AI Skills Hub - Browse 180,000+ Agent Skills

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).

Build and deploy PostgreSQL-compatible serverless distributed SQL databases with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when wanting a good solution for developing a scalable or distributed SQL database, user asks to use Amazon Aurora DSQL, or a project is already built with DSQL. Includes MCP tools for direct database interaction.

Create pull requests with summary from Ralph progress

Debug SystemVerilog testbench failures in the SVC project. Use when a

Generate a visual summary image from V2EX topic analysis using nanobanana (Gemini image generation). Use after v2ex-topic-analyzer to create an engaging visual summary of the discussion; requires GEMINI_API_KEY and GEMINI_API_ENDPOINT environment variables.

Create, edit, and structure Reveal.js lecture slides in this repo using `index.html` and `theme/custom.css`. Use when asked to draft slides, adjust layouts, reorganize sections, or enforce slide design standards for the Introduction-to-Informatics course (practical tone, 180 minutes / ~90 slides by default).

Fetch and crawl llms.txt files from websites. Parses the llms.txt format to extract page URLs and downloads all listed content. Use when you need to gather documentation or content from a website that provides an llms.txt file.

Copy Claude Code skills from GitHub repositories into local .claude/skills directory. Use when the user wants to install, download, or copy a skill from GitHub, or mentions a GitHub URL to a skill they want to add.

Skill para comunicacao entre agentes Claude em containers. Permite enviar mensagens, broadcasts, coletar resultados e gerenciar estado compartilhado via Redis. Use quando precisar que agentes conversem entre si.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Update Storybook visual regression snapshots after intentional UI changes. Use when visual tests fail due to expected changes, or when asked to update snapshots.

Risk analysis for trading strategies including Kelly criterion calculations, tail risk metrics, and Monte Carlo projections. Use when exploring position sizing, capital allocation, or understanding worst-case characteristics.

Run examples:start-all in auto mode with parallel execution, per-script logs, and start/stop helpers.

Browser automation for visual testing, accessibility audits, and DOM inspection using Playwright. Use this skill when users need to: (1) Run accessibility (a11y) audits on websites and generate reports, (2) Take screenshots of web pages (full-page or elements), (3) Compare screenshots to detect visual changes, (4) Inspect or select DOM elements interactively to get context for modifications, (5) Connect to an existing browser session or navigate to URLs for testing. Triggers on: "a11y audit", "accessibility check", "screenshot", "visual diff", "compare screenshots", "element picker", "inspect element", "DOM context", "what's on this page", "browser automation".

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Deploy Rails applications with Kamal (Docker + SSH). Use when: (1) Creating or modifying deploy.yml configuration, (2) Setting up new server deployments, (3) Configuring kamal-proxy, SSL, or accessories, (4) Writing deployment hooks, (5) Managing secrets with 1Password/Bitwarden/LastPass, (6) Troubleshooting deployment issues, (7) Setting up multi-server or multi-destination deployments.

Generate AI images with templates and style references. Use when creating images/illustrations/diagrams, managing templates or style references, choosing image providers (Gemini, OpenRouter, VertexAI), or when the user mentions /create-image (including /create-image help).

Implement single-writer queue pattern for SQLite in multi-process environments. Use when building CLI tools, local apps, or agent systems where multiple processes may write to SQLite concurrently. Covers file locking (flock/LockFileEx), WAL mode, timeout handling, and diagnostic error messages. Works for Go, Rust, Python, JavaScript/Node.

Create and debug rich link previews (Open Graph + Twitter/X Cards) for iMessage, WhatsApp, Slack/Discord, and social platforms. Use when user asks about og tags, twitter cards, link previews, social sharing metadata, or when a shared link preview looks wrong or missing.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Interact with the Up Banking API to query accounts, transactions, categories, and tags. Use when the user wants to: - Check account balances or list accounts - Search or filter transactions (by date, category, tag, status) - Analyze spending patterns or generate summaries - Categorize transactions or manage tags - Set up or manage webhooks for real-time notifications Requires UP_API_TOKEN environment variable.

Automate Unreal Engine (UE) C++ code changes, validation, and build/package runs on local machines. Use when a user asks to implement UE code, check correctness, compile/build, cook/package, or diagnose build errors for a UE project (typically `.uproject` + UnrealBuildTool/RunUAT).

Builds precise production-ready custom Agent Skills following AgentSkills.io guidelines. Use when user requests to create, refine or package Skills

Sets up Cypress E2E testing environment. Invoke when configuring automated testing for full-stack applications or when needing to run end-to-end tests.

Browser automation via Puppeteer CLI scripts (JSON output). Capabilities: screenshots, PDF generation, web scraping, form automation, network monitoring, performance profiling, JavaScript debugging, headless browsing. Actions: screenshot, scrape, automate, test, profile, monitor, debug browser. Keywords: Puppeteer, headless Chrome, screenshot, PDF, web scraping, form fill, click, navigate, network traffic, performance audit, Lighthouse, console logs, DOM manipulation, element selector, wait, scroll, automation script. Use when: taking screenshots, generating PDFs from web, scraping websites, automating form submissions, monitoring network requests, profiling page performance, debugging JavaScript, testing web UIs.

Automate first-pass customization of a new ShipAny Nano Banana (AI Image Generator) project from a short project brief. Use when the user says they are starting a new AI image generation project.

Table Structure Recognition (TSR) skill to extract structured tables from table images. Use when the user provides a table image and asks to convert it into OTSL and/or HTML, validate table structure, or troubleshoot TSR output. Supports two backends: (1) dedicated TSR VLM at vllm-vlm-tsr-1 (model agilesoda/vlm-tsr) and (2) perception VLM at vllm-vlm-perception-1 (model nanonets/Nanonets-OCR2-3B) which may return HTML directly or OTSL-like tags that need conversion.

Use when setting up git pre-commit and pre-push hooks - provides simple shell script approach and pre-commit framework method, both calling justfile commands for DRY principle

This skill should be used when the user asks to "find past conversation", "search session history", "where did we discuss X", "find when I worked on Y", or "search old sessions by keyword". Searches Claude Code session files in ~/.claude/projects/ by topic, keyword, or date.

Web crawler that converts URLs to clean markdown. Use when user wants to fetch a webpage, extract web content, convert URL to markdown, or scrape website content.

Creates Next.js API routes with Firebase. Use when adding GET/POST/PATCH/DELETE endpoints, implementing pagination, adding auth checks, or handling file uploads. Includes route templates and error handling.

Define, review, and scaffold Go service directory structures using hexagonal (ports-and-adapters / “jexagonal”) architecture and Go best practices. Use when creating or refactoring Go services, deciding package boundaries, organizing cmd/internal/api/config/deploy/migrations, or choosing layouts for common service types (HTTP REST API, gRPC API, async worker/consumer, scheduled job, CLI, multi-binary repos).

Create sophisticated economic data analyses and visualizations for higher education stakeholders using FRED (Federal Reserve Economic Data). Use this skill when users request: (1) Analysis of student loan debt, unemployment by education level, or earnings data, (2) Dashboard or visual presentations of higher ed economic indicators, (3) Narrative reports on higher education ROI or economic value, (4) Data-driven communications for institutional stakeholders (trustees, enrollment management, financial aid offices), or (5) Integration of FRED API data into interactive visualizations.

RSS/Atom 信息源聚合摘要。使用此 skill 当用户要求：(1) 获取 RSS/Feed 摘要，(2) 查看订阅源更新，(3) 总结今日信息流，(4) 分析多个信息源内容。支持智能分类、10分制评分筛选、关键词过滤。

Automates GitHub workflows including batch issue creation from JSON/CSV, PR creation with issue linking, pre-PR testing, and WordPress-specific validation (PHP linting, WPCS). Use when creating multiple issues, automating PR workflows, or validating WordPress code before commits.

Browser automation skill using browser-pilot CLI. Use this when you need to control a web browser - navigate to URLs, fill forms, click buttons, extract page content, or take screenshots. Works with local Chrome, BrowserBase, and Browserless providers.

Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution. Each call runs in fresh context.

Email operations skill for sending, fetching, and reading emails via IMAP/SMTP. Uses curl with OpenSSL/LibreSSL for reliable TLS compatibility with Tencent Enterprise Mail and other providers. Credentials are securely stored in macOS Keychain.

Post content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation.

Use when you need to download tikv/tiflash/s3clean logs from a Kubernetes cluster using scripts/copy_logs_from_k8s.py, including selecting specific sources and saving per-pod folders.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use for panel data analysis with fixed/random effects. Triggers on panel data, fixed effects, random effects, FE, RE, Hausman test, clustered standard errors, dynamic panel, GMM, Arellano-Bond, two-way fixed effects, TWFE, within estimator, entity effects, time effects.

Difference-in-Differences estimator with Top Journal standards (AER/MS). Includes rigorous diagnostics, placebo tests, and publication-quality reporting.

Use when estimating causal effects with Instrumental Variables. Triggers on IV, instrumental variable, 2SLS, two-stage least squares, LIML, endogeneity, weak instrument.

Use for exploratory data analysis in econometric research. Triggers on EDA, data exploration, data quality, missing values, outliers, distributions, correlation analysis, multicollinearity, panel data variation, attrition analysis.

-用户一般会提问：review [MR_IID]

Cancel an active dev-loop session and clean up resources.

This skill provides patterns for restoring campaign context across Claude sessions. Use when resuming campaigns or recovering from interruptions.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Search past reasoning for relevant decisions and approaches

Meta-skill for creating and managing Claude Code skills

Build reliable HubSpot ↔ Airtable sync workflows. Covers API selection, rate limits, sync architecture, and n8n implementation patterns.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

将Word格式的法律协议文档（用户协议、隐私协议、法律条款）转换为美观的响应式H5页面。仅处理用户指定的单个文件，不联想生成其他文件。当用户请求：转换指定Word文件为HTML、查看Word文档的H5效果、在浏览器中预览Word协议时使用此技能。

Find and localize untranslated user-facing strings in React components. Use when asked to localize,

Defines how implementation plans are written, structured, critiqued, and revised. Use when creating or updating ai/plan.md.

Best practices for designing UI widgets in xmcp. Use when creating interactive widgets for GPT Apps or MCP Apps, choosing between React components and template literals, designing widget layouts, handling state and data fetching, or troubleshooting widget rendering issues.

Build, test, and package Windows applications. Includes iterative development workflow, regression prevention, automated validation, and delivery checklists. Condensed from windows-app-standards-modular (392KB → ~25KB). Use when: "start coding", "implement feature", "fix bug", "create package", "ready to deliver".

Kit de ferramentas para interagir e testar aplicativos web locais usando Playwright. Suporta verificação de funcionalidade de frontend, depuração de comportamento de UI, captura de capturas de tela do navegador e visualização de logs do navegador.

Use when implementing motion design, timeline animations, visual animation editors, animating Three.js/R3F scenes, creating keyframe animations, or using Theatre.js, @theatre/core, @theatre/studio, @theatre/r3f, theatric, or building animation tooling for the web.

Resize designs to different dimensions. Use this skill when user wants to adapt a design for different platforms or sizes. Creates a new resized copy without modifying the original. Premium feature - requires Canva Pro or higher.

Import files into Canva (PPTX, PDF, AI, PSD). Use this skill when user wants to upload documents for editing in Canva. Supports file upload and URL import. Follows 3-mode workflow for safe operations. For uploading images/videos use canva-asset-manager.

Activate for marketing analytics, KPI tracking, reporting dashboards, attribution analysis, and performance optimization. Use when analyzing campaign data, creating reports, or measuring marketing ROI.

Upload and manage assets (images, videos, audio) in your Canva account. Use this skill when user wants to upload files to Canva, manage their asset library, or work with uploaded media. Handles image, video, and audio uploads. Follows 3-mode workflow. For organizing uploaded assets use canva-folder-organizer.

Expert guidance on API security, web application security, authentication, and authorization. Use this skill when working with JWT tokens, OAuth 2.0/OIDC flows, Keycloak configuration, Spring Security implementation, ABAC/RBAC policies, secure API design, vulnerability assessment, security headers, CORS, CSRF protection, or any authentication/authorization architecture decisions. Triggers on questions about securing APIs, implementing auth flows, configuring identity providers, token validation, access control patterns, security best practices, penetration testing concepts, OWASP guidelines, or debugging security issues in Spring/Keycloak environments.

Use this skill when managing OpenCode extensions with OCX (OpenCode eXtensions). This includes installing components from registries, using Ghost Mode for cross-repository development, auditing changes with SHA-256 verification, managing dependencies, configuring registries, or performing component updates and version management. Invoke for tasks involving ocx init, ocx add, ocx update, ocx diff, ocx ghost, or OCX registry operations.

Write Python in n8n Code nodes with _input/_json syntax and standard library.

Interpret n8n validation errors, warnings, and profiles to fix workflow issues.

Write JavaScript in n8n Code nodes with $input/$json syntax, $helpers, and DateTime.

Write integration tests for the Autumn billing system. Use when creating tests, writing test scenarios for billing/subscription features, track/check endpoints, or when the user asks about testing, test cases, or QA.

Validate design doc structure and frontmatter. Use when checking design docs for compliance, ensuring proper formatting, or verifying metadata before commits.

Markdownコンテンツから学生ノート風・ビジネス風などのインフォグラフィックを自動生成

Generate UML diagrams (state machines, class diagrams, etc.) from natural-language requirements by writing Umple code and running Umple CLI.

Integration test writing agent using BATS (Bash Automated Testing System) framework. Use when user says "write tests", "create BATS tests", "add integration tests", "bash tests", "test coverage", "write test cases", "shell script tests", "create unit tests", "BATS framework", "testing bash scripts".

负责将生成的 Article JSON 上传至数据库，并清理临时文件。

Post content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Supports Traditional Chinese.

Post content to Tencent Docs (腾讯文档). Supports creating new documents with title and content. Uses Chrome CDP automation. Supports Simplified Chinese, Traditional Chinese, English.

Post content to LinkedIn. Supports text posts and images. Uses Chrome CDP automation. Supports English, Simplified Chinese, Traditional Chinese.

Create new Claude Code skills with proper structure, validation, and best practices. Generates skills that follow Anthropic specifications and community patterns. Use when you need custom skills for specific workflows, either globally or per-project.

Drizzle ORM + PostgreSQL database layer. Use for db, database, query, schema, table, migrate, sql, postgres, drizzle, model, relation

TanStack Router file-based routing. Use for routes, params, search params, navigation, loaders, auth guards, layouts, nested routes, redirect

Summarize single-cell dataset information across formats (.rds/.qs Seurat or SummarizedExperiment, .h5ad AnnData, 10X .h5, 10x MTX). Use when users want a quick overview of cells/genes, QC summaries, assays, metadata fields, reductions/clusters, sparsity, and output as terminal table, JSON, or Markdown with optional file save.

This skill should be used when managing homepage/CV content - updating personal info, adding/editing/removing work experience, education entries, or skills. It provides an interactive workflow for content management with data stored in TypeScript files.

This skill should be used when managing portfolio projects - adding new projects, editing existing ones, or removing projects. It provides an interactive workflow starting with listing existing projects.

智能图片拼接工具，自动检测重复内容、删除多余导航栏、计算最佳拼接位置；适用于长截图拼接、滚动屏幕内容拼接、聊天记录拼接等场景

Upload local folders or files to GitHub using gh + git: create a new repository, push to an existing repository, convert nested git repos into proper submodules, or upload a file as a GitHub Gist. Use when the user asks to publish a local project (e.g., blog/Hugo site), upload a folder to GitHub, push a directory to a new repo, add/commit/push files to an existing repo, or share a file via gist.

Use when encountering any bug, test failure, or unexpected behavior in this project, before proposing fixes

Create custom slash commands for Claude Code with proper markdown structure and YAML frontmatter. Use when creating commands, generating slash commands, making workflow automations.

Deploys verified gameweek data to staging and production. Use ONLY after the user has verified the data locally using fetch-gameweek skill.

Define, review, and scaffold Go service directory structures using hexagonal (ports-and-adapters / “jexagonal”) architecture and Go best practices. Use when creating or refactoring Go services, deciding package boundaries, organizing cmd/internal/api/config/deploy/migrations, or choosing layouts for common service types (HTTP REST API, gRPC API, async worker/consumer, scheduled job, CLI, multi-binary repos).

Use when working in this dotfiles repository - modifying shell configs, SSH, neovim, or scripts. Covers symlink architecture, agent selection, and permission model.

评分计算引擎 - RICE/ICE/DREAD评分、MoSCoW分类、价值复杂度矩阵、ROI计算

Global Exception Filters and standard error formats.

Complete commit workflow - format, archive, update changelog, and commit in one operation.

Post content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation.

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Verifies UI tests catch the bug. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).

Write effective, type-safe Kysely queries for PostgreSQL. This skill should be used when working in Node.js/TypeScript backends with Kysely installed, covering query patterns, migrations, type generation, and common pitfalls to avoid.