Index of every page on this site: llms.txt
All skills
Run it yourself

用于 React 前端开发、页面与组件实现、前端技术选型和代码检查。统一 React、Vite、Tailwind CSS v4、shadcn/ui(Base UI + Nova)技术栈,优先复用成熟组件,限制重复依赖。独立使用,不依赖其他 Skill 或工作流。

  • 5 files
  • 15.9 KB
  • Updated 3 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alicedel66/frontend-stack-guardrails/frontend-stack

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈71 tokens for metadata: the name and description. ≈579 when used: this file. ≈2.4k more on demand in 2 files.

Description uses 1.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈148 characters, or 1.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

前端技术栈与实现规范

使用方式

处理前端开发任务时,先阅读 前端规范,再开展实现。规则、检查器与依赖清单均在本 Skill 目录内,不需要外部 Skill、全局配置或专用服务。

执行要求

  1. 先了解项目:读取项目说明、现有 AI 指令、package.json、components.json 及 ESLint 配置。明确任务的验收条件,只改需求所需部分。
  2. 判断适用性:本规范默认面向 React + Vite 的内部工具和数据看板。已有项目的明确约束优先;若已有技术栈与此冲突,说明冲突并由项目维护者决定,不擅自迁移框架、更换组件库或批量删除依赖。
  3. 先复用后实现:检查 shadcn/ui 和规范指定库是否已有能力。已有组件通过组合、className 或组件源码定制,不另造平行组件。
  4. 遵守边界:统一 Tailwind 与主题变量;HTTP 请求通过 src/lib/api.ts 中的 Axios 封装,接口缓存与重试交给 TanStack Query,客户端共享状态交给 Zustand;只使用白名单中的依赖。新增依赖或例外须经项目维护者确认并在清单中记录理由。
  5. 检查按需接入:guard/check-deps.mjs 和 guard/fe-stack.json 是依赖检查器;guard/eslint-restricted.js 是 ESLint flat config 片段。接入前检查项目已有配置,按包内 README 合并,不覆盖原配置。这些工具不会因 Skill 被加载而自动运行。
  6. 验证后交付:运行项目已配置的 lint、依赖检查、测试及构建;涉及界面时验证交互和相关布局。缺少命令先说明并按任务范围接入,不虚构通过结果。交付时列出实际检查结果、未验证项及已确认的例外。

资源与检查边界

依赖检查器检查当前项目 package.json 的 dependencies 与 devDependencies,不检查传递依赖或版本兼容性。ESLint 片段仅约束 src/**/*.ts、src/**/*.tsx 中配置覆盖的导入;它不能自动保证所有架构、样式与复用要求。其余条款仍需代码审查与测试。

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 64d5b67. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated 3 weeks ago

README badge

README badge for alicedel66/frontend-stack-guardrails