vibe-agentlisted

Standalone agentic architecture skill. Designs complete multi-agent AI systems from scratch — no other vibe-* skills required. Deep knowledge of LangGraph, LangChain, CrewAI, AutoGen, Vercel AI SDK, and custom implementations. Produces AGENT_ARCH.md covering pattern selection, agent roles, tool mapping, state design, HITL checkpoints, VerifierAgent rubrics, implementation order, stack recommendations, and boilerplate folder structure. Generates both an interactive inline topology diagram and an exportable static SVG. Triggers on "agent:" prefix, "design an agent system", "I want to build an agent", "multi-agent pipeline", "orchestrator and sub-agents", "agentic workflow", "which agent framework should I use", "how do I structure my agents", "build a workflow with AI agents", "human in the loop", "LangGraph architecture". Always use when designing any system involving AI agents — standalone, no dependencies.
aakashdhar/vibe-skill · ★ 7 · AI & Automation · score 68

Install: claude install-skill aakashdhar/vibe-skill

# Vibe Agent — Standalone Agentic Architecture Skill Designs complete multi-agent AI systems from first principles. No other skills required. No BRIEF.md needed. Works anywhere. Produces AGENT_ARCH.md — a complete implementation blueprint — and two topology diagrams: interactive (inline) and static (exportable). **Always run in Plan Mode. No code written during this session.** > **Autonomous / headless mode.** At startup resolve the settings with > `python3 ~/.claude/skills/vibe-mode/scripts/vibe_state.py mode`. If `vibe_mode` is > `autonomous`, every "wait", "ask", "confirm" and approval step in this skill follows > vibe-mode's `references/HEADLESS.md` §2 instead: take the recommended option, accept your > own draft after one self-check, log each choice to `vibe/DECISIONS.md`, never ask the > user, and stop — writing `vibe/.run_state.json` — only when a person is genuinely required. --- ## What makes a great agentic architecture Before asking any questions, understand this: Most agentic systems fail not because of bad code — but because of bad design. Agents with unclear responsibilities. State shared without ownership. Verification bolted on as an afterthought. Humans inserted too late to matter. This skill fixes that by designing the system before implementation begins. Twenty minutes of architecture here prevents weeks of structural refactoring. The five decisions that determine whether an agentic system works: 1. **Pattern** — the right structural pattern for