Agent Architect for Openclaw

An interactive architecture consultant that guides developers through designing and planning complex AI agent systems using proven patterns.

philitician
v1.0.2
Apr 8, 2026
0
833
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install blockmind-agent-architect

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install blockmind-agent-architect using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Agent Architect?

Agent Architect is a sophisticated design consultant for developers building agentic systems. It transforms the often-confusing process of selecting tools, memory structures, and deployment strategies into a structured, evidence-based conversation. By leveraging a curated set of Openclaw Skills references, this agent ensures that your architecture is grounded in real-world patterns like multi-channel routing and LLM-maintained wikis, moving beyond generic advice to actionable blueprints.

Agent Architect Use Cases

  • Planning a multi-agent system for complex enterprise workflows.
  • Designing a persistent memory layer for a personal AI assistant.
  • Selecting the right deployment strategy for local or cloud-based coding agents.
  • Architecting a documentation-heavy agent system using LLM-maintained wiki patterns.
  • Mapping out tool integrations for Slack, Discord, or CLI-based bots.

How Agent Architect Works

  1. The consultant initiates a structured intake flow, asking about the domain, purpose, and target users.
  2. It identifies the necessary surfaces and interaction points like web chat, mobile, or CLI.
  3. The system evaluates whether a single generalist or multiple specialist agents are required.
  4. It assesses specific coding agent preferences and persistent memory needs.
  5. The agent maps your requirements to a curated knowledge map of technical references.
  6. Finally, it synthesizes a comprehensive architecture overview with specific component recommendations and a suggested reading order.

Agent Architect Setup

To use Agent Architect, ensure your Openclaw Skills environment is configured and the necessary reference documents are available in the local repository.

# Navigate to your agent project
cd my-agent-project

# Initialize the architect skill
openclaw install agent-architect

# Start the interactive design session
openclaw run agent-architect

Agent Architect Data Schema & Taxonomy

The skill organizes architecture recommendations based on a knowledge map of curated Markdown references.

Category Metadata/File Reference Purpose
Routing references/openclaw-docs.md Multi-channel and gateway patterns
Memory references/claude-code-memory-docs.md Persistence for coding agents
Storage references/fly-tigris-docs.md S3-compatible data management
Wiki references/karpathy-llm-wiki.md LLM-driven knowledge bases

Agent Architect Advanced Features

  • Integration with specific IDE conventions for Claude Code and Cursor.
  • Support for filesystem-native agent context mapping using manifesto patterns.
  • Automated reading and citation of internal reference files for high-confidence advice.
  • Explicit gap analysis when requirements exceed the scope of the curated Openclaw Skills documentation.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*