From coding-agent
Multi-perspective ideation. Architect researches the query through relevant lenses (product, architecture, security, data, cost) in its own context using Glob/Grep/Context7/Exa/DeepWiki. Only runs the perspectives the query actually needs.
npx claudepluginhub devjarus/coding-agentThis skill uses the workspace's default tool permissions.
- Architect Step 1 research (brownfield or greenfield, before writing spec)
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
The architect assesses the query and researches only the relevant perspectives in its own context — it does NOT dispatch subagents (only the orchestrator has the Agent tool in this plugin). Each perspective is a focused research mode using Glob/Grep + MCP servers. The architect synthesizes findings into a unified recommendation for the spec.
| Perspective | Use When |
|---|---|
| Product | New features, user-facing changes, MVP scoping |
| Architecture | New systems, tech stack decisions, scalability |
| Deployment | New services, hosting decisions, going to production |
| Security | Auth, user data, payments, LLM integration |
| Data | New data models, database choices, migrations |
| Cost | Cloud infrastructure, LLM API usage, vendor choices |
Most queries need 2-3 perspectives, not all 6. Assess first, then research.