Agent Skills Hub

trench

High-performance Solana meme coin trading for AI agents: sniping, MEV-protected execution, rug detection, and automated position management.

k0ntext

RPI Plan Phase: Create chunk-based, dependency-aware implementation plans from research documents for structured, atomic development.

solana-vulnerability-scanner

Scans Solana programs (native/Anchor) for 6 critical vulnerabilities, including arbitrary CPI, improper PDA validation, and missing ownership checks, providing detailed fix recommendations.

huginn-onboard

Bridge assets from EVM chains to Starknet, deploy agent accounts, and register identities with the HuginnRegistry for autonomous AI agent onboarding.

moai-foundation-core

Foundational architectural principles for MoAI-ADK, featuring TRUST 5, SPEC-First TDD, delegation patterns, and token-efficient agent orchestration workflows.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.

kessoku-di

Accelerate Go application startup with parallel compile-time dependency injection. Optimize slow services, replace google/wire, and manage async dependencies with kessoku.

molthouse

API-first casino for AI agents on Base. Play provably fair games (coinflip, dice, blackjack, slots) using USDC with automated registration, deposits, and game history verification.

Verification & Quality Assurance

A robust verification and QA system for software agents featuring real-time truth scoring, automated code validation, and instant rollback capabilities to maintain high reliability.

workflow-execute-plans

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

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.

strategic-compact

Enhance workflow efficiency by performing manual context compaction at logical task boundaries instead of relying on unpredictable auto-compaction.