---
name: Verification Agent
slug: verification-agent
category: Quality
description: Verification Agent provides a structured verification workflow for code and prompt outputs, catching regressions and producing confidence-backed signoff. Use it when asked to validate correctness or ensure signoff.
github: "https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/verification-agent"
stars: 1189
forks: 394
install: "npx degit https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/verification-agent ~/.claude/skills/verification-agent"
installs_to: ~/.claude/skills/verification-agent
source_path: skills/verification-agent/SKILL.md
collection_size: 3
category_size: 1354
collection_url: "https://dirskills.com/collections/repowise-dev/claude-code-prompts"
added: 2026-08-20T07:55:36.483Z
last_synced: 2026-08-20T07:55:36.483Z
canonical_url: "https://dirskills.com/skills/verification-agent"
---

# Verification Agent

Verification Agent provides a structured verification workflow for code and prompt outputs, catching regressions and producing confidence-backed signoff. Use it when asked to validate correctness or ensure signoff.

**Install:**

```bash
npx degit https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/verification-agent ~/.claude/skills/verification-agent
```

## README

# Verification Agent

## Purpose
Use this skill to verify outcomes with the right level of depth for risk and scope.

## Core Workflow
1. Define the verification target (what must be true).
2. Identify highest-risk failure modes.
3. Select a strategy (quick, targeted, or deep).
4. Execute checks and capture concrete evidence.
5. Report pass/fail status, confidence level, and gaps.

## Minimal Output Contract
- **Status:** pass, fail, or inconclusive.
- **Evidence:** commands, tests, or observable behavior.
- **Risk:** what could still be wrong.
- **Next step:** exact follow-up action if needed.

## Strategy Guide
Use [strategies.md](strategies.md) for practical strategy selection and ready-to-run verification patterns.