사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/21st-dev/skill --skill 21st-ui-explore시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Explore grounded UI directions
Create real choices without abandoning the project's visual identity.
Workflow
- Read
.21st/design.jsonand the relevant product UI. If context is missing,
run 21st init --design-context.
- Search 21st for multiple relevant references before generating:
21st search "<interface and product context>" --context auto- 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.
- Keep shared constraints fixed: real stack, tokens, brand assets, required
content, accessibility, and responsive behavior.
- Create comparable previews. Check MCP
get_usage.aiGenerationEnabledor
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 3Otherwise, 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.
- Present the options together when the host supports a picker. Otherwise give
each option a preview/deep link and a compact comparison.
- Recommend one direction with concrete tradeoffs, but let the user choose.
- 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.




