DESIGN.md — AI时代设计规范技能
v1.0.0DESIGN.md 设计与品牌规范技能。当用户需要创建项目设计规范文档、为AI编写品牌规范、让AI生成符合品牌风格的页面时激活。 触发词：DESIGN.md、设计规范、品牌规范、设计系统、生成设计文档、写DESIGN.md、设计语言。 用于：创建新项目的 DESIGN.md、更新已有设计规范、让AI按规范生成UI。
⭐ 0· 139·1 current·1 all-time
bymingyuan@zmy1006-sudo
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name, description, and SKILL.md consistently describe creating/updating a DESIGN.md and using it to guide AI-generated UI. It requests no binaries, env vars, or installs — appropriate for a documentation/agent prompt helper. File read/write of project-level design assets (DESIGN.md, Tailwind config, color variables) is coherent with the stated purpose.
Instruction Scope
Instructions explicitly tell the agent to read and write DESIGN.md in the project root and to extract existing design resources (Tailwind config, color variables, 'brand materials'). This is expected for a design-spec skill, but it implies the agent will access arbitrary repo files labeled as design/brand assets. Users should confirm they are comfortable with the agent reading those project files and that no sensitive secrets are stored in them.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is downloaded or written to disk by an installer. This is the lowest-risk install profile.
Credentials
The skill requests no environment variables, credentials, or config paths. There are no disproportionate secret requests.
Persistence & Privilege
always is false and there are no special persistence or system modifications. The skill can be invoked autonomously by the agent (platform default); combined with this skill's limited scope, that is reasonable but consider agent invocation policies if you want to restrict autonomous runs.
Assessment
This skill is an instruction-only helper for authoring and using a DESIGN.md and appears internally consistent. Before enabling it, confirm: (1) you are comfortable with the AI agent reading and writing files in project root (DESIGN.md, Tailwind configs, other design assets); (2) no sensitive credentials or secrets are stored inside design/brand files the agent might access; (3) you will review any generated code or commits before executing or pushing them. If you need stricter limits, restrict the agent's file access or require manual approval for writes/commits.Like a lobster shell, security has layers — review code before you run it.
brandvk9720wmt3dm62pm3w94xfn1m5584d7gkdesignvk9720wmt3dm62pm3w94xfn1m5584d7gkdesign-systemvk9720wmt3dm62pm3w94xfn1m5584d7gklatestvk9720wmt3dm62pm3w94xfn1m5584d7gktailwindvk9720wmt3dm62pm3w94xfn1m5584d7gkuivk9720wmt3dm62pm3w94xfn1m5584d7gk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.