architecture — Claude Code skill: ADRs and system design review
Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies.
npx skills add anthropics/knowledge-work-plugins --skill architecture -a claude-codeWhat architecture does
The architecture skill runs in three modes: create an ADR, evaluate a design proposal, or design a new component from requirements and constraints. One call does it — /architecture plus the decision or system you have in mind.
You get back a markdown ADR: status, date, deciders, context, the decision itself, options considered with a table covering complexity, cost, scalability and team familiarity, a trade-off analysis, consequences, and action items. Each option gets its own pros and cons list.
State your constraints upfront, because they shape the answer: a two-week deadline and a target request rate pull in different directions. With a knowledge base connected, the skill searches prior ADRs and design docs; with a project tracker, it links the decision to epics and creates implementation tasks. For deeper frameworks on requirements gathering and scalability analysis it points you to the system-design skill.
What it helps with
- choose between Kafka and SQS for an event bus
- document a design decision with trade-offs and consequences
- review a microservices proposal
- design a notification system from requirements and constraints
- link an ADR to epics and implementation tasks
Example prompts for the agent
- /architecture Should we use Kafka or SQS for our event bus?
- /architecture Review this microservices proposal
- /architecture Design the notification system for our app
How to install architecture
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill architecture -a claude-code2Manually: put the files in place
~/.claude/skills/architecture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/architecture/
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill architecture -a codex2Manually: put the files in place
.agents/skills/architecture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill architecture -a cursor2Manually: put the files in place
.cursor/skills/architecture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/knowledge-work-plugins architecture2Manually: put the files in place
.github/skills/architecture/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill architecture -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/knowledge-work-plugins --path engineering/skills/architectureManually: put the files in place
.devin/skills/architecture/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill architecture -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set89
The whole set →Similar
Questions about architecture
How do I install architecture in Claude?
Run npx skills add anthropics/knowledge-work-plugins --skill architecture -a claude-code. The skill file lands at ~/.claude/skills/architecture/SKILL.md.
What does the architecture skill do?
It creates an Architecture Decision Record or evaluates a system design. Output covers options with pros and cons, trade-off analysis, consequences and action items.
What should I include for a useful review?
Constraints and non-functional requirements: timeline, expected load, latency, cost, team expertise. The skill advises naming your options explicitly even when you already lean one way.
Source text
SKILL.md · Apache-2.0
--- name: architecture description: Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints. argument-hint: "<decision or system to design>" --- # /architecture > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Create an Architecture Decision Record (ADR) or evaluate a system design. ## Usage ``` /architecture $ARGUMENTS ``` ## Modes **Create an ADR**: "Should we use Kafka or SQS for our event bus?" **Evaluate a design**: "Review this microservices proposal" **System design**: "Design the notification system for our app" See the **system-design** skill for detailed frameworks on requirements gathering, scalability analysis, and trade-off evaluation. ## Output — ADR Format ```markdown # ADR-[number]: [Title] **Status:** Proposed | Accepted | Deprecated | Superseded **Date:** [Date] **Deciders:** [Who needs to sign off] ## Context [What is the situation? What forces are at play?] ## Decision [What is the change we're proposing?] ## Options Considered ### Option A: [Name] | Dimension | Assessment | |-----------|------------| | Complexity | [Low/Med/High] | | Cost | [Assessment] | | Scalability | [Assessment] | | Team familiarity | [Assessment] | **Pros:** [List] **Cons:** [List] ### Option B: [Name] [Same format] ## Trade-off Analysis [Key trade-offs between options with clear reasoning] ## Consequences - [What becomes easier] - [What becomes harder] - [What we'll need to revisit] ## Action Items 1. [ ] [Implementation step] 2. [ ] [Follow-up] ``` ## If Connectors Available If **~~knowledge base** is connected: - Search for prior ADRs and design docs - Find relevant technical context If **~~project tracker** is connected: - Link to related epics and tickets - Create implementation tasks ## Tips 1. **State constraints upfront** — "We need to ship in 2 weeks" or "Must handle 10K rps" shapes the answer. 2. **Name your options** — Even if you're leaning one way, I'll give a more balanced analysis with explicit alternatives. 3. **Include non-functional requirements** — Latency, cost, team expertise, and maintenance burden matter as much as features.
© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins