architecture-advisor skill: a decision procedure for picking software patterns with written justifications
jordimarsal · ghdev · 2026-10-16
PR #2040 on anthropics/skills adds an architecture-advisor skill — the fourth in the author's MIT-licensed harness SDD suite — targeting the first decision in feature work: which core architecture pattern a service should use.
Structure:
- Three one-line selectors: domain complexity, team size, scaling needs
- A catalog of 8 core patterns (layered, hexagonal, clean, CQRS, microservices, modular monolith, event-driven, functional core/imperative shell), each with best-for, trade-offs, and a "when-NOT-to-use" list
- Per-pattern detail files with principles, data flow, and a "Do Not" list of real-world failure modes
- Independent overlay tables: API style (REST/GraphQL/gRPC/WS), frontend integration, persistence
- A justification block format (pattern + selectors + accepted trade-offs + rejected alternative) so reviewers challenge the reasoning, not the choice
Default when unsure: modular monolith until scale proves otherwise. SKILL.md is 84 lines plus 8 reference files; all 34 structural checks pass.
More from coding & agent
- Garry Tan endorses Aside Browser as the fix for agents getting blocked on the web — garrytan · 2026-10-23
- 1Password launches tool letting AI agents log in for you without seeing your password — AndrewSchmidtFC · 2026-10-23
- MCP server turned rogue 30 days after approval, prompting open-source mcp-guard lockfile tool — ErgoniaWorks · 2026-10-23
- Test: Coding Agents Won't Use an MCP Tool Unless AGENTS.md Mentions It — colinmcnamara · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- awesome-ai-apps: 132 Free Open-Source AI Agent and RAG Projects on GitHub — Arindam_1729 · 2026-10-23