/visual-review

Use to inspect a web UI with browser evidence before marking work complete.

Boost this command

yeaight7@yeaight7

GitHub

From plugin

agent-powerups

654 skills46 agents54 commands

Install

> /plugin marketplace add yeaight7/agent-powerups

How it fires

How this command gets triggered: by you, by Claude, or both.

Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/visual-review

Context preview

What this command does when you run it.

Use to inspect a web UI with browser evidence before marking work complete.

Command definition

visual-review.md

visual-review

Use to inspect a web UI with browser evidence before marking work complete.

Steps:

1. Confirm the dev server is running and Playwright MCP or equivalent is available. 2. Navigate to the target URL. Take a baseline screenshot and accessibility snapshot. 3. Check console errors on load. Flag any uncaught errors before continuing. 4. Exercise the target interaction with semantic selectors (role → text → label → testId → CSS). 5. Capture a screenshot after each significant state change. 6. Check network: did the expected API call fire and return a success status? 7. Check accessibility: are new elements keyboard-reachable and correctly labelled? 8. Report per scenario: expected, observed, evidence, PASS/FAIL/NEEDS_REVIEW.

Do not automate against production environments without explicit user approval.

Read it on GitHub ↗

Ships withagent-powerups

Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more

Get the whole plugin

Stats

Python TypeScript JavaScript Node HTML

+7 tags

SQL Git GitHub Markdown Anthropic Gemini MCP

Stars

Forks

Active

Maintenance

TypeScript

Language

Apache-2.0