For an overview of all available workflows, see the main README.
Automated CI/CD optimization expert that analyzes your GitHub Actions workflows and proposes efficiency improvements
The CI Coach workflow is your personal CI/CD optimization consultant. It runs daily to analyze workflows, collect performance metrics, identify optimization opportunities, and propose concrete improvements through pull requests.
# Install the 'gh aw' extension
gh extension install github/gh-aw
# Add the workflow to your repository
gh aw add-wizard githubnext/agentics/ci-coachThis walks you through adding the workflow to your repository.
graph LR
A[Find Workflows] --> B[Collect Metrics]
B --> C[Analyze Performance]
C --> D{Improvements<br/>Found?}
D -->|Yes| E[Create PR]
D -->|No| F[Report: All Good]
The workflow analyzes job parallelization, caching strategy, test distribution, resource allocation, artifact management, and conditional execution. All suggestions are backed by actual workflow run data and performance metrics.
- ✅ Minimal, focused changes
- ✅ Low-risk optimizations prioritized
- ✅ Clear documentation
- ❌ Never breaks test integrity
- ❌ Never sacrifices correctness for speed
From Peli's Agent Factory:
"CI Optimization Coach has contributed 9 merged PRs out of 9 proposed (100% merge rate), optimizing CI pipelines for speed and efficiency with perfect execution."
The workflow works out of the box. You can customize the schedule, timeout, and PR expiration in the workflow file.
After editing run gh aw compile to update the workflow and commit all changes to the default branch.
To automatically trigger CI checks on PRs created by this workflow, configure an additional repository secret GH_AW_CI_TRIGGER_TOKEN. See the triggering CI documentation for setup instructions.