verification-before-completion

Run verification commands and confirm output before claiming task completion.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/rahulsc/forge --skill verification-before-completion-rahulsc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/rahulsc/forge/tree/main/skills/verification-before-completion
Command: npx skills add https://github.com/rahulsc/forge --skill verification-before-completion-rahulsc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill prevents premature claims of task completion or success by enforcing a strict, evidence-based verification process before any assertions are made.

Core Features & Use Cases

  • Mandatory Verification: Ensures that claims of passing tests, successful builds, or completed tasks are always backed by fresh, verifiable evidence.
  • Risk-Scaled Evidence: Adapts evidence requirements based on the task's risk tier (Minimal, Standard, Elevated, Critical).
  • Use Case: Before committing code for a critical feature, this Skill ensures all tests have passed, the build is clean, and acceptance criteria are met, preventing the introduction of regressions or incomplete work.

Quick Start

Run the verification command to confirm the build passes before claiming the task is complete.

Frequently Asked Questions about verification-before-completion

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

FAQPage Schema
How do I enforce evidence-based verification before claiming an AI task is complete?

You can enforce evidence-based verification by mandating that specific verification commands are executed and their output confirmed before any task completion claims are made. This ensures all assertions are backed by fresh, verifiable data.

What is risk-scaled evidence in software quality assurance?

Risk-scaled evidence adapts verification requirements based on a task's risk tier, ranging from Minimal to Critical. Higher risk tasks demand more rigorous proof of passing tests and clean builds before any success is claimed.

How do I prevent false assertions of passing tests and successful builds in automated code review?

Preventing false assertions involves enforcing a strict verification process that requires running specific commands and confirming their output. This stops premature claims of task completion by ensuring all success statements are backed by concrete data.

Can I scale verification requirements for critical features versus minimal risk tasks?

Yes, you can scale verification requirements by assigning risk tiers like Minimal, Standard, Elevated, or Critical. This scales the evidence needed, ensuring critical features require more comprehensive test and build verification than minimal risk tasks.

Do I need to run verification commands manually to confirm a clean build before committing code?

The verification process mandates running verification commands to confirm the build passes and acceptance criteria are met. This ensures tests pass and builds are clean, preventing the introduction of regressions or incomplete work before committing code.