
Prevents reliance on partial checks or previous successful runs
Blocks confidence-based language in favor of objective output reporting
4 GitHub stars

Use Cases

Ensuring full test suites pass before creating a Pull Request
Verifying bug fixes by demonstrating failure before and success after changes
Confirming build and linter stability before committing to a repository

About

Key Features

Implements a multi-step Gate Function for identifying and executing validation commands
Enforces Red-Green-Refactor cycles for bug fixes and regression testing
Mandates fresh verification evidence before any completion claims
Prevents reliance on partial checks or previous successful runs
Blocks confidence-based language in favor of objective output reporting
4 GitHub stars

Use Cases

Ensuring full test suites pass before creating a Pull Request
Verifying bug fixes by demonstrating failure before and success after changes
Confirming build and linter stability before committing to a repository