Rework analyze-ci-failures skill#51513
Merged
vicroms merged 8 commits intoMay 13, 2026
Merged
Conversation
Member
|
Neat report! I'm not that surprised to see GPT win at this. |
BillyONeal
previously approved these changes
May 3, 2026
…s and minimum viable report format
Member
|
Drafted this because you still seem to be making changes. |
Co-authored-by: Billy O'Neal <bion@microsoft.com>
BillyONeal
previously approved these changes
May 7, 2026
BillyONeal
left a comment
Member
There was a problem hiding this comment.
I know I asked for curl commands in that one spot but this iteration has bigger pwsh blocks so I guess it doesn't matter. We might want to consider bash translations because when copilot-cli runs in there that's what it'll get but not worth it for now
BillyONeal
approved these changes
May 13, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I created an evaluation project for the AI agent skills in vcpkg using Microsoft/waza.
The skill is evaluated
analyze-ci-failuresusing five different models and grading the produced output. The skill is asked to analyze the output of a real CI run and generate a report of the regressions found.The changes to the skill were motivated by the output of the
waza checkandwaza runcommands, in combination this evaluate the quality of the skill and the output it produces. Taking an iterative approach the skill was reworked to greatly reduce over-specificity and produce output that can pass the evaluation metrics.I plan to make the evaluations public but probably kept in a separate repository (or maybe another branch?). The evaluation graders are:
I also ran a test comparing the best performing model with and without the skill.
Comparison (no skill vs skill improvements)
Average score (3 runs):
Cost report
Token Usage Per Trial
Cost Breakdown Per Trial