Commit Graph

4 Commits

Author SHA1 Message Date
Gal Elmalah 638d8dd94f update evals 2026-02-08 13:25:01 +02:00
Gal Elmalah d387274482 push skills level experiments 2026-02-04 10:43:24 +02:00
Gal Elmalah 533868ad9a feat(evals): add evaluation framework with fixtures and multi-fixture support
Adds a complete evaluation system for testing skills:
- CLI runner with support for specific fixture selection via positional args
- Multiple check types (file-exists, file-content, contains, json-schema, etc.)
- Markdown report generation
- Claude Code agent integration
- 7 test fixtures covering various Base44 SDK scenarios

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 10:39:19 +02:00
Gal Elmalah f119f60f1b docs: add JSON Schema and documentation for evals
Add IDE support and comprehensive documentation for the eval test framework:

- Create eval.schema.json with definitions for all 9 check types
- Update README.md with detailed check type reference and examples
- Add $schema reference to all 7 fixture eval.json files

The schema enables autocomplete and validation in VS Code and other
editors when editing eval.json files.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 09:33:49 +02:00