Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
TEST - A modular Rust-based self-learning episodic memory system for AI agents, featuring hybrid storage with Turso (SQL) and redb (KV), async execution tracking, reward scoring, reflection, and pattern-based skill evolution. Designed for real-world applicability, maintainability, and scalable agent workflows.
This extension transforms the Gemini CLI into "Pickle Rick," a hyper-intelligent, arrogant, yet extremely competent engineering persona. It enforces a rigid, iterative software development lifecycle through continuous AI agent loops. Emphasizing "God Mode" coding practices and a disdain for
extracting-pdf-text is an AI Agent skill that provides tools and guidance for converting PDF content into text consumable by Large Language Models. It offers a quick decision guide and specific Python scripts for different PDF types, including simple text, tables, and scanned documents.
skill-creator is an AI agent skill that provides structured guidance for creating modular skill packages. These packages extend Claude's capabilities by providing specialized domain knowledge, multi-step workflows, and procedural expertise that the base model cannot possess on its own.
Prompt -> Full Agentic System. Generates entire multiagent systems based on user constraints in a simple text prompt.
Sharing Skills is a workflow that allows developers to contribute skills from their local branch to the upstream repository, following guidelines for sharing and documentation
nuqs is a library for type-safe URL query state management in Next.js applications. It provides a set of best practices and rules for implementing, configuring, and optimizing search parameters, including integration with Server Components and parser configuration.
Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
pr-merge is an AI agent skill that handles pull request merging with pre-merge validation. It accepts a PR number or URL and executes a specified merge strategy (merge, squash, or squid) using a Haiku subagent for Bash operations to optimize computational costs.
three-best-practices is an AI agent skill containing a comprehensive performance optimization guide for Three.js. It provides over 100 rules across 17 categories, based on official guidelines from the Three.js `llms` branch maintained by mrdoob.
natalia-rules is an AI Agent skill that enforces strict mirroring of Excel data into PDF documents. It operates under non-negotiable rules to prevent recalculation, preserve exact sequence, and ensure all alternates are shown without any data filtering.
backlog-to-rules is an AI agent skill that processes a backlog of software improvements (.cursor/data/improvements-backlog.md) to automatically generate and update deterministic rule files (.cursor/rules/*.mdc), turning experiential knowledge into enforceable code standards.