// Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.
Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations.
Transfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
| name | ensemble-solving |
| description | Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality. |
Generate multiple solutions in parallel by spawning 3 subagents with different approaches, then evaluate and select the best result.
Activation phrases:
Good candidates:
Skip ensemble for:
Determine which category fits:
Task tool with:
- subagent_type: 'ensemble-orchestrator'
- description: 'Generate and evaluate 3 parallel solutions'
- prompt: [User's original task with full context]
The orchestrator handles:
The orchestrator returns:
For Code (Constraint Variation):
| Approach | Focus |
|---|---|
| Simplicity | Minimal code, maximum readability |
| Performance | Efficient, optimized |
| Extensibility | Clean abstractions, easy to extend |
For Architecture (Approach Variation):
| Approach | Focus |
|---|---|
| Top-down | Requirements → Interfaces → Implementation |
| Bottom-up | Primitives → Composition → Structure |
| Lateral | Analogies from other domains |
For Creative (Persona Variation):
| Approach | Focus |
|---|---|
| Expert | Technical precision, authoritative |
| Pragmatic | Ship-focused, practical |
| Innovative | Creative, unconventional |
| Criterion | Base Weight | Description |
|---|---|---|
| Correctness | 30% | Solves the problem correctly |
| Completeness | 20% | Addresses all requirements |
| Quality | 20% | How well-crafted |
| Clarity | 15% | How understandable |
| Elegance | 15% | How simple/beautiful |
Weights adjust based on task type.
User: "What's the best way to implement a rate limiter?"
Skill:
Output:
## Selected Solution
[Full rate limiter implementation with strategy pattern]
## Why This Solution Won
The extensible approach scored highest (8.4) because it provides
a clean abstraction that works for both simple use cases and
complex distributed scenarios. The strategy pattern allows
swapping Redis/Memcached backends without code changes.
## Alternatives
- **Simple approach**: Best if you just need basic in-memory
limiting and will never scale beyond one process.
- **Performance approach**: Best for high-throughput scenarios
where every microsecond matters.
~4x overhead vs single attempt. Worth it for: