Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

senior-fullstack高级全栈

Agent Skill

senior-fullstack 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

783

周安装

32

GitHub Stars

1

下载量

251
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:senior-fullstack(高级全栈)
来源仓库:https://github.com/pixel-process-ug/superkit-agents
仓库路径:skills/senior-fullstack
安装命令:
npx skills add https://github.com/pixel-process-ug/superkit-agents --skill senior-fullstack
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。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/pixel-process-ug/superkit-agents --skill senior-fullstack

简介

senior-fullstack 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 适用于全栈开发相关的信息搜集与筛选,可结合来源仓库和原始 README 核验具体用法。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态。
  • 安装前建议确认是否会触发联网、命令执行或文件读写等操作边界。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Senior Fullstack Engineer

Overview

Deliver complete, end-to-end TypeScript applications covering database design, API layer, frontend UI, authentication, and deployment. This skill specializes in the modern TypeScript full-stack: Next.js App Router, tRPC for type-safe APIs, Prisma for database access, and production deployment with monitoring.

Announce at start: "I'm using the senior-fullstack skill for end-to-end TypeScript development."


Phase 1: Data Layer

Goal: Design the database schema and data access patterns.

Actions

  1. Design database schema with Prisma
  2. Define relationships and indexes
  3. Create seed data for development
  4. Set up migrations workflow
  5. Implement repository pattern for data access

Prisma Schema Example

model User {
  id        String   @id @default(cuid())
  email     String   @unique
  name      String
  role      Role     @default(USER)
  posts     Post[]
  createdAt DateTime @default(now())
  updatedAt DateTime @updatedAt

  @@index([email])
  @@index([createdAt])
}

model Post {
  id        String   @id @default(cuid())
  title     String
  content   String?
  published Boolean  @default(false)
  author    User     @relation(fields: [authorId], references: [id], onDelete: Cascade)
  authorId  String
  createdAt DateTime @default(now())
  updatedAt DateTime @updatedAt

  @@index([authorId])
  @@index([published, createdAt])
}

Index Strategy Decision Table

Query PatternIndex TypeExample
Lookup by unique fieldUnique index@@unique([email])
Filter by foreign keyStandard index@@index([authorId])
Filter + sort combinationComposite index@@index([published, createdAt])
Full-text searchFull-text indexDatabase-specific
Geospatial querySpatial indexDatabase-specific

STOP — Do NOT proceed to Phase 2 until:

  • Schema is defined with all relationships
  • Indexes cover all query patterns
  • Seed data script exists
  • Migrations are generated and tested

Phase 2: API Layer

Goal: Build type-safe API with tRPC and Zod validation.

Actions

  1. Define tRPC routers and procedures
  2. Implement input validation with Zod
  3. Add authentication middleware
  4. Build business logic in service layer
  5. Add error handling and logging

tRPC Router Example

export const userRouter = router({
  list: protectedProcedure
    .input(z.object({
      page: z.number().min(1).default(1),
      pageSize: z.number().min(1).max(100).default(20),
      search: z.string().optional(),
    }))
    .query(async ({ ctx, input }) => {
      const { page, pageSize, search } = input;
      const where = search ? { name: { contains: search, mode: 'insensitive' } } : {};
      const [users, total] = await Promise.all([
        ctx.db.user.findMany({
          where, skip: (page - 1) * pageSize, take: pageSize, orderBy: { createdAt: 'desc' },
        }),
        ctx.db.user.count({ where }),
      ]);
      return { users, total, totalPages: Math.ceil(total / pageSize) };
    }),

  create: protectedProcedure
    .input(createUserSchema)
    .mutation(async ({ ctx, input }) => {
      return ctx.db.user.create({ data: input });
    }),
});

Authorization Pattern Decision Table

PatternUse WhenExample
Role-based (RBAC)Simple permission modelAdmin vs User
Resource-levelOwner-only accessUser can edit own posts
Attribute-based (ABAC)Complex rulesOrg membership + role + resource state
Feature flagsGradual rolloutPremium features

STOP — Do NOT proceed to Phase 3 until:

  • All tRPC routers are defined with Zod validation
  • Auth middleware protects appropriate routes
  • Business logic is in service layer (not in router)
  • Error handling returns structured errors

Phase 3: UI Layer

Goal: Build pages with Server Components by default, Client Components for interactivity.

Actions

  1. Build pages with Server Components (default)
  2. Add Client Components for interactivity
  3. Connect to API via tRPC hooks
  4. Implement optimistic updates
  5. Add loading and error states

Component Type Decision Table

NeedComponent TypeData Source
Static content, data displayServer ComponentDirect DB/API call
Interactive formClient ComponenttRPC mutation hook
Real-time updatesClient ComponenttRPC subscription or polling
Search/filterClient ComponenttRPC query with debounce
Navigation chromeServer ComponentSession data

STOP — Do NOT proceed to Phase 4 until:

  • Pages use Server Components by default
  • Client Components are minimal and justified
  • Loading and error states exist for all data-fetching paths
  • Optimistic updates work for mutations

Phase 4: Production

Goal: Prepare for deployment with auth, monitoring, and CI/CD.

Actions

  1. Set up authentication (NextAuth.js / Clerk / Lucia)
  2. Configure deployment (Vercel / Docker)
  3. Add monitoring and error tracking
  4. Implement CI/CD pipeline
  5. Performance audit

Auth Solution Decision Table

SolutionBest ForSSR SupportSelf-Hosted
NextAuth.js (Auth.js)OAuth providers, JWT/sessionYesYes
ClerkFast setup, managed serviceYesNo
LuciaCustom, lightweightYesYes
Supabase AuthSupabase ecosystemYesPartial

Monitoring Checklist

  • Error tracking (Sentry) with source maps
  • Performance monitoring (Vercel Analytics or custom)
  • Database query performance (Prisma metrics)
  • API endpoint latency and error rates
  • Uptime monitoring (external ping)
  • Log aggregation with structured logging
  • Alerting for error rate spikes

Docker Deployment

FROM node:20-alpine AS base
RUN corepack enable

FROM base AS deps
WORKDIR /app
COPY package.json pnpm-lock.yaml ./
RUN pnpm install --frozen-lockfile

FROM base AS builder
WORKDIR /app
COPY --from=deps /app/node_modules ./node_modules
COPY . .
RUN pnpm prisma generate
RUN pnpm build

FROM base AS runner
WORKDIR /app
ENV NODE_ENV=production
COPY --from=builder /app/.next/standalone ./
COPY --from=builder /app/.next/static ./.next/static
COPY --from=builder /app/public ./public
EXPOSE 3000
CMD ["node", "server.js"]

STOP — Production ready when:

  • Auth is configured and tested
  • Deployment pipeline works (preview + production)
  • Monitoring and alerting are active
  • Performance audit completed

Full-Stack Type Safety Pipeline

Prisma Schema -> Prisma Client (types) -> tRPC Router -> tRPC Hooks -> React Components
     |                  |                     |              |              |
  Migration        Type-safe DB          Validated API    Auto-typed    Rendered UI
                   queries               with Zod         queries

Project Structure

prisma/
  schema.prisma
  migrations/
  seed.ts
src/
  app/                    # Next.js App Router
    (auth)/               # Auth route group
    (dashboard)/          # Protected route group
    api/trpc/[trpc]/      # tRPC handler
  server/
    db.ts                 # Prisma client singleton
    trpc.ts               # tRPC init
    routers/              # tRPC routers
    services/             # Business logic
  components/
    ui/                   # Design system atoms
    features/             # Feature components
  hooks/                  # Custom React hooks
  lib/
    trpc.ts               # tRPC client
    auth.ts               # Auth configuration
    validators.ts         # Zod schemas
tests/
  unit/
  integration/
  e2e/

Anti-Patterns / Common Mistakes

Anti-PatternWhy It Is WrongCorrect Approach
Raw SQL in componentsBypasses type safety and securityUse Prisma through tRPC
Client-side fetch when Server Components workUnnecessary JavaScript, slowerServer Components for static data
Sharing Prisma client with frontendSecurity breach, exposes DBPrisma only in server code
Missing indexes on foreign keysSlow joins and lookupsIndex every foreign key
Storing tokens in localStorageXSS vulnerabilityHttpOnly cookies
Skipping Zod validationRuntime type errorsValidate all inputs at API boundary
Monolithic tRPC routerHard to maintain, merge conflictsSplit by domain (user, post, etc.)
Business logic in tRPC proceduresHard to test, not reusableExtract to service layer

Documentation Lookup (Context7)

Use mcp__context7__resolve-library-id then mcp__context7__query-docs for up-to-date docs. Returned docs override memorized knowledge.

  • react — for component patterns, hooks, or React 19+ features
  • next.js — for App Router, API routes, or server components
  • prisma — for schema design, client queries, or migrations
  • tailwindcss — for utility-first CSS patterns or configuration

Integration Points

SkillRelationship
senior-frontendUI layer follows frontend patterns
senior-backendAPI layer follows backend patterns
senior-architectArchitecture decisions guide service boundaries
security-reviewAuth implementation follows security patterns
testing-strategyFull-stack testing uses strategy frameworks
code-reviewReview covers all layers of the stack
performance-optimizationOptimization applies to all layers

Key Principles

  • Single language (TypeScript) from database to browser
  • Type safety across the entire stack (no runtime type mismatches)
  • Server Components by default, Client Components by necessity
  • Validate all inputs at the API boundary with Zod
  • Database indexes for every query pattern
  • Environment-based configuration (no hard-coded values)

Skill Type

FLEXIBLE — Adapt the tech choices to the project context. The four-phase process is strongly recommended. Type safety across the stack is non-negotiable. All API inputs must be validated with Zod. Database schema changes must use migrations.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

39.01%
按下载量换算98

Claude

30.23%
按下载量换算76

Cursor

18.86%
按下载量换算47

Gemini CLI

9.45%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills