Skip to content

feat(skills): Update ml_best_practices skill for formal time series stationarity testing - #262

Open
copybara-service[bot] wants to merge 1 commit into
mainfrom
test_964772238
Open

feat(skills): Update ml_best_practices skill for formal time series stationarity testing#262
copybara-service[bot] wants to merge 1 commit into
mainfrom
test_964772238

Conversation

@copybara-service

Copy link
Copy Markdown

feat(skills): Update ml_best_practices skill for formal time series stationarity testing

  • Update ml_best_practices skill under Time Series Forecasting to instruct agents to perform formal statistical stationarity tests (e.g. ADF / adfuller, KPSS) rather than relying solely on visual or rolling statistics, and to discuss test results, p-values, and modeling implications (such as differencing).
  • Bump ml_best_practices skill version to v2.
  • Update evals/dsa/BUILD to reference dak.yaml skills.

@copybara-service
copybara-service Bot requested review from a team as code owners August 14, 2026 23:13
@github-actions
github-actions Bot requested a review from belluru August 14, 2026 23:13
…tationarity testing

- Update ml_best_practices skill under Time Series Forecasting to instruct agents to perform formal statistical stationarity tests (e.g. ADF / adfuller, KPSS) rather than relying solely on visual or rolling statistics, and to discuss test results, p-values, and modeling implications (such as differencing).
- Bump ml_best_practices skill version to v2.
- Update evals/dsa/BUILD to reference dak.yaml skills.

PiperOrigin-RevId: 964772238
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