Agent Designer (Multi-Agent Architecture)
Picks a multi-agent orchestration pattern from requirements, generates and validates provider-ready tool schemas, and evaluates run logs for cost, latency, and bottlenecks.
Dev & CodingAdvanced★ 26,260⑂ 3,699AI score 9/10Last updated: Aug 30, 2026
What it does
- Architecture design: feed a requirements JSON (goal, tasks, constraints for response time, budget, concurrency) and
agent_planner.pydeterministically scores single-agent vs supervisor, pipeline, hierarchical, or swarm, then emits agent roles, communication links, a Mermaid diagram, and an implementation roadmap. - Tool schema generation: turns plain-language tool descriptions into Anthropic and OpenAI schema files, with a hard gate that every tool must report
✓ Validbefore you proceed. - Execution log evaluation: success rate, latency distribution, bottleneck and error analysis, cost breakdown, SLA compliance, and ranked optimization recommendations.
- Verification loop: iterate until 0 invalid schemas and 0 critical issues, comparing against
expected_outputs/for schema drift.
Who it's for
- AI engineers building their first coordinated multi-agent system
- Architects who want an orchestration pattern chosen by a scoring table instead of intuition
- Teams that need hard numbers on cost and latency for an agent pipeline already in production
Examples
- "Design an agent architecture for research automation" → write the requirements JSON, run the planner, get a supervisor pattern with roles and a Mermaid diagram.
- "Generate Anthropic tool schemas from these tool descriptions" → run
tool_schema_generator.py --validateand confirm every schema passes before wiring it into an agent. - "Analyze last week's agent run logs for bottlenecks" →
agent_evaluator.py --detailedsurfaces the slowest agent, error clusters, cost split, and a recommendations file.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/agent-designer/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the .gemini/skills/agent-designer folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/agent-designer/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/alirezarezvani/claude-skills.git && mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/agent-designer ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/alirezarezvani/claude-skills.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r claude-skills/.gemini/skills/agent-designer ~/.claude/skills/ - Verify Python is available:
python3 --version(the three scripts require it). - Run
ls ~/.claude/skills/agent-designerand confirmagent_planner.py,tool_schema_generator.py,agent_evaluator.py, and theassets/samples came along; if not, check the repo for the full skill folder. - Restart Claude Code and try a prompt like "design a multi-agent architecture for ..." to trigger the skill.
View source on GitHub ↗License: MIT