Agent Skills Hub

indirect-injection-detection

Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

skill-customizer

Adapt existing skills to your unique workflow, or create new ones for repetitive, time-consuming tasks.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

humanizer

Remove AI-generated patterns and inject natural human voice into your writing. Fixes robotic phrasing, overuse of AI vocabulary, and sterile structure to make text sound authentic.

mcaf-architecture-overview

Maintains a centralized architecture overview with Mermaid diagrams to document system boundaries, module dependencies, and interface contracts for onboarding and refactoring.

session-memory

Enables cross-session context persistence for Claude Code, managing history, project decisions, and workflow patterns to ensure seamless task continuation.

vultisig

MPC-based multi-chain wallet SDK and CLI for AI agents and developers. Perform secure, threshold-signed crypto operations (send, swap, sign) across 40+ blockchains without seed phrases.

qc

Automated quality gate using 5 parallel AI agents to review code changes for correctness, style, and consistency.

pr-operations

Manage PR review workflows, resolve threads, and handle discussion comments using specialized erk exec commands.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

n8n

Official n8n workflow automation support for building, debugging, and scaling complex business processes and AI-powered integrations.