SuperAPI AI Directory

21st-ui-explore

Design & creation

View repository

Updated 10-13 14:36

About this skill

Explore grounded UI directions

Create real choices without abandoning the project's visual identity.

Workflow

  1. Read .21st/design.json and the relevant product UI. If context is missing, run 21st init --design-context.

  2. Search 21st for multiple relevant references before generating:

    21st search "<interface and product context>" --context auto
    
  1. Define three named directions. Each direction must differ on at least two meaningful axes such as hierarchy, information density, navigation model, content emphasis, interaction pattern, or composition. Color-only variants do not count.

  2. Keep shared constraints fixed: real stack, tokens, brand assets, required content, accessibility, and responsive behavior.

  3. Create comparable previews. Check MCP get_usage.aiGenerationEnabled or run 21st usage and read the 21st AI generation line. CLI 1.17.1+ also supports 21st usage --json. Only when AI is explicitly enabled, use hosted generation with available AI credits:

    21st generate "<goal plus fixed constraints>" --context auto --variants 3
    

    Otherwise, implement the previews with your own coding agent, grounded in 21st search and 21st get (MCP: search and get_component). Do not call or suggest hosted generate or iterate_generation without AI access.

  4. Present the options together when the host supports a picker. Otherwise give each option a preview/deep link and a compact comparison.

  5. Recommend one direction with concrete tradeoffs, but let the user choose.

  6. After selection, remove abandoned local variants and record the decision in .21st/design.json.

Direction contract

For every direction provide:

  • a short, descriptive name;
  • the core idea and intended user effect;
  • the 21st/project references used;
  • what stays consistent with the project;
  • two or more meaningful differences;
  • accessibility or responsive risks;
  • the best-fit scenario.

Do not generate random style mutations. Every difference must support a product or usability hypothesis that a user can evaluate.