Skill UI

A sophisticated AI system that coordinates multiple specialized agents (e.g., Security Auditors, Performance Analysts, Architecture Specialists) to perform comprehensive, multi-perspective code assessments. It analyzes code context, manages state, and synthesizes conflicting insights to provide deep, holistic reviews for complex software projects.

Scans Solana and Anchor programs for six critical security vulnerabilities—arbitrary CPI, improper PDA validation, missing signer/ownership checks, sysvar spoofing, and instruction introspection issues—to support audits and pre-launch reviews.

Provides a structured workflow for defining agent-agnostic subagents with isolated context, covering purpose definition, metadata configuration, prompt writing, and common specialist patterns for verification, debugging, security auditing, and review.

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

This skill audits Model Context Protocol (MCP) servers to detect critical AI security vulnerabilities. It scans for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure. Use it before integrating new tools or during security reviews to ensure agent reliability and prevent supply chain attacks.

Delegates coding, code review, and plan review tasks to OpenAI Codex CLI with sandbox controls and security boundaries. Supports autonomous execution, multiple modes, and safe review handling.

This framework provides a rigorous pre-execution review mechanism for proposed actions by AI agents or systems. It functions as a critical safety boundary, auditing the entire decision path—from initial request to proposed tool execution—without authorizing or executing anything. It verifies action conformity, evidence integrity, temporal validity, and reviewer independence to ensure system compliance and security.

Convert approved documentation, repositories, or PDFs into reusable agent skills using the Skill Seekers workflow. Review generated content for triggers, guidance, and security before installation. Supports licensing checks and excludes private credentials.

Security hardening guidance for AI agent frameworks processing untrusted content, invoking tools, writing files, managing identifiers, or handling credentials. Use when building or reviewing agent runtimes, autonomous workers, tool gateways, memory services, or multi-tenant deployments.