- Evaluates conversations across 10 metrics: taskCompletion, accuracy, relevance, clarity, efficiency, userIntentAlignment, actionability, progress, errorHandling, completeness - Returns weighted overall score (0-10) - Provides verdict (pass/retry/fail) with reasons - Detects conversation loops and stuck states - Lists must-dos, suggestions, and next steps - Designed for frequent use in agentic loops |
||
|---|---|---|
| .. | ||
| bridge | ||
| config | ||
| db | ||
| env | ||
| mcp-client | ||
| mocks | ||
| npm-client | ||
| package-executor | ||
| storybook | ||
| test | ||
| tool-ideas | ||
| tools | ||
| types | ||
| ui | ||
| utils | ||