2,118 skills
Use when managing or interacting with favorite blogs via the BlogWatcher CLI—adding/removing blogs, scanning for new posts, listing articles, marking read/unread, or modifying related CLI behavior, scanning, storage, and tests.
A Cashu ecash wallet CLI for Bitcoin and Lightning payments. Use when managing Cashu tokens, sending/receiving payments via Lightning (bolt11) or ecash, handling HTTP 402 X-Cashu payment requests, or viewing wallet history.
Modern clean architecture workflow for Android (Kotlin, Compose/XML, coroutines) and Flutter (Dart, widget/state architecture). Use when designing new features, refactoring legacy modules, auditing code quality, or upgrading architecture and async patterns with low-risk, incremental changes.
Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and merge (consolidate batch results). Checks endpoints for missing ownership or authori…
Create a full frontend page following the 4-layer architecture (Page -> Container -> Component) with strict separation of concerns.
Generate production-ready Terraform code using Azure Verified Modules (AVM). Use when asked about Azure infrastructure, Terraform module selection, or infrastructure-as-code generation.
Integrate PayPal payment processing with support for express checkout, subscriptions, and refund management. Use when implementing PayPal payments, processing online transactions, or building e-commerce checkout flows.
<ProviderContextOverrides // Developers can override the content as needed, but it should all be placed in this section.
Submit a plan, code, or question to Claude Code for a second opinion. Use this skill when you want to challenge Vibe's proposed approach with Claude's opinion, or for any external review.
Audits WordPress plugin or theme PHP code for internationalization (i18n) correctness — text-domain consistency, use of escaped translation helpers (esc_html__, esc_attr__, esc_html_e), correct placeholder helpers (sprintf with translator comments, _n for plurals, _x for context), no variable text-…
Design-first MCP for coding agents that improves websites with screenshot-grounded iteration.
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
Set up and configure Replay for recording Cypress tests with time-travel debugging.
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
Review Goodfill frontend UI/UX from the perspective of older Thai adults, caregivers, and daily health users. Use when asked to inspect layouts, mobile/desktop responsiveness, hero/card/navigation clarity, voice/chat controls, screenshots, browser previews, accessibility, or "ตรวจ UI/UX" for Goodfi…
Create comprehensive CLAUDE.md files with tech stack, standard commands, repository structure, and boundaries to optimize repositories for AI-assisted development
Build distinctive, production-grade frontend interfaces with a strong visual point of view. Use this skill for pages, components, or applications that need polished design and non-generic aesthetics.
Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Generates valid JSON-LD structured data for 10 schema types with rich result eligibility validation and implementation-ready script blocks. Activate when the user wants to generate schema markup, JSON-LD, or structured data for any page.
Manage persistent memory and context notes across coding sessions with organized file-based storage. Use when saving preferences, patterns, project-specific knowledge, or session state for AI assistants.
Launch Claude Code Wrapped — an interactive Spotify Wrapped-style slideshow of your Claude Code usage stats in a new terminal window. Use when the user asks for their Claude Code usage summary, wants a year-in-review recap, mentions 'wrapped', or types /wrapped.
Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
Forces the minimal working solution — least code, fewest files, no speculative abstraction. Channels a senior dev applying YAGNI: stdlib, native platform features, and existing dependencies over custom code. Three levels: lite (name the lazier option, user picks), full (enforce the ladder), ultra (…
Generate agents, agent configurations, system prompts, and agent registry entries. Use when creating agents, modifying agent behavior, or when the user mentions research agent, coding agent, chat agent, or multi-agent coordination.
金蝶云苍穹开发主 Skill，优先复用 kd-cd-cosmic-commons 封装。适用于插件开发、单据/列表/表单逻辑、操作服务、BOTP 转换、后台视图打开、附件处理、DynamicObject 与元数据处理、弹性域解析及 OpenAPI 集成。默认优先使用仓库封装；在涉及原生插件事件、SDK API、方法签名或封装未覆盖场景时，使用内置脚本进行查询。
Run pr-review twice in parallel — once in this Claude session, once via OpenAI's Codex CLI — then merge the findings into unique-to-each / agreed-by-both buckets followed by both raw reports. Use when the user says "dual-review PR
从中文互联网平台（小红书/B站/牛客/脉脉等）采集真实社招面试真题，只保留有明确来源的实际被问题目，过滤泛泛而谈内容。 支持 AI Agent、后端、前端、产品、测试、UI设计、算法 7 大角色，自动识别角色并加载专属知识模块配置， 输出带来源标注+公司分类+轮次标签的 Markdown 题集，并为每道题生成解答思路与参考答案。 触发词：面试题采集、收集XX面试题、更新面试题集、刷新面试题、跑一次面试题采集、整理面试题、XX面经、XX面试真题。 未指定角色时默认采集 AI Agent 面试题。
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, …