Skip to content

Eval Driven Development#4

Open
djscheuf wants to merge 26 commits into
mainfrom
feat/edd
Open

Eval Driven Development#4
djscheuf wants to merge 26 commits into
mainfrom
feat/edd

Conversation

@djscheuf

@djscheuf djscheuf commented Jun 30, 2026

Copy link
Copy Markdown
Owner

Let's get some TDD on these prompts!

Currently in place:

  • Working Promptfoo Evals for 2 of the Skills ( starting at the top)
  • built on the Improving Promptfoo Wrapper
  • Both tests run against multiple models, using Haiku and SWE 1.6 for now.
  • Test results separated
  • Tests use the skill as invoked by windsurf agents.

More details to come.

djscheuf added 26 commits June 29, 2026 14:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant