Просматривайте и устанавливайте тысячи навыков AI Agent в каталоге Killer-Skills. Совместимо с Claude Code, Windsurf, Cursor и другими.
Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.
Release a new version of cqs. Bumps version, updates changelog, publishes to crates.io, creates GitHub release.
Use when searching for open-source resources, themes, components, libraries, or examples. Triggers on keywords like find, search for, look for, discover, open source, github, npm, template, example, boilerplate.
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
The make-yt-issue skill ensures YouTrack issue creation and management, benefiting developers by automating workflow and enhancing productivity with AI coding assistance.
React 19 and Next.js 16 performance optimization for the Arcanea platform. Use when writing, reviewing, or refactoring React components, data fetching logic, bundle optimization, or any frontend performance work. Triggers on: React components, Next.js pages, hooks, data fetching, bundle size, re-renders, Server Components, Client Components, hydration. Sourced from Vercel Engineerings official React best practices (57 rules, 8 categories) and adapted for the Arcanea stack.
Cross-repo testing facilitates end-to-end testing of features spanning SDK and Cloud backend, benefiting developers with efficient AI-driven development. It enables testing of new API endpoints and unreleased SDK packages.
Generate customizable widget plugins for the prompts.chat feed system
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator
V3 Core Реализация - это техника реализации ИИ Агентов, следующая принципам Domain-Driven Design и чистой архитектуры.
Checklist-driven review of staged Git changes with deterministic rule scanning and semantic analysis. Use when the user wants to review staged changes, check for errors before commit, or validate code quality before committing.
Implement ReasoningBank adaptive learning with AgentDBs 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.