visual-qaRun an evidence-driven UI review committee
Install via ClawdBot CLI:
clawdbot install kbo4sho/visual-qaGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains telemetry, tracking, or analytics calls not mentioned in documentation
pixel (Calls external URL not in known-safe list
http://localhost:3000AI Analysis
The skill's external calls (localhost:3000) are for local development testing, consistent with its stated purpose of visual regression testing. There is no evidence of credential harvesting, data exfiltration, or obfuscated malicious behavior. The 'pixel' reference appears to be a truncated description of pixel-level image diffing, not telemetry injection.
Audited Apr 17, 2026 · audit v1.0
Generated May 23, 2026
An online retailer uses Visual QA to gate deployments of UI changes to their product pages. Before any merge, the pipeline captures screenshots of key pages (home, product, cart) and compares them against approved baselines, blocking deployment if unintended visual differences are detected. This ensures customers always see a consistent and error-free shopping experience.
A SaaS company integrates Visual QA into their CI pipeline to catch visual regressions in their analytics dashboard after each commit. The tool captures screenshots at multiple viewports and provides diff images for quick developer review, preventing broken layouts or misaligned charts from reaching production. This maintains trust with users relying on accurate data visualization.
A design team maintains a component library with Visual QA to ensure updates do not break consumer applications. They capture baselines of all components in multiple states (hover, active, error) and run the gate script after any change. If a button color shift or padding change is unintended, the pipeline fails, prompting immediate review.
A digital agency uses Visual QA to verify that responsive layouts render correctly across Chrome, Firefox, and Safari. They capture screenshots at desktop, tablet, and mobile viewports for each browser and compare against baselines. This catches browser-specific rendering bugs before client demos.
A healthcare startup employs Visual QA to ensure their patient portal UI changes do not inadvertently affect accessibility. After each iteration, they compare screenshots of the portal against baselines, focusing on contrast, focus indicators, and tab order. This helps maintain WCAG compliance without manual re-inspection.
Offer a free tier for small projects with basic features (single URL, threshold only) and premium plans for teams requiring config files, multi-viewport, and advanced reporting.
Provide a hosted Visual QA service with dedicated support, custom integrations, and unlimited screenshot storage. Agencies pay per project or monthly retainer to outsource visual regression testing.
Keep the core scripts open source with a permissive license to drive adoption, then sell enterprise support contracts including priority bug fixes, custom integrations, and on-premises deployment assistance.
💬 Integration Tip
For CI integration, use the all-in-one gate.py script which returns a simple exit code—add a step in your pipeline to fail the build if exit code is 1.
Scored May 23, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.