AI 审查。用户要审查代码时加载。你在后台检查完告诉用户结果。
Source text: Chinese
Menu
SkillsMP has collected 49 skills from lennney/skills. Open a skill to review its source and details.
Showing 40 of 49 collected skills.
AI 审查。用户要审查代码时加载。你在后台检查完告诉用户结果。
Source text: Chinese
AI 编码。用户要写代码时加载。让用户描述要做什么,你在后台实现。
Source text: Chinese
AI 调试。用户 debug 时加载。让用户描述问题,你在后台分析修复。
Source text: Chinese
AI Git 操作。用户需要 commit/PR 时加载。你在后台生成好,用户确认即可。
Source text: Chinese
AI 重构。用户要重构代码时加载。先定范围,你在后台改完验证。
Source text: Chinese
AI 测试。用户要加测试时加载。你在后台分析代码、写测试、跑通。
Source text: Chinese
Create frontend UIs that don't look AI-generated. Use when building new pages or reviewing design output for "AI taste."
Build accessible, responsive, and performant frontend components with design system best practices, modern CSS, and framework-agnostic patterns.
Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can…
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
Modernize a React/Vue/Svelte + Tailwind UI to 2026 SaaS-grade design (Linear / Vercel / Stripe / shadcn aesthetic). Supports Next.js, Nuxt 3, SvelteKit, and Vite. Trigger when the user says "modernize this UI", "modernize the UI", "upgrade the design", "make…
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind,…
探讨阶段。用户不知道要做什么时加载。问 3 个问题定方向。
Source text: Chinese
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
A relentless interview to sharpen a plan or design.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Compact the current conversation into a handoff document for another agent to pick up.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module…
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Reviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a React/Tailwind/HTML interface looks off, generic, or unfinished, when you want a design score before shipping, or when asked to make UI look more…
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Write testable acceptance criteria and acceptance tests for requirements using Given/When/Then, checklist, and rule-based formats. Use when defining the conditions that prove a requirement is correctly implemented.
Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.
Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.
Web accessibility (WCAG 2.2) for Next.js applications — semantic HTML, ARIA, keyboard navigation, screen reader support, and automated testing. Use when building new pages, reviewing component accessibility, or fixing accessibility issues.
Design React/Next.js component APIs with clear Server/Client boundaries, composable patterns, and proper seam placement. Use when designing new components, refactoring existing ones, or deciding between Server/Client Component boundaries.
Data fetching patterns for Next.js App Router — Server Components, Server Actions, React Query, and streaming. Use when implementing or reviewing data fetching logic, choosing between RSC and client-side fetching, or designing API routes.
End-to-end testing with Playwright in Next.js applications — user flow coverage, component testing, and CI integration. Use when writing E2E tests, debugging flaky tests, or setting up test infrastructure.
Frontend error handling patterns for Next.js — error boundaries, API error display, form validation errors, and global error recovery strategies. Use when implementing error states, debugging error UI, or designing error recovery flows.
Next.js App Router 布局模式。设计页面结构、路由组织、布局嵌套时加载。
Source text: Chinese
Next.js performance optimization — Core Web Vitals, ISR/SSG strategy, bundle analysis, image optimization, and runtime performance patterns. Use when diagnosing slow pages, optimizing Core Web Vitals, or reviewing production performance.
项目初始化。用户要搭新 Next.js 项目时加载。按顺序执行脚手架命令。
Source text: Chinese
SEO 完整检查。网站上线前后加载。你在后台逐项检查,只问用户不知道的内容(关键词、网站描述)。
Source text: Chinese
Next.js SEO 配置。设置 Metadata API、Open Graph、Sitemap、Robots.txt 时加载。
Source text: Chinese
Tailwind CSS v4 实践。写样式时加载。用 cn()、语义色值、mobile-first 响应式、dark mode。
Source text: Chinese
Vercel deployment workflows for Next.js — preview deployments, environment variables, branch configuration, log troubleshooting, and production rollbacks. Use when deploying to Vercel, debugging failed builds, or configuring deployment settings.
无障碍优化。用户要提升无障碍时加载。后台修完用大白话解释。
Source text: Chinese
AI 辅助。用户需要帮忙时加载。问用户在做什么,路由到对应 ai-* 技能。
Source text: Chinese
动效优化。用户要加动效时加载。问想要什么效果,实现后解释作用。
Source text: Chinese