Token导航 LogoToken导航

Agent Skill · 前端设计

writing-descriptions(撰写描述)

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。

writing-descriptions 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证为 MIT,暂无第三方扫描结果,按安装量在前端设计类的 10,216 个 Skill 里排第 7,570。

总安装 364周安装 15GitHub Stars 6下载 119核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:writing-descriptions(撰写描述)
来源仓库:https://github.com/mgd34msu/goodvibes-plugin
仓库路径:skills/writing-descriptions
安装命令:
npx skills add https://github.com/mgd34msu/goodvibes-plugin --skill writing-descriptions
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/mgd34msu/goodvibes-plugin --skill writing-descriptions

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。适合生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码。需要结合项目现有设计系统、路由和构建方式使用。涉及页面改动时应配合本地预览和构建检查确认效果。安装方式:通过 GitHub 仓库添加技能。

writing-descriptions 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/writing-descriptions

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/mgd34msu/goodvibes-plugin --skill writing-desc…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

writing-descriptions 怎么安装?

在终端执行 npx skills add https://github.com/mgd34msu/goodvibes-plugin --skill writing-descriptions。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

writing-descriptions 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

writing-descriptions 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

writing-descriptions 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

writing-descriptions 用的人多吗?

公开数据是累计安装 364 次,近一周安装 15 次,下载 119 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

writing-descriptions 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
writing-descriptions

撰写描述 · 本页

3646操作浏览器MIT未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Writing Effective Descriptions

The description field is THE routing key. Claude reads descriptions to decide whether to invoke an agent or skill. Poor descriptions = artifacts that never trigger.

The Formula

{Role/expertise}. Use [PROACTIVELY] when {specific trigger conditions}.
  • Role/expertise: What the agent/skill does (third person for skills)
  • PROACTIVELY: Include if Claude should invoke without being asked
  • Trigger conditions: Specific situations that warrant invocation

Agent Description Examples

By Category

CategoryDescription
Debugging"Docker troubleshooter. Use PROACTIVELY when containers fail to start, crash, or behave unexpectedly."
Code Review"Security-focused code reviewer. Use PROACTIVELY when reviewing authentication, authorization, or data handling code."
Testing"Test generation specialist. Use when asked to add tests or improve test coverage for existing code."
Infrastructure"Kubernetes deployment expert. Use PROACTIVELY when working with k8s manifests, helm charts, or cluster issues."
API Design"REST API designer. Use when creating new endpoints, designing request/response schemas, or documenting APIs."
Performance"Performance optimization specialist. Use when profiling, optimizing queries, or reducing latency."
Database"PostgreSQL query optimizer. Use PROACTIVELY when queries are slow or EXPLAIN shows sequential scans."
Frontend"React component architect. Use when building complex UI components or refactoring component hierarchies."

Good vs Bad

BadWhy It FailsBetter
"Helps with Docker"Too vague, no triggers"Docker troubleshooter for container failures"
"General coding assistant"No specificity"Python async specialist for concurrent code"
"Does database stuff"Unclear scope"PostgreSQL query optimizer for slow queries"
"Useful for many things"No routing signal"Git workflow automator for branching and merging"
"I help you with tests"Wrong person (first)"Test generator for untested functions"

Skill Description Examples

By Category

CategoryExample Description
Document Processing"Comprehensive document creation, editing, and analysis with tracked changes support. Use when working with.docx files for creating, modifying, or extracting content."
Data Analysis"Analyzes Excel spreadsheets, creates pivot tables, generates charts. Use when analyzing.xlsx files, spreadsheets, or tabular data."
API Integration"Creates MCP servers for external API integration using TypeScript or Python. Use when building Model Context Protocol servers or LLM tool integrations."
Creative/Design"Creates distinctive production-grade frontend interfaces. Use when building web components, landing pages, dashboards, or styling any web UI."
Workflow Automation"Guides users through structured document co-authoring. Use when writing documentation, proposals, technical specs, or decision docs."
Testing"Tests local web applications using Playwright. Use when verifying frontend functionality, debugging UI, or capturing browser screenshots."
PDF Processing"Extracts text and tables from PDFs, fills forms, merges documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction."
Presentations"Creates and modifies PowerPoint presentations with consistent styling. Use when building slide decks, adding charts, or formatting presentations."

Skills: Third Person Requirement

Skills must use third person voice:

# Good (third person)
description: Extracts text from PDFs and fills form fields.

# Bad (first person)
description: I help you process PDFs.

# Bad (second person)
description: Helps you extract PDF text.

Proactive vs On-Demand

Use PROACTIVELY when:

  • The situation is detectable from context (error messages, file types)
  • Waiting for explicit request would delay the user
  • The agent/skill is highly specialized
# Proactive - Claude should invoke without being asked
"Docker troubleshooter. Use PROACTIVELY when containers fail to start..."
"Security reviewer. Use PROACTIVELY when reviewing auth code..."

On-demand (no PROACTIVELY) when:

  • User should explicitly request the capability
  • Multiple valid approaches exist
  • The action has significant side effects
# On-demand - wait for user request
"Test generator. Use when asked to add tests..."
"Database migrator. Use when user requests schema changes..."

Trigger Specificity

More specific triggers = more reliable invocation:

Vague TriggerSpecific Trigger
"when needed""when containers fail to start or exit unexpectedly"
"for code review""when reviewing authentication, authorization, or session code"
"for testing""when test coverage is below 80% or user asks for tests"
"for performance""when queries exceed 100ms or EXPLAIN shows sequential scans"

Combining Multiple Triggers

Use "or" to list multiple valid triggers:

"PDF processor. Use when working with PDF files, filling forms,
extracting tables, or merging documents."

Use commas for related triggers:

"Kubernetes expert. Use PROACTIVELY when working with pods,
deployments, services, or ingress configurations."

平台分布

Claude Code

26.93%
按下载量换算32

Codex

23.45%
按下载量换算28

Cursor

17.23%
按下载量换算21

Antigravity

10.88%
按下载量换算13

windsurf

7.52%
按下载量换算9

github-copilot

3.65%
按下载量换算4

安全审计

暂无安全审计结果可展示。

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills