$npx -y skills add anthropics/knowledge-work-plugins --skill architectureCreate 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 constraint
| 1 | # /architecture |
| 2 | |
| 3 | > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). |
| 4 | |
| 5 | Create an Architecture Decision Record (ADR) or evaluate a system design. |
| 6 | |
| 7 | ## Usage |
| 8 | |
| 9 | ``` |
| 10 | /architecture $ARGUMENTS |
| 11 | ``` |
| 12 | |
| 13 | ## Modes |
| 14 | |
| 15 | **Create an ADR**: "Should we use Kafka or SQS for our event bus?" |
| 16 | **Evaluate a design**: "Review this microservices proposal" |
| 17 | **System design**: "Design the notification system for our app" |
| 18 | |
| 19 | See the **system-design** skill for detailed frameworks on requirements gathering, scalability analysis, and trade-off evaluation. |
| 20 | |
| 21 | ## Output — ADR Format |
| 22 | |
| 23 | ```markdown |
| 24 | # ADR-[number]: [Title] |
| 25 | |
| 26 | **Status:** Proposed | Accepted | Deprecated | Superseded |
| 27 | **Date:** [Date] |
| 28 | **Deciders:** [Who needs to sign off] |
| 29 | |
| 30 | ## Context |
| 31 | [What is the situation? What forces are at play?] |
| 32 | |
| 33 | ## Decision |
| 34 | [What is the change we're proposing?] |
| 35 | |
| 36 | ## Options Considered |
| 37 | |
| 38 | ### Option A: [Name] |
| 39 | | Dimension | Assessment | |
| 40 | |-----------|------------| |
| 41 | | Complexity | [Low/Med/High] | |
| 42 | | Cost | [Assessment] | |
| 43 | | Scalability | [Assessment] | |
| 44 | | Team familiarity | [Assessment] | |
| 45 | |
| 46 | **Pros:** [List] |
| 47 | **Cons:** [List] |
| 48 | |
| 49 | ### Option B: [Name] |
| 50 | [Same format] |
| 51 | |
| 52 | ## Trade-off Analysis |
| 53 | [Key trade-offs between options with clear reasoning] |
| 54 | |
| 55 | ## Consequences |
| 56 | - [What becomes easier] |
| 57 | - [What becomes harder] |
| 58 | - [What we'll need to revisit] |
| 59 | |
| 60 | ## Action Items |
| 61 | 1. [ ] [Implementation step] |
| 62 | 2. [ ] [Follow-up] |
| 63 | ``` |
| 64 | |
| 65 | ## If Connectors Available |
| 66 | |
| 67 | If **~~knowledge base** is connected: |
| 68 | - Search for prior ADRs and design docs |
| 69 | - Find relevant technical context |
| 70 | |
| 71 | If **~~project tracker** is connected: |
| 72 | - Link to related epics and tickets |
| 73 | - Create implementation tasks |
| 74 | |
| 75 | ## Tips |
| 76 | |
| 77 | 1. **State constraints upfront** — "We need to ship in 2 weeks" or "Must handle 10K rps" shapes the answer. |
| 78 | 2. **Name your options** — Even if you're leaning one way, I'll give a more balanced analysis with explicit alternatives. |
| 79 | 3. **Include non-functional requirements** — Latency, cost, team expertise, and maintenance burden matter as much as features. |