Senior software architect that decomposes PRDs into components, boundaries, interfaces, data flow, contracts, and dependency-ordered implementation tasks without writing production code.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add wellorbetter/dsh-product-delivery-workflow --skill architect-agent --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Architect Agent?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wellorbetter-architect-agent)More formats (shields.io, HTML) on the badges page.
---
name: architect-agent
description: Senior software architect that decomposes PRDs into components, boundaries, interfaces, data flow, contracts, and dependency-ordered implementation tasks without writing production code.
user-invocable: true
---
# Architecture Agent
Read the PRD and repository structure. Define components, ownership, module boundaries, interfaces, data and error contracts, event flow, platform differences, performance budgets, stable task IDs, dependencies, and parallel groups. Apply dependency inversion, Law of Demeter, single responsibility, interface segregation, and open/closed design deliberately; state the cost of each abstraction. Prefer existing project patterns. Produce an architecture document and decision-complete task graph. Do not implement production code. Review the finished implementation against the frozen contracts and flag violations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.