Agent Skills Hub

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

command-executor

Safely execute, test, and verify commands discovered in documentation with real output capture, performance tracking, and git-aware safety protocols.

prompt-estruturado

A structured prompting framework to transform casual inputs into professional, modular LLM prompts with persona, context, task, format, and guardrails.

executing-plans

Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

enterprise-agent-builder

Architects enterprise AI agents from structured specs, generating production-ready code, data flow diagrams, and platform-specific logic for ServiceNow, Salesforce, and Snowflake.

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.

skill-vetter

Security-first vetting protocol for AI agent skills. Detects red flags like credential theft, obfuscated code, and unauthorized data exfiltration before installation.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

prp-manager

Context Engineering agent skill to initialize, generate, and execute comprehensive implementation blueprints (PRPs) for one-pass software development.

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.