Essential command-line tools and system utilities.
Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.
Create system design documents based on requirements. Use when users need technical architecture, API design, data models, or system design. Triggers on keywords like "system design", "architecture", "technical design", "API design".
Backend Architect Agent. 시스템 설계, 아키텍처 결정, 기술 선택을 담당합니다. 설계, 아키텍처, 구조, 패턴, 기술 선택 관련 요청 시 사용됩니다.
Agent execution patterns including LLM calls and token handling. Use when implementing agent execution or multipart forms. Triggers: agent.Agent, VisionForm, ParseVisionForm, Token injection, constructAgent, ChatStream, VisionStream, multipart/form-data, base64, Provider.Options["token"], go-agents, ExecuteRequest, SetSecret, GetSecret. File patterns: internal/agents/*.go
Use OpenAI Codex CLI as a discussion partner to verify ideas, evaluate plans, and improve quality. Automatically triggered during implementation planning, troubleshooting, debugging, or when seeking a second opinion on technical decisions.
Create new Claude Code skills through guided conversation. Use when the user wants to create a skill, write a skill, make a skill, or set up custom instructions for a specific domain or workflow.
Extract lessons from task failures using Reflector agent, merge insights via Curator pattern, achieving 10% accuracy improvement without context collapse. Use for post-failure analysis, lesson extraction, self-improvement, and building resilience. Analyzes what went wrong and formulates actionable lessons. Triggers on "learn from failure", "analyze mistake", "reflect on error", "post-mortem", "failure analysis", "what went wrong".
Generate any kind of visual asset using OpenRouter's Nano Banana Pro (Google Gemini 3 Pro Image Preview). Handles images, graphics, illustrations, icons, banners, backgrounds, UI elements, stickers, characters, and more. Flexible and adaptable to any creative request.
Use when users ask about Claude Code features, setup, configuration, troubleshooting, slash commands, MCP servers, Agent Skills, hooks, plugins, CI/CD integration, or enterprise deployment. Activate for questions like 'How do I use Claude Code?', 'What slash commands are available?', 'How to set up MCP?', 'Create a skill', 'Fix Claude Code issues', or 'Deploy Claude Code in enterprise'.
Autonomous agent creation skill that generates specialized agent definitions from templates. Use when you need to create new Claude Code agents for specific tasks like code review, deployment automation, testing, documentation, security analysis, or general-purpose research. This skill automates the creation of agent definition files (.md) with proper structure, workflow instructions, and tool access patterns following Miyabi framework standards.
Use when you need validation, analysis, or research from multiple AI agents before implementing. Gathers perspectives from Gemini and Codex, synthesizes feedback.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Write Claude Code skills and SKILL.md files. Use when creating new skills, writing skill content, structuring SKILL.md, organizing skill directories, or when user mentions "write skill", "create skill", "author skill", "new skill", "skill structure", "SKILL.md", "skill content", "skill template".
Orchestrates autonomous development workflows through specialized character-based phases - research (Lisa), complexity assessment (Mayor Quimby), planning (Professor Frink), documentation (Martin Prince), implementation (Ralph), and quality validation (Comic Book Guy). Handles multi-step development tasks end-to-end with automatic error recovery, kickback routing, and iterative refinement. Use for complex feature development, bug fixes requiring investigation, or any task benefiting from structured research-plan-implement-validate cycles.
This skill should be used when the user asks about "build action", "create action", "execute block", "input_fields", "output_fields", "streaming action", "multistep action", "config_fields", "wait for resume", or needs to implement actions for a Workato custom connector.
CLI tool for AI agents to browse the web, interact with UI elements, and analyze frontend applications. Supports navigation, clicking, typing, and capturing snapshots for accessibility analysis.
Mapping guidance for Vapi voice events to dashboard templates.
Agent logs, reasoning, and token tracking. Use when logging interactions, saving reasoning, tracking tokens, or managing events.
Create and structure Claude Code Skills with best practices. Use when building custom Skills, setting up Skill directories, writing SKILL.md files, or creating reusable Claude capabilities.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Automatically routes complex coding tasks to specialized agents (Gemini, Codex, Cursor) via Roundtable MCP for multi-model verification and long-context analysis.
Terminal-style React UI for Claude Agent SDK with keyboard navigation, tool approval, and dark theme
