Explora e instala miles de habilidades para AI Agents en el directorio de Killer-Skills. Compatible con Claude Code, Windsurf, Cursor y más.
Resumen localizado: The Ultimate iOS Crash Reporter # Async-Signal-Safety Review (with Libc ground-truthing) Scope is strict: async-signal-safety and crash-time correctness only. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: HardStop is a rock-solid protection for AI-generated commands. It covers agentic-ai, ai-safety, claude workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: Enter autonomous development mode with STRUCTURAL enforcement. It covers agent-framework, agent-identity, agent-infrastructure workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: AI governance through geometric cost scaling — 14-layer security pipeline using hyperbolic geometry to make adversarial attacks mathematically impossible. It covers adversarial-ml, ai-alignment, ai-firewall workflows. This AI agent skill supports Claude Code, Cursor, and
Resumen localizado: His work on logical clocks, consensus (Paxos), and formal specification (TLA+) provides the theoretical foundation for nearly every reliable distributed system built today. It covers adversarial-attacks, ai-safety, consensus workflows. This AI agent skill supports Claude Code
Resumen localizado: Prevent i18n regressions for ko/en/vi (missing keys, long Vietnamese text UI breakage). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: # Inbox One LLM Safety Use this skill for AI-flow and prompt-boundary review in Inbox One. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: Human-in-the-loop execution for LLM agents # /pr - Prepare and Submit Changes Purpose Commit changes to a feature branch, bump version if needed, update changelog, and open a PR. It covers agent-safety, automation, cli workflows. This AI agent skill supports Claude Code
Resumen localizado: Build scalable Python apps with the power of DI & AOP # Monitor PR 인자: PR 번호. It covers aspect-oriented-programming, asyncio, dependency-injection workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Resumen localizado: Use when creating Git commits — produces distinctive emoji-adorned commit messages with creative visual metaphors # Creative Commits Craft Git commits with distinctive, metaphorical emoji and concise messages. It covers data-validation, declarative, input-validation workflows.
Resumen localizado: feature-development helps AI agents handle repository-specific developer workflows with documented implementation details. It covers ai-agent, clinical, ddd workflows.
Resumen localizado: The unsafe {} block is a syntax marker; the real safety mechanism is private fields behind a safe public API, within a module (or crate) where all code is trusted. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.