Claude Skills by NeverSight

查询中国地区的天气预报，支持15天及逐小时预报、各种生活指数

Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.

Search arXiv for academic papers, preprints, and research using the arXiv API. Finds foundational research, state-of-the-art techniques, and academic context. Returns structured findings with links, abstracts, and citations.

后端架构模式、API 设计、数据库优化，以及针对 Node.js、Express 和 Next.js API 路由的服务端最佳实践。

针对高性能分析工作负载的 ClickHouse 数据库模式、查询优化、分析和数据工程最佳实践。

适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。

基于 Instinct 的学习系统，通过 hooks 观察会话，创建具有置信度评分的原子 instincts，并将其演进为 skills/commands/agents。

自动从 Claude Code 会话中提取可重用模式，并将其保存为 learned skills 供将来使用。

基于 C++ Core Guidelines (isocpp.github.io) 的 C++ 编码标准。在编写、审查或重构 C++ 代码时使用，以强制执行现代、安全和地道的实践。

Claude Code 会话的正式评估框架，实施 eval-driven development (EDD) 原则

React、Next.js 的前端开发模式，以及状态管理、性能优化和 UI 最佳实践。

惯用的 Go 模式、最佳实践和约定，用于构建健壮、高效和可维护的 Go 应用程序。

Go 测试模式，包括表驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循具有惯用 Go 实践的 TDD 方法论。

Pi-hole 安装、阻止列表管理、DNS-over-HTTPS 设置、DHCP 集成、本地 DNS 记录以及在家庭网络上排除 DNS 解析故障。

逐步细化上下文检索以解决子 agent 上下文问题的模式

PostgreSQL 数据库模式，用于查询优化、架构设计、索引和安全。基于 Supabase 最佳实践。

TypeScript 后端的 Prisma ORM 模式 —— 模式设计、查询优化、事务、分页以及关键陷阱，如 updateMany 返回计数而非记录、$transaction 超时、migrate dev 重置数据库、@updatedAt 在批量写入时跳过、以及无服务器连接耗尽。

当添加认证、处理用户输入、使用 secrets、创建 API 端点或实施支付/敏感功能时使用此技能。提供全面的安全检查清单和模式。

建议在逻辑间隔进行手动上下文压缩，以保留任务阶段的上下文，而不是依赖任意的自动压缩。

在编写新功能、修复 bug 或重构代码时使用此技能。强制执行具有 80%+ 覆盖率（包括单元测试、集成测试和 E2E 测试）的测试驱动开发。

AI 辅助视频编辑工作流，用于剪切、结构化和增强真实素材。覆盖从原始录制到 FFmpeg、Remotion、ElevenLabs、fal.ai 以及在 Descript 或 CapCut 中最终润色的完整流水线。当用户想要编辑视频、剪切素材、制作 Vlog 或构建视频内容时使用。

Generates a structured penetration testing report based on OWASP standards including OWASP Top 10, ASVS, and WSTG methodology. Scans code for vulnerabilities, maps findings to OWASP categories, assigns CVSS scores, and produces a professional pentest report. Use when the user says "pentest report", "penetration testing", "OWASP audit", "OWASP report", "security assessment", "vulnerability assessment", "application security test", or "OWASP compliance check".

Write, review, and fix Blazor Server components in the BookStore project — covering render modes (InteractiveServer), lifecycle with IDisposable cleanup, DI via @inject/[Inject], ReactiveQuery<T> for SSE-driven data loading, MudBlazor forms/dialogs/tables, tenant-aware services, and AuthorizeView guards. Trigger whenever the user writes, reviews, or asks about .razor files, adding a page or component, ReactiveQuery, MudForm/MudTable/MudDialog, real-time UI updates from SSE, tenant-aware compo...

Brand identity generator that creates logos, color palettes, typography, brand images, and checks domain and social media username availability. Suggests and verifies available handles across platforms. Outputs a complete brand kit to Notion, Google Drive, or downloadable PDF. Use this skill when the user says things like: 'create a brand for...', 'build a brand identity', 'I need a logo for...', 'brand kit for my business', 'check if this domain is available', 'find me a username for...', 'b...

AI-powered coffee cupping assistant by Catador Pro (catador.pro). Guides users through professional cupping sessions following SCA Arabica, SCA Robusta, Cup of Excellence, and CVA protocols. Analyzes uploaded cupping forms and score sheets (PDF, images, text), identifies flavors using the SCA Flavor Wheel, calculates scores accurately, generates visual HTML reports with spider charts, and educates on cupping techniques and coffee science. Use this skill whenever the user mentions coffee cuppi...

Content marketing calendar and media plan generator. Creates a complete content calendar (1, 2, or 4 weeks) with a post-by-post schedule, format examples with AI-generated sample images, and a brand strategy summary. Stores results in Notion and/or exports a local HTML file. Use this skill when the user wants to plan their social media content, create a content calendar, build a posting schedule, develop a content strategy, get a media plan for their brand, or says things like 'create a conte...

Resume and CV builder that creates professional, deployable web resumes from any source (PDF, DOCX, TXT, MD, HTML, URL, LinkedIn, Notion). Acts as an expert recruiter: extracts information from multiple files, interviews the user to refine content, researches the target industry to give informed advice, suggests improvements and optimal organization, generates a professional AI headshot from a reference photo, and builds a polished single-page HTML resume with PDF download — deployed instantl...

Interactive feature planning assistant that pulls a spec template from Notion, walks the user through filling it out step-by-step, and creates a completed feature spec as a new Notion page ready to paste into Claude Code. Use this skill whenever the user wants to plan a new feature, start a new page or screen, spec out a UI, create a feature brief, or says things like "let's plan a feature", "new feature spec", "I want to build something new", "help me spec this out", "create a feature plan",...

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics. Auto-detects project context (Rails+Inertia, standalone React, or plain HTML) and generates code that fits.

Generate professional invoices for freelancers and contractors. Creates a polished HTML invoice with live preview and download button, saved to /invoices. Stores contractor info (company name, address, phone) in a config file so it's only entered once. Asks for client name, email, line items, and optional payment terms each time. Auto-numbers invoices per client (saleshood_001, saleshood_002, etc.) and auto-dates to today. Supports multiple languages and currencies. The user can customize the...

Research-driven landing page generator. Pulls data from social media, websites, Google Maps, YouTube, forums, and optionally a CV to build a complete profile of a company or person. Analyzes the data as a marketer to extract competitive advantages, value props, audience insights, and brand voice. Then generates a compelling landing page with AI-generated images tailored to the audience. Use this skill when the user says things like: 'create a landing page for...', 'build a website for this bu...

Research-driven presentation generator. Creates self-contained HTML slide decks with keyboard navigation, transitions, and responsive design. Starts from a document, URL, file, pasted text, or image — or walks through guided questions and multi-source research (social media, news, finance, trends, ads, YouTube, app stores, Google Maps reviews, web scraping). Supports multiple presentation types (pitch deck, sales, marketing, business model canvas, portfolio, etc.) and visual styles (minimalis...

Initialize a new project from the rails-ai-kit starter kit. Clones the repo, creates a new GitHub repository, remaps git remotes (origin → new project, upstream → rails-ai-kit), runs bin/setup, and verifies the app boots. Use this skill when the user says things like: 'start a new rails-ai-kit project', 'scaffold a new app from rails-ai-kit', 'create a new project from the kit', 'init rails-ai-kit for...', 'new project called...', 'clone rails-ai-kit as...', or wants to bootstrap a new Rails ...

Skill development assistant that creates new Claude Code skills following Anthropic's official conventions. Guides through requirements gathering, resource planning, SKILL.md authoring, and validation. Use this skill when the user says things like: 'create a skill', 'build a new skill', 'make a skill for...', 'new skill for...', 'I want a skill that...', 'add a skill to the repo', 'skill for...', 'write a SKILL.md', or wants to create, scaffold, or develop a Claude Code skill.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

HIPAA compliance autopilot. Loops through ALL controls: scans infrastructure, fixes what it can, asks questions for interview-only controls. The "just handle it" command.

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode. Use this skill when the human user needs help, status, or reference about hcom - when user asks questions like "how to setup hcom", "hcom not working", "explain hcom", or any hcom troubleshooting.

multi-agent communication and coordination for Claude Code, Gemini CLI & Codex. Use this skill when the human user needs help, status, or reference about hcom - when user asks questions like "how to setup hcom", "hcom not working", "explain hcom", or any hcom troubleshooting.

图鉴.skill — 跨作者 persona skill 智能调度器 / Cross-author persona skill router that lives in your IDE. 当用户需要在整个 persona skill 生态(花叔 nuwa / titanwings colleague / 各位单 persona 作者)中跨作者发现、推荐、组合召唤 persona skill 时使用。这是中文世界唯一的 in-IDE 跨作者 persona router,覆盖 30+ 精选 persona,远程精选库每周更新。 正向触发(中文):「找 persona」「找人物 skill」「推荐 persona」「装个 persona」「有什么人物 skill」「想用 X 视角」「X 会怎么想」「X 会怎么看」「X 会怎么做」「用 X 的角度」「该不该」「要不要」「帮我想清楚」「借脑」「借 X 的脑」「想跟 X 聊」「扮演 X」「我前任」「我导师」「我师兄」「我老板」「我同事」「我暗恋的」「我初恋」「我妈」「我父母」「我家人」「想跟马斯克 / 乔布斯 / Naval / 芒格 /...

CortexFS Memory Skill - Persistent cognitive memory layer backed by CortexFS CLI. Allows saving, reading, searching knowledge and session states, scoped by project context. Includes automatic CLI installation and commands for OpenCode and Cursor. Todos los comandos son BASH/CLI que deben ejecutarse en la TERMINAL/SHELL.

Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分

Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. 广告创意/广告文案/RSA标题

Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading...

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calc...

Use when the user asks to "build audience segments from my customer list", "make value-based / lookalike seed lists", "set up exclusion / suppression segments", or "map audiences to funnel stages across platforms"; turns the user''s OWN customer/CRM/GA4 export into seed audiences, value-based lookalike SEED lists, exclusion/suppression segments, and a cross-platform funnel-stage targeting map, informing the ROAS A (Audience) dimension. Not for building account structure or match types — use c...

Use when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a bid-strategy choice (tCPA / tROAS / max-conversions / manual CPC), the starting target math, a portfolio grouping map, and a learning-phase entry plan. Not for splitting the budget across campaigns — use budget-optimizer; not for in-flight pacing/scale moves — use budget-pacing-monitor; not for scoring the account — use ad-account-auditor. 出价策略/tCPA目标/tROAS/学习期

Use when the user asks to "check pacing", "am I over/under-spending", "is this campaign on track to hit budget", or "why did spend spike/stall mid-flight"; returns a spend-vs-target-curve read, learning-phase status, an over/under-delivery call, and a reallocation trigger. Not for initial budget allocation — use budget-optimizer; not for choosing the bid strategy — use bid-strategy-planner; not for the RQS gate — use ad-account-auditor. 付费广告预算节奏监控/跑量过快过慢/在途配速

Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension + structure. Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site archi...

Use when the user asks to register/query a social channel, record channel state, cadence, governance, voice adaptation, UGC permission, or advocacy facts; curates them through the append-only channels event stream and derived views. Not for ECHO scoring — use social-quality-auditor; not for channel selection — use channel-portfolio-planner. 渠道台账/账号档案/UGC授权记录

Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a warmup + send-throttle ramp schedule, jurisdiction opt-in/CAN-SPAM guardrails (guidance, not legal advice), and a SEND S-dimension read. Not for B2C lifecycle flows — use email-seque...