Skill UI

Interactive first-time onboarding for new Ouroboros users, checking Claude and Codex runtime setup readiness, tracking completion, and supporting skip or force re-run options.

This document defines the critical architectural contract for standardizing advisory transport across diverse AI code review runtimes (e.g., Claude Code, OpenCode, Codex). It mandates that all integrations adhere to a shared Go contract, governing how review results, evidence, and validation are processed. This is essential for ensuring system integrity, managing architectural transitions, and preventing the creation of isolated, proprietary review systems.

This skill allows delegating self-contained coding tasks to assistants like Codex or Claude Code via non-interactive background processes. It supports feature development, code review, and refactoring. Use OpenSquilla's exec_command and process tools to manage sessions, poll output, and send inputs without blocking the main workflow. Ideal for tasks requiring substantial file exploration.

Turns your Kanban board (Asana, GitHub Projects, Linear) into an autonomous AI development pipeline with multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, cost tracking, and recoverable task state.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations like Claude Code and OpenAI Codex. Detects attack vectors where attacker-controlled input reaches AI agents in CI/CD pipelines through static analysis.

Secure AI coding agents such as Claude Code, Cursor, Codex and Copilot with permission boundaries, secret scanning, sandbox isolation, command allowlists and code review gates for team environments.

This skill converts human-written CLAUDE.md files into AI-native structured-label formats. It proposes and evaluates rewrites while preserving rule meaning, ensuring benefits are evidenced. Ideal for optimizing LLM system prompts, reducing token usage, and migrating rules across different AI tools like Claude, Codex, and Gemini.

BlockRun integrates Claude Code with external AI providers via x402 micropayments, enabling image generation, real-time X search, and second-opinion LLM calls with wallet-based budget control.

Deep expertise in Anthropic's Claude Code CLI: configure hooks, MCP connections, permissions, CLAUDE.md memory, sub-agents, and advanced workflows to maximize developer productivity.

Comprehensive reference for configuring and using Claude Code, covering project instructions (CLAUDE.md), advanced features like debugging and thinking keywords, and best practices for iterative development and efficient context management.

Delegate a bounded coding task to a separate Claude Code CLI session for implementation, while the orchestrator reviews the diff and lands the changes. Use only when the user explicitly requests delegation. Requires the claude CLI, Node 18+, and git.

Diagnose and fix Claude in Chrome MCP extension connectivity issues on macOS, including native host conflicts between Claude.app Cowork and Claude Code CLI, socket mismatches and reconnect steps.