General skillTesting and debugging
claude-code-genai-prompt-optimizer
Tests cheaper-model replacements against an expensive oracle and tunes prompts for measured parity.
Tests cheaper-model replacements against an expensive oracle and tunes prompts for measured parity.
genai-prompt-optimizer finds every LLM call in a GenAI app, pins one model per run, and derives adversarial cases from the app’s prompts and JSON schemas. It first records the expensive model as an oracle, then iterates on the cheaper student’s prompt and re-verifies each cohort with deterministic checks, semantic comparison, and limited judge review. The result reports measured token cost and projected savings; it asks for consent before the token-heavy run.
Resource types
Use cases
Platforms
Test mobile and desktop app navigation without routine screenshots.
Capture and decode logic-analyzer signals through natural-language requests.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Turn one browser exploration into repeatable end-to-end tests.
Query CloudWatch in natural language and investigate AWS incidents from Claude Code.