evidence-verification

Collect and verify test, build, and code-quality evidence before task completion.

10|Updated Aug 26, 2025
One-click install
npx skills add https://github.com/ArieGoldkin/ai-agent-hub --skill evidence-verification
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evidence-verification
Source: https://github.com/ArieGoldkin/ai-agent-hub/tree/main/skills/evidence-verification
Command: npx skills add https://github.com/ArieGoldkin/ai-agent-hub --skill evidence-verification

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes examples (resource) and templates (resource) components.

What problem does it solve?

This skill prevents "hallucinations" or false claims of task completion by enforcing an evidence-based verification protocol. It ensures that every task is backed by verifiable proof, such as test results, build logs, and quality metrics, ensuring production-grade quality.

Core Features & Use Cases

  • Evidence Collection Protocol: Standardized steps to identify verification points, execute checks (tests, builds, linters), capture results, and store evidence.
  • Comprehensive Templates: Provides templates for documenting test, build, code quality, and deployment evidence for clear reporting.
  • Quality Standards: Defines minimum, production-grade, and gold-standard requirements for task completion, ensuring consistency.
  • Use Case: After implementing a new feature, use this skill to automatically run tests, build the project, and lint the code, then generate a combined evidence report to prove the task is truly complete and production-ready.

Quick Start

I've just finished implementing the user login feature. Run all necessary verification checks and generate a combined evidence report.

Frequently Asked Questions about evidence-verification

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

FAQPage Schema
How do I verify that a code implementation is production-ready?

Verification requires collecting evidence across tests, builds, and code quality checks. This skill standardizes that process by running all necessary checks, capturing results with exit codes and timestamps, and generating a combined evidence report that proves the task meets production-grade quality standards.

What evidence should I collect before marking a task complete?

Evidence-based task completion requires test results, build status, code-quality metrics, and deployment health checks. This skill provides templates and a protocol to systematically identify verification points, execute checks, capture outcomes, and store evidence in shared context for compliance.

Can I automate verification across testing, builds, and code quality?

Yes. This skill enforces an evidence collection protocol that runs tests, executes builds, and lints code automatically, then combines all results into a single report. It stores findings with exit codes and timestamps to create undeniable proof of task completion.

Why do task completion claims fail without verification?

Unverified claims lead to production issues because they lack backing evidence. This skill prevents that by requiring test results, build logs, and quality metrics before marking work complete, ensuring every deliverable is backed by documented proof aligned to production standards.

What's the difference between minimum and production-grade quality standards?

This skill defines tiered quality standards—minimum, production-grade, and gold-standard—so teams know what evidence is required at each level. Production-grade requires comprehensive test coverage, clean builds, and passing linters; the skill's templates clarify what each threshold demands.