opencode

Use when implementing code changes, bug fixes, refactors, or multi-step edits that may sprawl; keeps work split into atomic, independently verifiable changes.

Helm chart development patterns for packaging and deploying Kubernetes applications. Use when creating reusable Helm charts, managing multi-environment deployments, or building application catalogs for Kubernetes.

Generate commit messages following conventional commit format.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

Use when building Go-based Kubernetes agents/controllers, reconcile loops, or cloud-native systems. Invoke for controller-runtime, CRDs, leader election, and Go concurrency.

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.

Audit OpenCode configuration quality, safety, and operability with a 100-point rubric and concrete remediations.

Stage specific code hunks using git hunks for selective commit preparation

Build and optimize PySpark pipelines on Databricks.

Proactively simplify recently modified code while preserving exact behavior.