Communication guidelines for non-technical founders. Plain English defaults, analogy-first explanations, progressive disclosure. Use when generating any user-facing architecture output.
Translates technical architecture into plain English explanations for non-technical founders.
npx claudepluginhub navraj007in/architecture-cowork-pluginThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Guidelines for communicating architecture decisions to non-technical founders and early-stage teams. These rules apply to all outputs unless the user explicitly requests deep technical language.
Expand every acronym on first use in every deliverable:
After the first expansion, use the acronym freely.
When introducing a concept, use an analogy before the technical definition:
| Concept | Analogy |
|---|---|
| Load balancer | "Like a host at a restaurant — directs customers to available tables" |
| Message queue | "Like a to-do list between two teams — one team adds tasks, the other works through them" |
| Caching | "Like keeping frequently used files on your desk instead of walking to the filing cabinet" |
| WebSocket | "Like a phone call — both sides can talk at any time, unlike email where you send and wait" |
| Vector database | "Like a librarian who understands meaning — finds related documents even if they don't share exact words" |
| API gateway | "Like a reception desk — all visitors check in here before being directed to the right department" |
| Microservices | "Like separate departments in a company — each handles its own job and communicates through email" |
| Container | "Like a shipping container — your app and everything it needs, packed so it runs the same way everywhere" |
| CI/CD pipeline | "Like an assembly line — every code change gets automatically tested and deployed" |
Structure every output following this order:
Never lead with technical implementation details. A founder reading the output should understand the business value in the first 2 sentences.
Use these severity levels consistently:
| Severity | Label | Meaning | Example |
|---|---|---|---|
| Low | "Manageable" | Standard engineering challenge, well-understood solution | "Real-time updates add some complexity but it's a solved problem" |
| Medium | "Significant" | Requires careful planning or specialized expertise | "Multi-tenant data isolation needs to be designed carefully from day one" |
| High | "Potential dealbreaker" | Could fundamentally change scope, timeline, or feasibility | "HIPAA compliance adds 2-3 months and requires specialized infrastructure" |
Always pair a risk with a mitigation: "This is significant because X, but you can manage it by Y."
Start simple. Add detail only when:
If in doubt, keep it simple. A founder who wants more detail will ask.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.