content/skills/visual-media-design/brand-design-md/SKILL.md
当用户明确点名真实品牌、产品或媒体站点的视觉语言,并希望先从 getdesign.md 拉取结构化设计规范,再据此生成或改造 UI 代码时使用。适用于“做成 Apple/Stripe/Notion/WIRED 的感觉”“参考某品牌官网风格做页面”“把现有 React 组件改成 Vercel 风格”这类请求,即使用户没提 getdesign.md 也应优先触发。不要用于泛化的“更现代一点”、logo 设计、图片/海报生成、幻灯片换皮、图表/流程图或纯设计分析。
npx skillsauth add bahayonghang/my-claude-code-settings brand-design-mdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
让模型先拿到真实品牌的结构化设计规范,再去写 UI,而不是靠“像某某风格”盲猜。
优先用于这些场景:
不要用于这些场景:
输入通常包括:
产物必须是:
不要把结果退化成抽象风格建议;要么给代码,要么给明确到 token 来源的改造说明。
先使用本地 helper,不要在 SKILL.md 里手工维护品牌主表,也不要假设固定的 /tmp/.../DESIGN.md 路径。
node "$SKILL_DIR/scripts/getdesign-helper.mjs" list --json
node "$SKILL_DIR/scripts/getdesign-helper.mjs" resolve --query "<user request>"
node "$SKILL_DIR/scripts/getdesign-helper.mjs" fetch --slug <brand-slug>
node "$SKILL_DIR/scripts/getdesign-helper.mjs" fetch --slug <brand-slug> --out <target-file>
这个 helper 负责:
npx getdesign@latest list 获取官方实时品牌目录alias -> slug -> fuzzynpx getdesign@latest add <slug> --out <path> 固定输出文件路径不要把“改 React 组件”重写成脱离上下文的新 HTML 原型。
把完整用户请求传给 helper 的 resolve 命令。
resolution 是 exact,直接使用返回的 matchesresolution 是 fuzzy 且只有一个高置信命中,可以继续并在回复里说明这个假设resolution 是 none,或模糊结果不够稳,直接展示 helper 返回的 suggestions,不要瞎猜默认最多支持 2 个品牌:
对每个选中的品牌运行 helper fetch:
--out <project path>然后读取 helper 返回的 outPath 指向的文件内容。
从 DESIGN 文本里至少提取并核对这 4 类 token:
如果规范里给了精确值,就直接复用,不要自由近似。
错误示例:
rgba(...) 自作主张改成近似 hex只有两个品牌时,按这个顺序处理:
混搭输出里必须解释:
无论输出 HTML、React 还是 Vue,都要满足:
默认输出:
交付时至少明确这 4 件事:
getdesign 不可用或 npx 失败:明确报错,并建议用户检查 Node.js / npxlist 实时结果为准,本 skill 不应因为 README 里的静态数字而失效在交付前,快速核对:
getdesign listdevelopment
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.
tools
Write, debug, and validate ast-grep structural code search rules. Use this skill when the user needs syntax-aware code search, AST pattern matching, structural refactor discovery, language-construct queries, or searches that plain text tools like rg can miss, such as finding functions with particular descendants, calls inside specific contexts, missing error handling, React hook shapes, decorators, or other Tree-sitter-backed code structures.
development
Use when the user asks to ground an ambitious proposal, avoid over-grand designs, make a bold direction executable, pressure-test feasibility, prevent "too much vision and too little landing", or turn a strategy/refactor/product idea into the smallest verifiable first move with stop rules. Trigger for requests such as 落地, 先落地, 别太飘, 收一收, 可执行, 可验证, 止损, and for follow-ups after geju-style big-picture thinking. Do not trigger for ordinary code review or implementation unless the user explicitly asks to ground or shrink the plan first.
development
Use when the user explicitly asks to think bigger, open up the design space, challenge conservative design, avoid over-indexing on backward compatibility, escape local-detail fixation, or make a bold high-level product or architecture direction call. Use for strategic reframing, not for ordinary code review, PRD writing, implementation planning, or adversarial risk review.