skill-stocktake
[ Featured ]skill-stocktake is a code quality audit AI agent skill that evaluates and enhances Claude skills and commands using AI holistic judgment.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
skill-stocktake is a code quality audit AI agent skill that evaluates and enhances Claude skills and commands using AI holistic judgment.
strategic-compact is a Claude Code AI agent skill that enables manual control over context compaction, optimizing workflow efficiency and context preservation.
laravel-verification is a comprehensive AI agent skill for verifying Laravel project integrity and readiness for deployment.
perl-testing is a skill that provides comprehensive testing patterns for Perl applications using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
laravel-security is a skill providing comprehensive security guidance for Laravel applications to protect against common vulnerabilities.
Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.
ai-regression-testing is a skill that enables automated testing strategies for AI-assisted development, leveraging sandbox-mode API testing and automated bug-check workflows.
x-api is a Twitter API integration skill for posting, reading, searching, and analytics, utilizing OAuth auth patterns and rate limits for seamless interactions.
Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.