software-architect
by Roy Yuen
A structured framework for planning, reviewing, and evolving complex software systems with explicit trade-offs.
- Decompose a legacy monolith into scalable microservices
- Design event-driven data flows with explicit reliability trade-offs
- Compare multiple technical options against cost and latency drivers
$5
One-time purchase
Included in download
- Decompose a legacy monolith into scalable microservices
- Design event-driven data flows with explicit reliability trade-offs
- Includes example output and usage patterns
See it in action
Current State: Monolithic Ruby on Rails, DB contention at 4k/rps. Candidate Option A: Extract Auth via gRPC. Candidate Option B: Event-driven via SNS/SQS. Recommendation: Option B. Migration: Phase 1: Dual-write to SQS; Phase 2: Deploy Go consumer; Phase 3: Deprecate legacy Rails worker.
software-architect
by Roy Yuen
A structured framework for planning, reviewing, and evolving complex software systems with explicit trade-offs.
$5
One-time purchase
⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →
Included in download
- Decompose a legacy monolith into scalable microservices
- Design event-driven data flows with explicit reliability trade-offs
- Includes example output and usage patterns
- Instant install
- One-time purchase
See it in action
Current State: Monolithic Ruby on Rails, DB contention at 4k/rps. Candidate Option A: Extract Auth via gRPC. Candidate Option B: Event-driven via SNS/SQS. Recommendation: Option B. Migration: Phase 1: Dual-write to SQS; Phase 2: Deploy Go consumer; Phase 3: Deprecate legacy Rails worker.
About This Skill
Systematic Architecture Design
The Software Architect skill transforms vague engineering briefs into rigorous, artifact-driven technical designs. Instead of jumping straight to a final recommendation, it enforces a structured workflow that identifies drivers, maps current bottlenecks, and explores multiple candidate options before settling on a target state.
What it does
- Artifact-First Planning: Generates explicit documents for Problem Framing, Architecture Drivers, and Current-State Mapping.
- Comparative Analysis: Produces and scores multiple viable options against scale, latency, and cost constraints.
- Implementation Path: Delivers a comprehensive Target Architecture including component boundaries, data flow diagrams, and migration plans.
- Validation Gates: Built-in review steps ensure recommendations are implementable and free of hidden coupling.
Why use this skill?
Standard LLM prompting often results in "hallucinated complexity" or biased recommendations. This skill provides a professional-grade framework that forces the AI to act as a Senior Architect, surfacing risks and trade-offs that are usually overlooked. It is particularly effective for service decomposition, event-driven transitions, and scaling legacy systems where "getting it right" is more important than "getting it fast."
Output Format
The skill produces a structured technical document following an industry-standard Output Contract, covering everything from reliability notes and security boundaries to a concrete, step-by-step migration plan.
📖 Learn more: Best Frontend & Design Skills for Claude Code →
Use Cases
- Decompose a legacy monolith into scalable microservices
- Design event-driven data flows with explicit reliability trade-offs
- Compare multiple technical options against cost and latency drivers
- Generate a detailed migration plan for major infrastructure refactors
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/software-architect | tar xz -C ~/.claude/skills/Free skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
java-best-practice-checker
Expert Java code auditor for SE 8–24, flagging performance leaks, threading risks, and modernization gaps.