Visual Verdict
技能 已验证 活跃Structured visual QA verdict for screenshot-to-reference comparisons
To automate visual quality assurance by providing a strict, deterministic verdict for generated UI screenshots against reference images, enabling iterative refinement of visual fidelity.
功能
- Structured visual QA verdict generation
- Screenshot-to-reference image comparison
- Concrete difference identification
- Actionable editing suggestions
- Pass/fail threshold enforcement
使用场景
- Verifying UI generated by AI against design mockups
- Ensuring visual consistency across different development iterations
- Automating visual regression testing
- Providing deterministic feedback for UI refinement
非目标
- Performing actual image editing or code generation
- Providing functional or accessibility testing
- Interpreting non-visual aspects of UI components
工作流
- User provides reference images and a generated screenshot.
- Skill compares the generated screenshot against references.
- Skill returns a JSON verdict including score, differences, suggestions, and reasoning.
- User reviews the verdict and iterates on edits if the score is below the threshold.
先决条件
- Claude Code CLI
- Reference images and generated screenshot
安装
请先添加 Marketplace
/plugin marketplace add Yeachan-Heo/oh-my-claudecode/plugin install oh-my-claudecode@omc质量评分
已验证类似扩展
Telegram Crabbox E2e Proof
100Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
Qa
100Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
UltraQA
99QA cycling workflow - test, verify, fix, repeat until goal met
Dogfood
99系统地探索和测试 Web 应用程序以发现 bug、用户体验问题和其他问题。在被要求“内部测试”（dogfood）、“QA”、“探索性测试”、“查找问题”、“bug 搜寻”、“测试此应用/网站/平台”或审查 Web 应用程序质量时使用。会生成结构化报告，并附带完整的重现证据——每个问题的分步截图、重现视频和详细的重现步骤——以便将发现直接移交给负责的团队。
Grammar Check
99Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.
Acceptance Criteria Generator
99Generates structured Given/When/Then acceptance criteria for a user story or feature slice. Use when translating product requirements into testable scenarios that cover the happy path, edge cases, error states, and non-functional expectations for engineering handoff and QA.