메뉴
Make defensible architecture decisions by translating requirements into trade-offs and ADRs. Use when choosing styles, components, or integration approaches that need a documented rationale.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | architecture |
| description | Make defensible architecture decisions by translating requirements into trade-offs and ADRs. Use when choosing styles, components, or integration approaches that need a documented rationale. |
| risk | unknown |
| source | community |
| date_added | 2026-02-27 |
Architecture is the set of decisions hard to change later. This skill turns requirements and constraints into evaluated options and durable decision records using MADR 4.x ADRs, the C4 model, and ISO/IEC 25010:2023 quality attributes.
| Concern | Recommended |
|---|---|
| Decision record format | MADR 4.x in /docs/adr (one ADR per decision) |
| Quality model | ISO/IEC 25010:2023 |
| Architecture description | ISO/IEC/IEEE 42010:2022 (concerns, viewpoints, views) |
| Diagrams | C4 model (Structurizr DSL or Mermaid C4) |
| Discovery template | arc42 sections 1, 2, 3, 9, 10 |
| Trade-off framework | Cost / Risk / Benefit matrix + sensitivity to each quality attribute |
| Currency signal | ThoughtWorks Tech Radar; internal Adopt/Trial/Hold list |
flowchart LR
R[Requirements + constraints] --> O[Generate 2-4 options]
O --> T[Trade-off analysis]
T --> D[Decide and record ADR]
D --> V[Validate with fitness functions]
V -->|drift| O
Proposed and moves to Accepted after review.ADR skeleton (MADR 4.x):
# ADR-NNNN: <decision title>
Status: Proposed | Accepted | Deprecated | Superseded by ADR-XXXX
Date: YYYY-MM-DD
Deciders: <names>
Context: <forces, constraints, drivers>
Options:
- Option A: ...
- Option B: ...
Decision: <chosen option and why>
Consequences: <positive, negative, follow-ups>
Fitness functions: <how we will know this is still right>
| Pitfall | Why it hurts | Mitigation |
|---|---|---|
| Deciding before defining quality attributes | Optimizes the wrong axis | Anchor every decision to ISO/IEC 25010:2023 attributes |
| One-option ADRs | No real evaluation | Require >=2 credible options including status quo |
| Treating reversible and irreversible decisions the same | Slows trivial calls, rushes critical ones | Tag one-way vs two-way doors and adjust rigor |
| ADRs as prose only | Searchable but not testable | Add fitness functions and link from code/CI |
| Ignoring team skill fit | Beautiful design, failed delivery | Include team capability as an explicit driver |
| Stale ADRs | Misleading newcomers | Quarterly review; mark Deprecated/Superseded promptly |
# Decision: <one-sentence question>
- Owner: <name> | Reversibility: one-way | Due: YYYY-MM-DD
## Drivers and Quality Attributes
## Options Considered (A, B, C)
## Trade-off Matrix (attribute x option, with weights)
## Decision and Rationale
## Consequences (positive / negative / follow-up actions)
## Fitness Functions
## Links: ADR-NNNN, C4 view(s), affected runbooks
Build production integrations with Anthropic Claude (Claude 4.5 Sonnet, Claude Opus 4, Claude Haiku 4) via the Messages API — system prompts, multi-turn conversations, tool use (function calling), prompt caching, extended thinking, vision, batched requests, and streaming. Use when wiring Claude into backends, agentic workflows, or evaluating it against other foundation models. Requires ANTHROPIC_API_KEY.
Deploy Cloudflare Workers, Pages, and Workers-with-static-assets safely using Wrangler 4.x with versioned uploads, gradual deployments, preview/production environments, secret bindings, observability, and one-command rollback. Use when shipping edge workloads, API routes, or full-stack apps to Cloudflare. Requires CLOUDFLARE_API_TOKEN with scoped permissions or an authenticated Wrangler session.
Deploy static sites, framework apps (Next.js, Astro, Remix, SvelteKit, Nuxt), Edge Functions, and serverless Functions to Netlify with deploy previews, branch deploys, atomic production promotion, scoped env vars, and instant rollback. Use when releasing on Netlify via CLI, API, or Git-triggered builds. Requires NETLIFY_AUTH_TOKEN (PAT) and NETLIFY_SITE_ID.
Transcribe audio with OpenAI speech-to-text models (gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1) using prompt-guided terminology, segment-level timestamps, optional diarization via post-processing, and reliable artifact delivery. Use when converting interviews, calls, podcasts, or meeting recordings into reviewable text. Requires OPENAI_API_KEY.
Deploy Web Services, Private Services, Background Workers, Cron Jobs, Static Sites, PostgreSQL, and Key-Value (Redis-compatible) on Render via Blueprints (`render.yaml`) or the Render API with preview environments, zero-downtime rolling deploys, health checks, env-group secret scoping, and one-click rollback. Use when releasing services, applying schema migrations, or syncing infra-as-code on Render. Requires RENDER_API_KEY (owner- or workspace-scoped).
Operate Sentry end-to-end — error monitoring, performance tracing, session replay, profiling, release health, source-map upload, ownership routing, alert tuning, issue triage, and CI integration via sentry-cli — across web, mobile, and backend stacks. Use when instrumenting an app, wiring releases into deploy pipelines, or running incident-grade triage. Requires SENTRY_AUTH_TOKEN (org-scoped, `project:releases project:write`), project DSN, and (for source maps) `org` + `project` slugs.