agent evaluation skill risk: low
Nielsen Heuristics Mobile UX Auditor
Audits screens or flows against Nielsen's 10 heuristics plus mobile UX checks for reachability, touch ergonomics, and thumb-friendly placement, then returns a prioritized issue lis…
SKILL 1 file
SKILL.md
--- name: antigravity-awesome-skills-ux-audit-159daee4 description: "Audit screens against Nielsen's heuristics and mobile UX best practices using the StyleSeed Toss design language as the implementation context." --- # UX Audit ## Overview Part of [StyleSeed](https://github.com/bitjaru/styleseed), this skill audits usability rather than just visuals. It uses Nielsen's 10 heuristics plus modern mobile UX expectations to find issues in navigation, feedback, recovery, hierarchy, and cognitive load. ## When to Use - Use when a screen feels awkward even though the code and styling seem correct - Use when evaluating a flow before or after implementation - Use when reviewing a mobile-first product for usability regressions - Use when you want findings framed as user experience problems with remediation ## Audit Framework Review the target against: - visibility of system status - match between system and real-world language - user control and freedom - consistency and standards - error prevention - recognition rather than recall - flexibility and efficiency - aesthetic and minimalist design - recovery from errors - help, onboarding, and empty-state guidance Add mobile-specific checks for reachability, touch ergonomics, input burden, and thumb-friendly action placement. ## Output Return: 1. A prioritized issue list 2. The heuristic violated by each issue 3. Why the issue matters to real users 4. Specific remediation suggestions for the page, component, or flow ## Best Practices - Judge the experience from the user's point of view, not the implementer's - Separate high-severity flow blockers from minor polish issues - Include recovery and state-management guidance, not only layout comments - Tie recommendations back to concrete UI changes ## Additional Resources - [StyleSeed repository](https://github.com/bitjaru/styleseed) - [Source skill](https://github.com/bitjaru/styleseed/blob/main/seeds/toss/.claude/skills/ux-audit/SKILL.md) ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
REQUIRED CONTEXT
- target screen, component, or flow to audit
OPTIONAL CONTEXT
- StyleSeed Toss design language context
- mobile-first product details
ROLES & RULES
- Judge the experience from the user's point of view, not the implementer's
- Separate high-severity flow blockers from minor polish issues
- Include recovery and state-management guidance, not only layout comments
- Tie recommendations back to concrete UI changes
- Use this skill only when the task clearly matches the scope described above
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing
EXPECTED OUTPUT
- Format
- structured_report
- Schema
- numbered_list · A prioritized issue list, The heuristic violated by each issue, Why the issue matters to real users, Specific remediation suggestions for the page, component, or flow
- Constraints
-
- Return a prioritized issue list
- For each issue state the heuristic violated
- Explain why the issue matters to real users
- Provide specific remediation suggestions tied to UI changes
SUCCESS CRITERIA
- Judge the experience from the user's point of view, not the implementer's
- Separate high-severity flow blockers from minor polish issues
- Include recovery and state-management guidance, not only layout comments
- Tie recommendations back to concrete UI changes
CAVEATS
- Missing context
-
- How the screen or flow under review will be provided as input (description, code, screenshot, etc.)
- Desired output length or formatting constraints
- Ambiguities
-
- StyleSeed Toss design language is referenced but not defined or summarized inside the prompt
QUALITY
- OVERALL
- 0.79
- CLARITY
- 0.88
- SPECIFICITY
- 0.78
- REUSABILITY
- 0.82
- COMPLETENESS
- 0.72
IMPROVEMENT SUGGESTIONS
- Add an explicit 'Input' section describing the expected form of the artifact to be audited
- Include a short example of the desired output structure
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Advanced LLM-as-Judge Evaluation agent evaluation
- Context Degradation Pattern Diagnoser agent evaluation
- Agent Evaluation Framework Builder agent evaluation
- LLM Experiment Integrity Auditor agent evaluation
- Experiment Results Claim Evaluation Gate agent evaluation
- NVIDIA Cosmos Policy LIBERO RoboCasa Evaluator agent evaluation
- Nielsen Heuristics Mobile UX Auditor agent evaluation
- Scientific Manuscript Peer Reviewer agent evaluation
- UX/UI Principles Agent Skills agent evaluation
- Nielsen Heuristics Mobile UX Auditor agent evaluation
- ScholarEval Academic Research Evaluator agent evaluation
- AI Agent Reasoning Trace Optimizer agent evaluation
- Experiment Integrity Cross-Model Auditor agent evaluation
- Research Result-to-Claim Evaluator agent evaluation
- Web Interface Guidelines File Reviewer agent evaluation
- UX/UI Principles Interface Evaluator agent evaluation
- Comprehensive Final Review Checklist Assessor agent evaluation
- UX/UI Principles Agent Skills agent evaluation
- Conductor Project Artifacts Validator agent evaluation
- Comprehensive Codebase Bug Analysis and Fixer agent analysis
- Xcode MCP Usage Guidelines for Agents agent tool_use
- Xcode MCP Usage Guidelines agent tool_use
- Rapid App MVP Prototyper agent coding
- Local Documentation Online Sync Automator agent operations
- HashiCorp Packer Golden Image Expert agent operations