Skills

A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. This section collects skills for Claude Code, Cursor, Codex and other agents, each with an install command, a risk level and a plain description of who needs it and when.

Match with Foxx AI

Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.

Found: 76

A skill that builds in-app screen and element capture for a SwiftUI app and loops it across every locale for the App Store

Medium risk260Repository stars

Erich Owens' large Claude Code skill marketplace: design, computer vision, engineering, career, plus two MCP servers

Medium risk237Repository stars

Creative Director

Creative Director Skill

A creative director skill: insights, ideas via SIT and TRIZ, Cannes-calibrated scoring and checks against a library of landmark campaigns

Low risk233Repository stars

A skill that turns an agent into an MBB-grade strategy consultant: problem structuring, frameworks, market sizing, case work

Low risk126Repository stars
Russian stack

A skill for auditing and running Yandex Direct campaigns via API v5: 55 checks, an A-F grade, ad creation and reports

High risk52Repository stars
Russian stack

Claude Code skills for product and UX work: website UX audit, requirement docs, a PMF cycle, text clustering and ADRs

Medium risk51Repository stars

Yandex Direct Docs Skill

Yandex Direct Docs

Russian stack

509 articles from Yandex Direct's official help center in Markdown as a SKILL.md skill, so the agent answers on campaigns, bidding and moderation with a source

Low risk28Repository stars
Russian stack

Search tours, hotels, flights, trains and excursions via Aviasales, Travelata, Level.Travel, Tutu.ru, Tripster and Sputnik8

Medium risk17Repository stars
Russian stack

Five cache-first shell skills for Direct, Metrika, Webmaster, Wordstat and Search API, with Claude choosing which one to run

High risk13Repository stars
Russian stack

An OpenClaw skill that tracks orders, prices and stock on Ozon, Wildberries and Yandex Market from one interface

High risk12Repository stars
Russian stack

A skill pack for Yandex 360: Mail, Calendar, Contacts, Directory, Telemost, Disk, Forms and Tracker

High risk10Repository stars
Russian stack

A first-pass contract review skill under Russian law: Civil Code, 152-FZ, Roskomnadzor, personal data

Low risk4Repository stars

Ozon shopper skill

Ozon Shopper

Russian stack

A skill for searching Ozon products with seller checks, spec validation and scam detection against a red-flag checklist

Medium risk3Repository stars
Russian stack

A skill for reading and searching email over IMAP via the myl CLI: Gmail, Yandex Mail, Mail.ru, autodiscovery for others

Low risk2Repository stars
Russian stack

A Claude skill that audits a website and its documents against Federal Law 152-FZ using a 55-point checklist, with fine estimates and a fix plan

Medium risk2Repository stars

Yandex SEO audit

yandex-seo-audit

Russian stack

A Claude Code skill for technical SEO audits under Yandex requirements: canonical tags, JSON-LD, robots.txt, favicon and Webmaster diagnostics

Medium risk1Repository stars

152-FZ personal data audit

152fz-data-audit-skill

Russian stack

A 152-FZ personal data audit skill: where the database lives, what leaves Russia, who really has access and what never gets deleted

High risk1Repository stars
Russian stack

A skill that checks a website against Russian law: personal data, cookies and trackers, operator details, advertising and login methods

Medium risk1Repository stars

Yandex Direct planning and audit skill

Yandex Direct Skill for Codex and AI agents

Russian stack

A read-only Codex skill: Unified Performance Campaign structure, Search and YAN, negatives, moderation, strategies and Metrika goals, without API access

Low risk

Bitrix24 for Claude Code

Битрикс24 для Claude Code

Russian stack

A single-file skill directly on the Bitrix24 REST API instead of a third-party MCP: the webhook never leaves the portal, token masking, no deletes

Medium risk
Russian stack

An evidence-based SEO audit skill using signals from the Google Content Warehouse API leak, plus a Russian 152-FZ and Roskomnadzor launch checklist

Low risk
Russian stack

An OpenClaw agent skill: a reference for the Yandex Metrika API and rules for picking the right report, Logs call and OAuth token

Medium risk

Frequently asked questions

What is a skill for an AI agent?

A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. The agent picks it up and solves the task by the defined scenario.

How do I install a skill?

Each entry has an install command for a specific agent: Claude Code, Cursor, Codex and others. Usually you copy a folder into the skills directory or install it through a plugin manager.

How is a skill different from an MCP server?

A skill gives the agent knowledge and a sequence of actions, an MCP server gives access to external data and tools over a protocol. They are often used together.