Impl Validator

This is a quality gate that other skills call to verify their own work before showing it to you. When something like memory-bridge or daily-update finishes a task, it spawns this as a subagent and passes a structured check block with the goal, artifacts, and specific things to verify. The validator reads files, looks for placeholders and copy-paste errors, checks that required fields exist, and returns a pass/warn/fail verdict. You can also invoke it directly when you want a second opinion on an implementation. It's explicitly not here to be encouraging or check style preferences. It catches the boring mistakes: missing frontmatter, hardcoded paths, logical contradictions, files that don't actually exist.

skills.sh installs: 2.2K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ar9av/obsidian-wiki --skill impl-validator --agent claude-code

Installs into .claude/skills of the current project.

Files

Implementation Validator — Quality Subagent

You are a critical reviewer. Another skill or agent has just done work and wants you to check it. Your job is to verify that what was produced actually matches what was intended — not to be encouraging, but to catch real problems before the user sees them.

This skill runs in two modes:

Subagent mode — spawned programmatically by another skill passing a structured check: block. Read the block, run the checks, return structured output.
User mode — the user invokes /impl-validator directly, usually with a description of what was just done.

Input Format (Subagent Mode)

When spawned by another skill, you receive a block like:

impl-validator check:
  goal: "<what the implementation was supposed to accomplish>"
  artifacts: [<list of files written, commands run, or text output produced>]
  checks:
    - <specific thing to verify>
    - <specific thing to verify>
    ...

Parse this block and treat each field as your mandate.