Claude Skills by NeverSight

Comprehensive guidance for applying modern UI design styles, including Soft UI, Dark Mode, Flat Design, Neumorphism, Glassmorphism, and Aurora UI Gradients. Use when a user asks to: (1) Apply a specific UI style to a project, (2) Create a modern, visually appealing UI prototype, (3) Improve accessibility while following design trends, or (4) Understand the technical implementation of specific UI effects like frosted glass or soft shadows.

Guides the agent to apply Generativity Theory to solve problems by building high-leverage, open-ended systems. Use this skill when the user asks for "out of the box" ideas, platform strategies, or when a task benefits from enabling others to innovate rather than providing a narrow, single-purpose fix.

Principles, laws, and checklists for analyzing and optimizing software latency. Use this skill when: (1) Diagnosing slow performance or latency spikes, (2) Designing systems with strict latency requirements, (3) Analyzing theoretical limits using Little's Law or Amdahl's Law, or (4) Learning about latency sources (OS, Hardware, Network).

Material 3 Expressive (M3E). Comprehensive guidance on expressive design system for Flutter with platform support for Android and Linux desktop. Covers color tokens, typography scales, motion specifications, shape tokens, spacing ramps, and component enhancements for creating emotionally engaging UIs. Includes migration guidance from standard M3 and platform-specific integration notes.

Comprehensive guide for diagnosing, optimizing, and hiding latency in software systems. Use when: (1) Debugging slow performance, (2) Designing low-latency architectures (High Frequency Trading, Real-time), (3) Optimizing Data/Compute layers, or (4) Learning about latency theory (Little's Law, Coordinated Omission).

Manage AI agent memory files (AGENTS.md/CLAUDE.md). Supports update and restructure modes. Use when users need to sync, update, or restructure agent memory files. Triggers on keywords like "记忆文件", "memory file", "AGENTS.md", "更新记忆", "重构记忆", "memory sync", "memory restructure".

Opinionated constraints for writing maintainable, testable code. Apply MTE principles, avoid over-engineering, guide refactoring, and provide code review checklists. Use when users write code, refactor, or need code review. Triggers on keywords like "code quality", "refactor", "review", "MTE", "代码质量", "重构", "审查".

Generate and maintain self-describing code structure with module-level CLAUDE.md files and source file header comments (INPUT/OUTPUT/POS). Supports init, update, and audit modes. Use when users want to add AI-friendly code descriptions, improve code navigation, or maintain code documentation. Triggers on keywords like "self-describe", "code description", "CLAUDE.md", "自描述", "代码描述", "模块描述", "生成描述".

Git 提交信息规范。着重于提交信息的格式化、风格统一。优先学习并沿用项目已有的提交历史风格，若无明显风格或为新项目，则遵循 Conventional Commits 规范。

Test-first bug fixing workflow. Guide users through reproducing bugs, writing failing tests, fixing code, and committing. Use when users report bugs, need to fix issues, or mention keywords like "bug", "fix", "issue", "崩溃", "报错", "修复".

Break down system design into executable development tasks. Use when users need task breakdown, sprint planning, or development task lists. Triggers on keywords like "dev tasks", "task breakdown", "sprint planning", "implementation tasks".

Execute development tasks with skeleton-first approach and layered TDD. Use when users start working on a task (T-XX), need development guidance, or implement features/bugfixes. Triggers on keywords like "execute task", "start T-XX", "implement", "develop", "开发任务", "执行任务".

Add new features to existing DevDocs projects. Use when users need to add new features, iterate on existing functionality, or mention keywords like "add feature", "new feature", "新功能", "迭代", "新增功能".

Generate project context summary for AI tool handover. Use when switching AI tools, starting new sessions, or onboarding team members. Triggers on keywords like "project context", "handover", "onboard", "项目上下文", "交接", "接手项目".

Expand user requirements into detailed DevDocs documents. Use when users provide feature requirements, want to clarify requirements, or need to create product requirement documents. Triggers on keywords like "requirements", "PRD", "feature request", "user story".

Retrofit existing projects to DevDocs workflow, or migrate old DevDocs to new standards. Use when users want to adapt existing projects, migrate documentation, standardize documents, or upgrade DevDocs version. Triggers on keywords like "retrofit", "改造", "适配", "迁移", "标准化", "逆向", "升级文档".

Sync documentation with implementation progress. Use when users need to update docs after development, verify doc-code consistency, or track implementation progress. Triggers on keywords like "sync docs", "update progress", "doc consistency", "同步文档", "更新进度".

Create or update system design documents. Supports initial design and incremental design modes. Use when users need technical architecture, API design, data models, design changes, or impact analysis. Triggers on keywords like "system design", "architecture", "technical design", "API design", "design change", "impact analysis", "设计变更", "影响分析".

Design test cases based on requirements. Use when users need test case design, testing strategy, or QA planning. Triggers on keywords like "test cases", "test design", "unit test", "integration test", "e2e test".

Git 操作安全与规范。强制要求使用 git 原生命令处理受控文件，防止丢失索引或产生冗余变更。当 Agent 尝试移动、重命名或删除文件时触发。

Systematic refactoring skill with test coverage requirements. Supports scope analysis, test-first refactoring, and integration with DevDocs workflow. Use when users need to refactor code, improve code quality, or restructure existing implementations. Triggers on keywords like "refactor", "重构", "优化代码", "代码改造", "tech debt", "技术债".

Opinionated constraints for writing effective tests. Guide unit tests, integration tests, and E2E tests with quality metrics beyond coverage. Use when users write tests, review test code, or need testing strategy. Triggers on keywords like "test", "testing", "单元测试", "集成测试", "E2E", "测试质量", "coverage", "断言".

UI/UX skill dispatcher that routes to specialized external skills based on project needs. Use when working on UI development, design systems, or frontend tasks. Triggers on keywords like "UI", "界面", "前端", "组件", "animation", "动画", "layout", "布局", "SwiftUI".

Opinionated constraints for building better interfaces with agents. Apply when writing UI code, implementing designs, or reviewing frontend components. Use within DevDocs workflow during development phase for UI-related tasks. Triggers on keywords like "UI", "界面", "前端", "组件", "animation", "动画", "layout", "布局".

生成周报、月报、季度报和年终总结。当用户提到"周报"、"月报"、"季报"、"季度报"、"年终总结"、"年度总结"、"weekly report"、"monthly report"、"quarterly report"、"annual summary"、"yearly review"，或者需要生成各类工作报告时使用此 Skill。

R style guide covering naming conventions, spacing, layout, and function design best practices. Use when writing R code.

Modern tidyverse patterns for R including pipes, joins, grouping, purrr, and stringr. Use when writing tidyverse R code.

ABC 医疗云 API 文档查询工具。读取和查询 ABC API 的 OpenAPI 规范文档（5000+ 接口），支持按模块、路径、方法搜索，自动解析 $ref 引用。采用按模块拆分的缓存结构，查询速度快。使用场景：(1) 查询 API 接口定义 (2) 搜索特定功能接口 (3) 查询 Schema 定义 (4) 查看接口统计信息

ABC 医疗云 API 文档查询工具。读取和查询 ABC API 的 OpenAPI 规范文档（4209 个接口），支持按模块、路径、方法搜索，自动解析 $ref 引用。使用场景：(1) 查询 API 接口定义 (2) 搜索特定功能接口 (3) 导出接口文档摘要 (4) 查看接口统计信息

阿里云云效 Codeup 代码仓库管理工具集。使用场景包括：(1) 代码仓库操作 - 分支管理、文件操作、代码对比、合并请求/MR管理 (2) 组织管理 - 部门管理、成员查询、角色管理 (3) 操作 codeup 仓库、分支、MR、合并请求 (4) 查询云效组织成员、部门列表

ABC Jenkins 项目发布技能。支持智能参数推断和交互式触发 Jenkins 构建，自动获取 Git 分支和标签信息。当用户请求"发布 Jenkins"、"触发构建"、"部署项目"、"Jenkins 发布"或类似操作时触发此技能。需要环境变量 JENKINS_USER 和 JENKINS_TOKEN。

墨刀原型稿抓取工具。自动从墨刀原型稿链接抓取所有页面、截图和批注，生成 Markdown 文档。使用场景包括：(1) 抓取原型稿页面 (2) 生成页面截图 (3) 提取批注内容 (4) 导出 Markdown 文档

Use when creating, modifying, or debugging Claude Code plugins. Triggers on .claude-plugin/, plugin.json, marketplace.json, commands/, agents/, skills/, hooks/ directories. Provides schemas, templates, validation workflows, and troubleshooting.

根据 traceId 或 URL（带时间戳）查询阿里云日志服务 (SLS) 获取日志，分析日志内容，定位代码中的问题。

TAPD 敏捷研发管理平台集成。使用脚本调用 TAPD API，实现需求、缺陷、任务、迭代、测试用例、Wiki 等实体管理。使用场景包括：(1) 查询/创建/更新需求、缺陷、任务、迭代 (2) 管理测试用例和 Wiki (3) 管理评论和工时 (4) 关联需求与缺陷 (5) 获取源码提交关键字

用 Browser-Use 做复杂网页自动化（多步骤登录、填表、发帖、数据抓取）。当内置 browser tool（snapshot→act）搞不定时用这个——它是专门的浏览器AI agent，一个task丢进去自主完成全流程。触发词：browser-use、浏览器自动化、自动登录、自动填表、自动发帖、网页操控、复杂网页操作。

Comprehensive bug audit for Node.js web projects. Activate when user asks to audit, review, check bugs, find vulnerabilities, or do security/quality review on a project. Works by dissecting the project's actual code to build project-specific check matrices, then exhaustively verifying each item — not by running a generic checklist. Supports games, data tools, WeChat apps, API services, bots, and dashboards.

Systematic debugging and problem-solving methodology. Activate when encountering unexpected errors, service failures, regression bugs, deployment issues, or when a fix attempt has failed twice. Also activate when proposing ANY fix to verify it addresses root cause (not a workaround). Prevents patch-chaining, wrong-environment restarts, workaround addiction, and "drunk man" random fixes.

Node.js project architecture standards for AI-assisted development. Enforces file splitting (<400 lines), config externalization, route modularization, and admin dashboards. Use when creating new Node.js projects, refactoring large single-file codebases, or when AI context window is being consumed by oversized files. Covers H5 games (Canvas/Phaser/Matter.js), data tools (crawlers/scrapers), content platforms, monitoring dashboards, API services, and SDK libraries.

OpenClaw + Ollama 中文记忆系统优化。诊断 FTS5 unicode61 中文分词 bug，优化搜索参数，自动维护记忆文件。命中率从 55% 提升到 100%。

Autonomous multi-step agent flow sequencer and command router. Intercepts /agentflow <text> invocations, expands short instructions into execution-grade engineering briefs using workspace rules, classifies tasks, routes to the optimal model, executes autonomously, runs dynamic stack-based post-execution validation, and updates project documentation.

Build Flutter features using BLoC state management, clean architecture layers, and the project's design system. Apply when creating screens, widgets, or data integrations.

Comprehensive guide to data binding patterns in Avalonia for AI agents.

Implement MVVM patterns using CommunityToolkit.Mvvm in Avalonia applications with ViewModels, Commands, and Dependency Injection

Professional Adobe Photoshop automation via COM/ExtendScript bridge. Supports text updates, filters, and action playback.

All-in-one Apple developer skill with three integrated tools shipped as a single unified binary. (1) Documentation search across Apple frameworks, symbols, and 1,267 WWDC sessions from 2014-2025. No credentials needed. (2) App Store Connect CLI with 120+ commands covering builds (find/wait/upload), TestFlight, pre-submission validate, submissions, signing, subscriptions (family-sharable), IAP, analytics, Xcode Cloud, metadata workflows, release pipeline dashboard, insights, win-back offers, p...

Run a full McKinsey-level market research and strategy analysis using 12 specialized prompts. Use when the user asks for: market research, competitive analysis, business strategy, TAM analysis, customer personas, pricing strategy, go-to-market plan, financial modeling, risk assessment, SWOT analysis, market entry strategy, or comprehensive business analysis. Also triggers on: بحث سوق, تحليل استراتيجي, تحليل منافسين, دراسة جدوى, خطة عمل

Self-healing monitoring system for OpenClaw gateway. Auto-detects failures, fixes crashes, and sends Telegram alerts.

Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (CoT, Few-Shot, Persona, etc.). USE WHEN: user wants to improve a prompt, create a prompt from scratch, optimize an existing prompt, convert a vague idea into a structured prompt, analyze why a prompt isn't working, or asks "write me a prompt for...", "improve this prompt", "prompt engineer this". DON'T USE WHEN: user wants to execute the ...

Complete Google Workspace integration (Gmail, Docs, Sheets, Calendar, Drive, Tasks, Slides). Load when user mentions 'google', 'gmail', 'email', 'google docs', 'google sheets', 'spreadsheet', 'google calendar', 'schedule meeting', 'calendar', 'google drive', 'upload file', 'download file', 'google tasks', 'todo', 'google slides', 'presentation', or any Google service operation.