← ClaudeAtlas

prompt-ux-designlisted

Use when designing the user-facing prompt experience for any AI feature. Covers input design, suggestion patterns, history, feedback signals, and the interaction model between user intent and model execution.
RBraga01/builder-design · ★ 2 · Web & Frontend · score 75
Install: claude install-skill RBraga01/builder-design
# Prompt UX Design ## The Law ``` THE PROMPT INPUT IS THE PRODUCT INTERFACE FOR AN AI FEATURE. "It's just a text box" ships an input with no suggestions, no state feedback, and no token limit — users probe the model by trial and error until they give up. Input design + suggestion system + 6-state feedback loop + constraints IS a prompt UX. ``` ## When to Use Trigger when: - Designing the user-facing input for any AI feature - Adding a chat or conversational interface - Designing inline AI suggestions (autocomplete, copilot-style) - Designing an agent invocation interface (slash commands, @ mentions) - Reviewing whether an existing prompt input meets production standards ## When NOT to Use - API-only interfaces with no user-facing input - Admin / developer tools where power users are the only audience (simplify; don't over-design) ## The Five Prompt UX Dimensions ### 1 — Input Design The physical input must match the expected interaction pattern: | Pattern | Use When | Input Type | |---|---|---| | Short query | Single-question answers, search | Single-line input, auto-submit on Enter | | Multi-line | Document drafting, detailed prompts | Auto-resize textarea, Cmd+Enter to send | | Conversational | Chat, back-and-forth dialogue | Textarea + history above | | Command | Agent invocation, slash commands | Input with `@` / `/` trigger detection | | Constrained | Structured data entry, forms | Templated input with field hints | Never default to multi-line when single-line