Dispatch two competing reviewers (arch-reviewer and impl-reviewer) before deep analysis. Competition produces more thorough results. Use before creating code, modifying architecture, making technical decisions, or answering codebase questions.
Dispatches two competing agents (arch-reviewer and impl-reviewer) in parallel before complex tasks. Use when creating code, modifying architecture, or making technical decisions to get thorough analysis from multiple perspectives.
/plugin marketplace add ANcpLua/ancplua-claude-plugins/plugin install metacognitive-guard@ancplua-claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Dispatch two competing reviewers before deep analysis. Competition produces more thorough results.
Different perspectives catch different issues. Architecture reviewers find structural problems; implementation reviewers find code-level bugs and fact-check claims. Running them in competition ("whoever finds more issues gets promoted") increases thoroughness.
Use before ANY complex task involving:
Say: "I'm dispatching two competing reviewers to analyze this."
Task(agent="arch-reviewer", prompt="[full user question + context]")
Task(agent="impl-reviewer", prompt="[full user question + context]")
Tell each agent:
"You are competing against another agent. Whoever finds more valid issues gets promoted. Be thorough."
Wait for both agents to return their analysis.
## Review Competition Results
| Reviewer | Issues Found | HIGH | MED | LOW |
|----------|--------------|------|-----|-----|
| arch-reviewer | X | X | X | X |
| impl-reviewer | Y | Y | Y | Y |
**Winner: [agent with more HIGH severity issues]**
### Combined Issues (deduplicated)
[Merge both lists]
### Verified Facts
[From impl-reviewer's fact-checking]
ONLY NOW spawn deep-think-partner with:
## Review Competition Results
| Reviewer | Issues Found | HIGH | MED | LOW |
|----------|--------------|------|-----|-----|
| arch-reviewer | 3 | 0 | 2 | 1 |
| impl-reviewer | 4 | 1 | 2 | 1 |
**Winner: impl-reviewer** (1 HIGH vs 0 HIGH)
### Combined Issues
1. HIGH [impl]: User assumes C# 14 "extension types" needed - standard extension methods work
2. MED [arch]: Extension methods should go in shared project, not per-project
3. MED [impl]: Need to verify target framework in .csproj
4. MED [arch]: Consider source generators for compile-time safety
5. LOW [impl]: Should use file-scoped namespaces
6. LOW [arch]: Missing XML documentation
### Verified Facts
- .NET 10 is LTS (November 2025), not preview
- C# 14 extension types are optional, standard works
### Feeding to deep-think-partner...
[using-superpowers] - activates chain
|
[epistemic-checkpoint] - verifies facts
|
[competitive-review] - THIS SKILL
|
+-- arch-reviewer (parallel)
+-- impl-reviewer (parallel)
|
[deep-think-partner] - receives verified context
|
[verification-before-completion] - validates result
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.
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.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.