From magic-powers
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
npx claudepluginhub kienbui1995/magic-powers --plugin magic-powersThis skill uses the workspace's default tool permissions.
Delegate tasks to specialized agents with isolated context. Each agent gets precisely crafted instructions — never your session history.
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.
Delegate tasks to specialized agents with isolated context. Each agent gets precisely crafted instructions — never your session history.
Core principle: One agent per independent problem domain. Let them work concurrently.
Use when:
Don't use when:
Group by what's broken:
Each domain is independent — fixing auth doesn't affect rendering.
Each agent gets:
| Task Type | Agent | Why |
|---|---|---|
| Bug investigation | debugger (Sonnet) | Systematic debugging, full tools |
| Code review | reviewer (Haiku) | Fast, cheap, read-only |
| Architecture question | architect (Opus) | Deep reasoning |
| Implementation | (default subagent) | Sonnet, balanced |
After all agents complete:
| Pattern | Problem |
|---|---|
| Dumping full session context | Agents get confused, waste tokens |
| Overlapping file scope | Merge conflicts |
| Too many agents at once | Hard to coordinate |
| Not reviewing results | Agents can make mistakes |