Agent Skills Hub

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

lsp-code-analysis

Compiler-accurate semantic code analysis via LSP. Navigate definitions, references, and implementations, perform workspace-wide renames, and get file outlines for Python, Rust, Go, TypeScript/JS, and Java.

phase-5-validator

Automates finalization validation for project workflows by enforcing git compliance, documentation standards, and deployment readiness.

vercel-deploy

Deploy applications to Vercel instantly. Supports preview and production deployments, automatic framework detection, and fallback script execution for seamless project publishing.

audit-skills

Audit AI skills for security vulnerabilities including prompt injection, hidden instructions, tool misuse, and data exfiltration risks.

ffuf-web-fuzzing

Expert-level guidance for ffuf web fuzzing, enabling automated discovery of hidden directories, files, parameters, and vulnerabilities during penetration testing.

vibe-run

A deterministic orchestration engine for autonomous coding agents, managing workflow loops, state persistence, and checkpoint-based execution.

pr-demo

Create polished animated terminal demos for pull requests and documentation using asciinema, agg, and svg-term-cli.

debugging

Standardized debugging and diagnostic guidelines for AI coding agents.

cowork-router

Dynamic meta-router for managing and orchestrating multi-domain AI coding agent skills across plugins and projects.

parallel-worktrees

Create and manage git worktrees for parallel coding sessions. Enable zero-dead-time development by running tests, builds, and multiple branch sessions simultaneously without interference.