pipeline-setup

To set up an isolated git worktree for automated pipeline runs, you can use a pipeline-setup tool that provisions a dedicated worktree, auto-detects project tooling, and runs baseline metrics. This creates a reproducible environment and outputs a baseline.json file for downstream pipeline stages.

Capturing baseline code coverage and test metrics requires running type checks, lint, and tests at the start of your workflow. A pipeline-setup skill automates this by executing baseline checks and outputting the results to a baseline.json file, establishing a reference point for downstream stages.

Auto-detecting project tooling across Python, Go, and other languages involves scanning for configuration files like package.json, pyproject.toml, go.mod, and Cargo.toml. The pipeline setup process automatically identifies these manifests to configure the environment and run the appropriate baseline checks.

Yes, you can use a single pipeline setup step for both standalone tasks and orchestrated workflows. The setup process applies universally by provisioning a git worktree, loading configurations, and generating spec artifact directories with necessary environment variables for any downstream tasks.

Deriving a spec name and creating a spec artifact directory organizes environment outputs and baseline metrics for downstream tasks. This ensures that orchestrated pipeline stages can access the generated SPEC_NAME and baseline.json within a structured docs/spec path, maintaining reproducibility.

Loading a constitution file when bootstrapping a development pipeline shapes sub-agent behavior and establishes project guidelines. This ensures that automated tasks and downstream pipeline stages adhere to defined standards while operating within the isolated git worktree environment.