Communitygithub.com

leonxlnx/taste-skill

기본 LLM 출력 잘림 동작을 재정의합니다. 완전한 코드 생성을 강제하고, 플레이스홀더 패턴을 금지하며, 토큰 제한 분할을 깔끔하게 처리합니다. 완전하고 요약되지 않은 출력이 필요한 모든 작업에 적용하세요.

taste-skill란 무엇인가요?

이 스킬은 LLM의 기본 출력 잘림 동작을 대체하여, 모든 작업에서 완전하고 중단 없는 출력을 보장합니다. '완전성'을 최우선으로 하여 부분적인 출력을 버그로 간주하며, 사용자가 요청한 전체 파일, 5개의 컴포넌트 등 모든 요청 항목을 예외 없이 완전히 제공하도록 강제합니다. `// ...`, `// TODO`, `// rest of code` 등 코드를 생략하는 모든 플레이스홀더 패턴을 하드 실패로 금지하고, 프롤로그에서도 축약 표현을 사용할 수 없습니다. 또한, 긴 출력 시 토큰 제한에 도달하면 압축하거나 건너뛰지 않고 깔끔한 중단점에서 `[PAUSED — X of Y complete. Send "continue" to resume from: next section name]` 형식으로 일시 중지하고, 'continue' 명령으로 이어서 정확히 중단된 지점부터 재개합니다. Claude Code, Cursor, Codex 등 모든 LLM 기반 코딩 도우미에서 사용할 수 있으며, 프로덕션 수준의 완전한 코드 생성이 필요한 시나리오에 특히 유용합니다.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/leonxlnx/taste-skill/tree/main/skills/output-skill

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

전체 출력 강제

기본 원칙

모든 작업을 프로덕션에 중요한 것으로 취급하십시오. 부분 출력은 잘못된 출력입니다. 간결함이 아닌 완전함을 최적화하십시오. 사용자가 전체 파일을 요청하면 전체 파일을 제공하십시오. 사용자가 5개의 컴포넌트를 요청하면 5개의 컴포넌트를 제공하십시오. 예외는 없습니다.

금지된 출력 패턴

다음 패턴은 하드 실패입니다. 절대 생성하지 마십시오.

코드 블록 내: // ..., // rest of code, // implement here, // TODO, /* ... */, // similar to above, // continue pattern, // add more as needed, 생략된 코드를 대신하는 단순 ...

산문 내: "Let me know if you want me to continue", "I can provide more details if needed", "for brevity", "the rest follows the same pattern", "similarly for the remaining", "and so on" (실제 내용을 대체하는 경우), "I'll leave that as an exercise"

구조적 지름길: 요청이 전체 구현이었는데 스켈레톤만 출력. 중간을 건너뛰고 첫 번째와 마지막 섹션만 보여줌. 반복되는 로직을 하나의 예제와 설명으로 대체. 코드가 수행해야 할 작업을 설명하는 대신 실제 코드를 작성하지 않음.

실행 프로세스

  1. 범위 파악 — 전체 요청을 읽습니다. 예상되는 고유한 산출물(파일, 함수, 섹션, 답변)이 몇 개인지 셉니다. 그 숫자를 고정합니다.
  2. 구축 — 모든 산출물을 완전히 생성합니다. 부분 초안이나 "이것은 나중에 확장할 수 있습니다"와 같은 것은 없습니다.
  3. 교차 확인 — 출력하기 전에 원래 요청을 다시 읽습니다. 산출물 수를 범위 수와 비교합니다. 누락된 항목이 있으면 응답하기 전에 추가합니다.

긴 출력 처리

응답이 토큰 제한에 가까워지면:

  • 남은 섹션을 압축하여 집어넣지 마십시오.
  • 결론으로 건너뛰지 마십시오.
  • 깔끔한 중단점(함수 끝, 파일 끝, 섹션 끝)까지 전체 품질로 작성하십시오.
  • 다음으로 종료하십시오.
[PAUSED — X / Y 완료. "continue"를 보내면 다음 위치부터 재개: 다음 섹션 이름]

"continue" 명령이 오면 정확히 중단된 지점부터 이어서 작업하십시오. 요약이나 반복은 없습니다.

빠른 확인

응답을 마무리하기 전에 다음을 확인하십시오:

  • 위 목록의 금지된 패턴이 출력 어디에도 나타나지 않음
  • 사용자가 요청한 모든 항목이 존재하고 완료됨
  • 코드 블록에 코드가 수행할 작업에 대한 설명이 아닌 실제 실행 가능한 코드가 포함됨
  • 공간을 절약하기 위해 어떤 것도 단축되지 않음

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

leonxlnx/design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

leonxlnx/design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

leonxlnx/gpt-taste

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

leonxlnx/image-taste-frontend

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/industrial-brutalist-ui

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/minimalist-ui

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

leonxlnx/redesign-existing-projects

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

leonxlnx/stitch-design-taste

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

leonxlnx/taste-skill

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

leonxlnx/taste-skill

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/taste-skill

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/taste-skill

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/taste-skill

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

leonxlnx/taste-skill

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

leonxlnx/taste-skill

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/taste-skill

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

leonxlnx/taste-skill

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

관련 스킬