Agent Workflow Design — Design skill for Claude Code
Design a multi-agent workflow with the right pattern, explicit handoffs, and human gates on consequential actions.
How to install Agent Workflow Design
Installs to ~/.claude/skills/amey-thakur-ai-skills-agent-workflow-design/SKILL.md
mkdir -p ~/.claude/skills/amey-thakur-ai-skills-agent-workflow-design && curl -fsSL https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/HEAD/commands/agent-workflow-design.md -o ~/.claude/skills/amey-thakur-ai-skills-agent-workflow-design/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Workflow Design does
description: "Design a multi-agent workflow with the right pattern, explicit handoffs, and human gates on consequential actions." argument-hint: "[task]"
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Design an agent workflow for:
{task}
Constraints: {constraints}
Use agent-
Alternatives in Design
- Planning With Files — Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B 17.4k ★
- Kode Agent — Kode Agent — Design for post-human workflows 5k ★
- Mckinsey Deck — Build a McKinsey-style PPTX deck from a brief 566 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
A2AChannel
Desktop workspace for coordinating multiple Claude Code agents with typed handoffs (accept / decline / cancel
System Design Skill
System design for coding agents: map, design, review & evolve architectures with capacity math, failure stress
Multi Agent
Orchestrate multiple Claude instances on Figma canvas with box widgets, coordinated handoffs, error recovery
Agent Design
Guided workshop for designing a multi-agent system — task decomposition, agent roles, orchestration pattern, p
Agent Architecture
Visual multi-agent system designer for Claude Code. 28 agents, Five Minds Protocol, HITL gates, Live Simulatio
TermHive
Human-driven multi-agent dashboard for Claude Code, Codex, Gemini & OpenCode. Web UI, project wiki, shared con
Related Agents
Event Plan Builder
Merges every validated artifact into one coherent, human-readable event plan. Runs only after the validator re
Premise Checker
Adversarially test one explicit consequential premise in fresh read-only context; return supported, revise, or
iOS UX Reviewer
iOS UI/UX review expert grounded in Apple's Human Interface Guidelines and established design philosophy. Use