verification-before-completion

Require fresh command execution and output verification before task completion claims.

Updated May 5, 2026

Search Tags:#testing #quality assurance #best practices #verification #reliability

Ready to run

npx skills add https://github.com/iani-kuli/harness_bro --skill verification-before-completion-iani-kuli

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/iani-kuli/harness_bro/tree/main/.claude/skills/curated/verification-before-completion
Command: npx skills add https://github.com/iani-kuli/harness_bro --skill verification-before-completion-iani-kuli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents the common AI pitfall of claiming work is complete or successful without actual, verifiable evidence, ensuring high-quality and reliable output.

Core Features & Use Cases

Verification Gate: Mandates the execution of specific commands to prove claims before they are made.
Evidence-Based Reporting: Ensures that every claim of success is backed by fresh, objective output.
Use Case: Before telling a user that a bug is fixed or a test suite is passing, the agent must run the relevant test command and confirm the output matches the expected success criteria.

Quick Start

Apply the verification-before-completion protocol to your current task by running the necessary test commands and confirming the output before reporting any progress.

Frequently Asked Questions about verification-before-completion

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

FAQPage Schema

How do I prevent AI from claiming a task is complete without running tests?▼

To prevent false completion claims, enforce a verification protocol requiring fresh execution of validation commands and independent confirmation of exit codes before any status assertion is made.

What is evidence-based work verification in agentic workflows?▼

Evidence-based work verification is a strict protocol mandating that AI agents run validation commands and confirm the output matches expected success criteria before reporting progress to the user.

How do I verify test suite execution before reporting a bug fix?▼

Verify a bug fix by applying a verification gate that requires running the relevant test command, checking the exit code, and confirming the fresh output matches expected criteria before asserting success.

Does evidence-based verification work for general software development tasks?▼

Yes, evidence-based verification applies to software development, testing, and agentic workflows where accuracy and reliability are critical, ensuring every success claim is backed by objective output.

What is the best way to ensure reliability in automated quality assurance reporting?▼

The best way to ensure reliability is mandating evidence-based reporting, which prevents unverified success assertions by requiring the execution of specific commands to prove claims before they are made.