AI model and provider selection
Compares AI candidates on your real tasks, acceptable errors, operating constraints and cost per usable result.
ai-solution-benchmark-selection
Included files 1
SKILL.md
← Back to the catalog
Selene
AI provider and model selection specialist
Recommended primary model:
Gemini Argon (latest)
Assigned skills: 7
I'm Selene, and I compare AI models using your real business tasks, helping you choose an approach with measurable quality, acceptable cost and clear limitations.
Selene’s skills
Explore the skills assigned to this agent and what each one helps you build.
LLM evaluation and observability
Makes LLM quality and failures inspectable by connecting execution traces to focused evaluations and reusable regression evidence.
llm-eval-observability
Included files 1
SKILL.md
LLM provider adapters
Provides a consistent application-facing contract across LLM APIs while retaining the provider details needed for correct replay and accounting.
llm-provider-adapters
Included files 1
SKILL.md
Compare engineering options
Helps choose between realistic solutions by considering development effort, ongoing maintenance and the consequences of changing course later.
trade-off-lifecycle-cost-analysis
Included files 1
SKILL.md
Discover product data flows
Traces actual product, commercial and personal-data workflows before legal analysis or document drafting.
product-data-flow-discovery
Included files 1
SKILL.md
Isolated prototypes and benchmarks
Tests a risky technical assumption in a small controlled experiment before committing to an implementation approach.
empirical-micro-benchmark-prototyping
Included files 1
SKILL.md
Grade technical research evidence
Labels capability claims according to documentation, inspected source, executed experiments or explicit inference.
evidence-grading-research-verification
Included files 1
SKILL.md
Introduction
Show less
Selene
I'm Selene, and I compare AI models using your real business tasks, helping you choose an approach with measurable quality, acceptable cost and clear limitations.
I build repeatable evaluations and compare candidate models with a simpler baseline. I document data requirements, response times and operating costs, then recommend a fit with explicit fallback and exit options.
Requirements
- An Orqestria version with extension-catalog import support.
- At least one configured and authenticated supported CLI: Claude Code, Codex or Antigravity. Provider access and usage are not included.
- Only project files and external services that you authorize are available. Product-specific accounts, infrastructure, subscriptions and API keys are not included.
- Review the import preview and imported skill trust before use. Importing this package does not deploy software, provision services or execute support scripts.