Reality Checker

Validates deployment readiness by cross-checking QA claims against Playwright screenshot evidence.

2|Updated May 21, 2026
One-click install
npx skills add https://github.com/tcvdog/agency-agents-hermes --skill reality-checker-tcvdog
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Reality Checker
Source: https://github.com/tcvdog/agency-agents-hermes/tree/main/testing/reality-checker
Command: npx skills add https://github.com/tcvdog/agency-agents-hermes --skill reality-checker-tcvdog

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents premature production approvals by requiring concrete visual and performance evidence before certifying a web project as ready, replacing inflated ratings with honest assessments. ## Core Features & Use Cases - Evidence-Based Certification: Runs reality-check commands and Playwright screenshot captures to verify what was actually built versus what was claimed. - QA Cross-Validation: Compares previous QA findings against automated screenshots and test-results.json to confirm or challenge earlier assessments. - End-to-End Journey Testing: Analyzes responsive, navigation, and form interaction screenshots across desktop, tablet, and mobile viewports. - Use Case: After a QA agent declares a landing page "production ready", run this Skill to capture device screenshots, verify specification compliance, and issue a realistic NEEDS WORK or READY verdict with required fixes. ## Quick Start Use the reality-checker skill to validate whether the website at localhost:8000 is genuinely production ready with screenshot evidence.

Frequently Asked Questions about Reality Checker

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

FAQPage Schema
How do I verify a website is production ready before deployment?▼

Run reality-check commands to inspect built files, capture Playwright screenshots across devices, and review test-results.json for load times and errors. Certify readiness only when visual evidence matches specification requirements.

How to cross-validate QA findings with automated screenshots?▼

Compare the QA agent's reported issues against responsive-desktop, responsive-tablet, and responsive-mobile screenshots plus interaction before/after images. Confirm or challenge the QA assessment based on what the automated evidence actually shows.

Does this testing approach work with Laravel and static HTML sites?▼

Yes, the reality-check commands handle both stacks by checking resources/views/ for Laravel blade templates or root-level HTML files for simple sites. Playwright capture works against any local server URL.

What triggers an automatic fail in integration testing?▼

Automatic fails include claims of zero issues, perfect scores without evidence, premium design claims for basic implementations, broken user journeys in screenshots, and load times exceeding three seconds.

Why default to NEEDS WORK instead of production ready?▼

First implementations typically require two to three revision cycles, so C+/B- ratings are normal. Defaulting to NEEDS WORK ensures only systems with overwhelming demonstrated evidence receive production certification.