Improving UX Through User Feedback
Improving UX Through User Feedback
ChatGPTClaudeGeminiβ Human review requiredπ Needs web accessπ Needs project contextπ MCP-ready
Health
100/100
β² 17
π 130 copies
Trigger Phrase
Use prompt: Improving UX Through User Feedback
Prompt
61 wordsYou are a UX researcher.
Input:
- Your role/context: {{TARGET_AUDIENCE}}
Improve a product's UI using feedback: 1) define 3-5 key personas 2) a structured way to gather feedback 3) synthesise findings into themes 4) prioritise issues (impact x effort) 5) 3 concrete UI changes.
Constraints:
- Mark assumptions to validate with real users; no invented results.
- Structured output.
Output: a feedback-driven UX improvement plan.
Input:
- Your role/context: {{TARGET_AUDIENCE}}
Improve a product's UI using feedback: 1) define 3-5 key personas 2) a structured way to gather feedback 3) synthesise findings into themes 4) prioritise issues (impact x effort) 5) 3 concrete UI changes.
Constraints:
- Mark assumptions to validate with real users; no invented results.
- Structured output.
Output: a feedback-driven UX improvement plan.
Before & After
β Without this prompt
Unstructured request with unclear constraints and inconsistent output.
β With this prompt
Reusable, testable prompt/skill with clear trigger, inputs, output format, guardrails, and pass criteria.
Install Instructions
Copy the prompt text. Paste into ChatGPT, Claude, Gemini, or any AI chat. Fill in bracketed placeholders with your details. Run and review output.
Test It
Test command:
Trigger with: 'Test the Improving UX Through User Feedback with this input: [provide a short real example]'. Confirm output is specific, structured, and useful.
Expected output:
Persona: new user. Feedback method: 5 usability tests. Theme: onboarding confusion.
Fix: add a 3-step guide.
Fix: add a 3-step guide.
Pass criteria:
- Output is specific to the input provided β not generic. Output follows the stated format and length. No invented statistics, facts, prices, or dates. Placeholders are not left unfilled.
β οΈ Guardrails
- Do not invent statistics, prices, laws, medical claims, or financial advice. Do not leave placeholders unfilled in output. Flag when inputs are too vague to produce a quality result β ask for clarification.
π Context File Tip
Brand brief, ICP/persona, offer details, source notes, policy constraints, examples of good/bad output.
β‘ Automation
π MCP-compatible
