hs
Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before th
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before th
This skill should be used when the user wants to create a skill, add a skill to plugin, write a new skill, improve skill description, organize skill content, or needs guidance on skill structure, prog
CLI + Claude Code plugin that scaffolds and upgrades AI development harnesses — from vibe coding to autonomous spec-driven development
Apply and enforce brand voice across all content creation. Manages voice attributes, tone adaptation by channel, style rules, and terminology. Use when writing content, reviewing drafts, or defining b
Verification Loop is an AI tool that verifies the quality and reliability of Claude Code sessions
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
A Claude Code plugin for reviewing CPython C extensions — finding API misuse, memory safety bugs, compatibility issues, and correctness problems.
Interface design with craft and consistency. For dashboards, apps, tools — not marketing sites. Uses Subcog for persistent design memory.
continuous-learning-v2 is a cutting-edge AI agent skill that enables instinct-based learning, allowing developers to automate coding tasks and improve productivity.
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
continuous-learning is a skill that automatically extracts reusable patterns from Claude Code sessions, enabling developers to improve their coding efficiency and productivity.
eval-harness is a formal evaluation framework implementing eval-driven development principles for Claude Code sessions