impl-validator

Validate implementation artifacts against stated goals with PASS/WARN/FAIL verdicts.

4|Updated May 9, 2026
One-click install
npx skills add https://github.com/itsmarsss/memento --skill impl-validator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: impl-validator
Source: https://github.com/itsmarsss/memento/tree/main/obsidian-wiki/.cursor/skills/impl-validator
Command: npx skills add https://github.com/itsmarsss/memento --skill impl-validator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Impl-validator prevents incorrect or incomplete work from being presented by checking whether an implementation matches its stated goal.

Core Features & Use Cases

  • Goal-to-output validation: Reframes the intended goal and verifies that produced artifacts actually satisfy it.
  • Artifact and check auditing: Checks existence, completeness, correctness, and project conventions while evaluating each requested check explicitly.
  • Structured verdict reporting: Returns a clear pass/warn/fail report with actionable issues and non-blocking notes.

Quick Start

Tell impl-validator what you just did and what result you expected, and it will return a structured report with any FAIL/WARN issues to fix.

Frequently Asked Questions about impl-validator

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

FAQPage Schema
How do I validate that my code implementation matches the intended goal?

Validate implementations by providing the intended goal and produced artifacts to run existence, completeness, correctness, and convention checks, returning a structured PASS/WARN/FAIL verdict with actionable issues.

What is artifact checking in code review and how does it work?

Artifact checking audits produced work for existence, completeness, correctness, and project conventions. It evaluates explicit checks against your stated goal to ensure the implementation matches the expected result.

How do I run a self-check on my implementation after completing a task?

Run a self-check by telling the validator what you just did and what result you expected. It reviews the provided artifacts and returns a structured report with any FAIL or WARN issues to fix.

Does implementation validation work for both automated agents and direct user review?

Implementation validation applies to both subagent self-checking and direct user validation after work has been performed. It parses a check block or infers goals and artifacts to evaluate the output.

What is the best way to catch incomplete work before presenting it?

The best way to catch incomplete work is goal-to-output validation, which prevents incorrect results by explicitly auditing produced artifacts against stated goals and returning actionable PASS/WARN/FAIL reports.

What does a structured pass warn fail verdict report include?

A structured PASS/WARN/FAIL verdict report includes actionable issues and non-blocking notes. It evaluates explicit checks on your artifacts to clearly identify what needs fixing before presenting the work.