Skip to content

Latest commit

 

History

History
12 lines (9 loc) · 614 Bytes

File metadata and controls

12 lines (9 loc) · 614 Bytes

Model Compatibility Matrix

Track which prompts/skills have been verified against which models. Update this whenever you re-run the eval suite after a model update.

Prompt/Skill Target Model Last Verified Status
refactor-logic gpt-4o 2026-06-01 ✅ Pass
code-reviewer (skill) claude-sonnet-5 2026-06-01 ✅ Pass
data-parser (skill) gpt-4o 2026-06-01 ✅ Pass

Legend: ✅ Pass · ⚠️ Degraded (works with caveats) · ❌ Failing · ➖ Not yet tested