Skip to content
cccskills
FreePublished on GitHub

design-taste-frontend

Compatibility adapter into ui-implementation-workflow visual direction. Invoke explicitly for expressive marketing, brand, portfolio, or editorial work; do not use as the primary product UI workflow.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md2.1 KB
  • agents/openai.yaml315 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Frontend Visual Direction Compatibility Adapter

The maintained capability now lives inside $ui-implementation-workflow. This adapter preserves the old skill name without creating a second UI workflow. It carries no inherited aesthetic preference: old defaults and review history have no authority unless the user explicitly confirms a choice again.

Route

  1. Load $ui-implementation-workflow and classify the page.
  2. For marketing, brand, portfolio, or content pages that need a new visual direction, read ../ui-implementation-workflow/references/visual-direction.md.
  3. Return the selected visual-direction brief to the main workflow, then continue its implementation and screenshot loop.
  4. For dashboards, lists, details, forms, settings, and routine auth pages, stop here and use the existing product design system through $ui-implementation-workflow only.
  5. Record new explicit visual-review feedback through the main workflow's fresh review-signal ledger; do not turn it into a persistent preference automatically.

Boundaries

  • Do not run a second audit, implementation plan, token setup, responsive pass, or screenshot loop.
  • Do not require dark mode, image generation, animation, a particular framework, a global punctuation rule, or a fixed hero formula unless the brief needs it.
  • Preserve the existing component system, content hierarchy, accessibility, analytics, and product behavior unless the task explicitly authorizes change.
  • Treat aesthetic guidance as context-dependent decision rules. Keep hard requirements for user scope, factual integrity, accessibility, permissions, and rendered acceptance.

Output

Return the visual concept, design dials, typography, palette, composition, asset direction, motion policy, patterns to avoid, and visual acceptance criteria. Do not duplicate the main UI workflow output.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Route CEO-first multi-window work into owner-led role loops. Use for 总控/CEO、架构/CTO、内容主编、角色派发与复用、模型路由、来源窗口回调、role-windows 台账、skill 命中统计或 multi-window loop engineering。

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

Read-only first workflow for diagnosing application incidents by collecting service, log, network, configuration, and functional evidence before proposing any fix.

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

Run user-authorized black-box web security tests and evidence-based reports. Use for 黑盒安全测试、渗透测试、数据泄露、未授权访问、公开 JS/API、登录爆破防护、CORS 或安全响应头检查。

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

Choose the narrowest reliable browser surface across Codex Browser, signed-in Chrome, Playwright CLI, and platform scripts. Use for browser automation, logged-in workflows, UI inspection, screenshots, form filling, publish previews, or frontend QA.

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词:"升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

初始化 cheat-on-content 内容校准工作区。仅在用户明确开始该工作流,或其子 skill 确认缺少 .cheat-state.json 时使用;不响应一般项目初始化、安装诊断或 Codex 首次会话。

The English summary is being prepared. Showing the original description.

Dirtytrii/codex-skills11Updated Oct 9, 2026

See all skills by Dirtytrii

Report a problem with this skill