This generates Architecture Decision Records in a structured format, which is honestly more useful than it sounds. You feed it a technical choice (Kafka vs SQS, microservices vs monolith) and get back a proper ADR with options, trade-offs, and consequences laid out. The format forces you to document why you picked something, not just what you picked. It can also evaluate existing designs or help you sketch out new components from requirements. Works best when you state your constraints upfront (budget, timeline, scale requirements) so it doesn't give you the theoretically perfect answer that's completely impractical for your situation.

skills.sh installs
7K
GitHub stars
35.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill architecture --agent claude-code

Installs into .claude/skills of the current project.

Files

/architecture

If you see unfamiliar placeholders or need to check which tools are connected, see 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

# 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**Status:** Proposed | Accepted | Deprecated | Superseded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]

Sponsors

Details

Repository
github.com/anthropics/knowledge-work-plugins
Categories
Frontend Development, Code Review & Quality, Productivity & Planning, Design & UI/UX
First seen
May 16, 2026

More from anthropics/knowledge-work-plugins

All 198
1pixijs avatarpixijs-mathpixijs/pixijs-skillsUse this skill when working with coordinates, vectors, matrices, shapes, hit testing, or layout rectangles in PixiJS v8. Covers Point/ObservablePoint, Matrix (26.9Kskills.sh installs
2wshobson avatarblock-no-verify-hookwshobson/agentsConfigure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code pro6.9Kskills.sh installs
3clerk avatarclerk-expo-patternsclerk/skillsExpo / React Native patterns with Clerk — SecureStore token cache, OAuth deep linking, useAuth in native, Expo Router protected routes, push notifications with 6.8Kskills.sh installs
4pixijs avatarpixijs-createpixijs/pixijs-skillsUse this skill when scaffolding a new PixiJS v8 project with the create-pixi CLI or adding PixiJS to an existing project. Covers npm/yarn/pnpm/bun create comman6.8Kskills.sh installs
5wshobson avatarsigned-audit-trails-recipewshobson/agentsStep-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating, or demonstrating the patt6.7Kskills.sh installs
6assistant-ui avatarstreamingassistant-ui/skillsStreaming backends and wire protocols for assistant-ui via the assistant-stream package. Use when building a custom (non-AI-SDK) streaming endpoint with createA6.7Kskills.sh installs