Install once. Invoke anywhere.

Reusable agent skills for every repository.

Browse curated skills with install commands, trigger phrases, and quality signals so your agents ship faster with less guesswork.

26k+

Indexed skills

180+

Topics & tags

12M+

Weekly install events

Top 1%

Rising skills surfaced

Skills library

Filter by topic, language, and quality signals—then open any skill for install steps and repository context.

Official Only

26355 skills

Ctrl+K
verification-rules
Python

4-layer verification system for task completion. Use when verifying that a task has been fully completed before marking it done.

issue-maker
Python

Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.

parse-video
Python

根据 todolist.md 使用 MCP 解析视频元数据并下载。读取任务清单,调用 MCP 服务下载视频和封面,保存元数据 JSON,更新任务完成状态。

testcase-generator
Shell

基于 TestFlow 四阶段工作流的智能测试用例生成器。当用户需要为 Story/需求/缺陷生成测试用例、创建 Markdown 格式的 markmap 思维导图测试用例、根据技术方案设计测试场景、或者需要生成测试覆盖矩阵时使用。支持功能测试、边界测试、异常测试、兼容性测试、性能测试、安全测试等多种测试类型。

systematic-debugging
Shell

Invoke when debugging failures. MANDATORY when 3+ fix attempts have failed. Enforces root cause investigation before fixes.

evaluate-brand
Branding

This skill forecasts a brand name's potential success by evaluating domains, social handles, trademarks, pronunciation, international meanings, similar

MarketingProductResearchSocial Media+2
peekaboo
Shell

Use when working with the Peekaboo CLI or MCP server to capture macOS screens, inspect UI elements, and automate GUI interactions (see/click/type/scroll/hotkey/window/menu/dock/space), or when troubleshooting Peekaboo permissions, snapshots, or focus issues.

security-audit

Use when conducting security reviews, investigating vulnerabilities, or creating security documentation - provides systematic methodology for code audits with severity assessment, dual documentation patterns (client + internal), and acceptance-focused ticket creation

go-development
Backend

This skill guides robust Go development with domain-driven design, proper context propagation, and structured logging for scalable, maintainable apps.

Code ReviewDebuggingMonitoringObservability+2
mcp-builder
Shell

创建高质量 MCP(Model Context Protocol)服务器的指南,使 LLM 通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用,无论是 Python(FastMCP)还是 Node/TypeScript(MCP SDK)。

review
Code Review

This skill conducts thorough Lua code reviews focusing on quality, security, and alignment with project standards to guide PR decisions.

DocsLintingSecurityTesting+1
interview
Typescript

Ask clarifying questions before implementing. Only trigger on `/interview`.

example-skill
Shell

An example skill demonstrating the Agent Skills format. Use this as a template for creating your own skills.

olakai-get-started
Shell

Get started with Olakai - install, authenticate, and set up your first agent. AUTO-INVOKE when: CLI is not installed, user is not authenticated, user asks about getting started with Olakai, user wants to try Olakai, user mentions they don't have an account yet, or when other skills fail due to missing prerequisites. TRIGGER KEYWORDS: get started, setup, install olakai, olakai account, sign up, signup, new to olakai, try olakai, olakai onboarding, first agent, getting started, no account, create account, register. DO NOT load for: users who are already authenticated and have agents set up (use olakai-create-agent, olakai-add-monitoring, or olakai-troubleshoot instead).

ruby
Ruby

Comprehensive Ruby development skill covering language fundamentals, object-oriented design patterns, error handling strategies, performance optimization, modern Ruby 3.x features (pattern matching, ractors, typed Ruby), testing patterns, metaprogramming, concurrency, and Rails-specific best practices. Use when writing Ruby code, refactoring, implementing design patterns, handling exceptions, optimizing performance, writing tests, or applying Ruby idioms and conventions.

api-integration
Python

Design and implement REST API integrations with proper error handling, authentication, rate limiting, and testing. Use when building API clients, integrating third-party services, or when users mention API, REST, webhooks, HTTP requests, or service integration.

prompt-design
Ai

This skill helps you design reusable xmcp prompts by guiding parameterized prompt creation and metadata generation for scalable workflows.

AutomationCode ReviewDocsWriting
frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when user asks to build web components, pages, or applications. Activates when user says "build UI", "create component", "design page", "make it look good", mentions "frontend", "CSS", "styling", or asks for visual improvements.

database-schema-design

Database schema design patterns for SQL and NoSQL databases

wcag-audit-perceivable-layout-deep
Javascript

Page structure and spatial organization accessibility design patterns

news-intelligence-agent
Python

Batch news analyzer for /news page. Processes multiple news articles simultaneously, extracting sentiment, keywords, themes, and ticker mentions. Generates aggregated market intelligence including trending topics and ticker buzz scores.

FAQ

Frequently Asked Questions

Common questions about agent skills, how they work, and how to use this directory.

An agent skill is a packaged unit of behavior, including prompts, tool wiring, and documentation, that you can install into a compatible AI agent or IDE to give it a new capability. Instead of re-explaining a task every time, you install a skill once and the agent can invoke it whenever it is relevant. This directory lists skills you can use with clients like Claude Code, Codex, and other compatible agents.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational