backend-selector

Multi-backend comparison and selection skill for optimal hardware choice

509 stars

Best use case

backend-selector is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Multi-backend comparison and selection skill for optimal hardware choice

Teams using backend-selector should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/backend-selector/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/domains/science/quantum-computing/skills/backend-selector/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/backend-selector/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How backend-selector Compares

Feature / Agentbackend-selectorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Multi-backend comparison and selection skill for optimal hardware choice

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Backend Selector

## Purpose

Provides expert guidance on comparing and selecting quantum backends across multiple providers based on circuit requirements and performance criteria.

## Capabilities

- Backend capability comparison
- Queue time estimation
- Cost optimization
- Fidelity-based ranking
- Connectivity analysis
- Job prioritization
- Provider API integration
- Historical performance tracking

## Usage Guidelines

1. **Requirements Analysis**: Determine circuit qubit and gate requirements
2. **Backend Query**: Fetch available backends from all providers
3. **Filtering**: Eliminate backends that cannot support circuit
4. **Ranking**: Score backends by fidelity, queue time, and cost
5. **Selection**: Choose optimal backend for execution

## Tools/Libraries

- Qiskit
- Amazon Braket
- Cirq
- Azure Quantum SDK
- pytket

Related Skills

LLVM Backend

509
from a5c-ai/babysitter

Expert skill for LLVM integration including IR generation, optimization passes, and native code emission

statistical-test-selector

509
from a5c-ai/babysitter

Skill for selecting appropriate statistical tests for analyses

thermodynamic-model-selector

509
from a5c-ai/babysitter

Automated thermodynamic property method selection based on component characteristics and operating conditions

corrosion-materials-selector

509
from a5c-ai/babysitter

Materials selection skill for corrosion resistance based on process conditions and industry standards

biocompatibility-test-selector

509
from a5c-ai/babysitter

Biocompatibility test selection and protocol recommendation skill based on device categorization

Incremental Model Strategy Selector

509
from a5c-ai/babysitter

Selects and configures optimal incremental model strategies

graph-algorithm-selector

509
from a5c-ai/babysitter

Select optimal graph algorithm based on problem constraints

data-structure-selector

509
from a5c-ai/babysitter

Select optimal data structure based on operation requirements

redis-memory-backend

509
from a5c-ai/babysitter

Redis backend for conversation state persistence and caching

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.