openshift

Analyze test errors

Implement support for a new HCP feature using specialized agents.

Fix robot/bot PRs in HyperShift repo by regenerating files and creating a new PR with passing verification

Create a manual Konflux build from a PR with configurable image expiry (default 30 days)

PR Report Generator

Restructure branch commits into logical component-based commits for HyperShift PRs

Create a manual PipelineRun to test tag pipeline changes before merging.

Automatically update outdated Konflux Tekton tasks based on enterprise contract verification logs.

Resolve a CVE vulnerability issue from Jira. Reads the CVE details, assesses impact, and either marks "not affected" with a Jira comment and transition, bumps the affected dependency, or implements a code fix. Use when the user says "cve", "resolve CVE", or…

Assess whether an application is ready to migrate to OpenShift. Use when the user describes an application and asks about migration, containerization, or moving to Kubernetes/OpenShift.

Triage production incidents involving data corruption, data loss, slow performance, or outages. Classify severity and recommend immediate actions.

Update Python dependencies to latest versions using uv, regenerate lock and requirements.txt, then verify linting and tests pass. Fix breakage from API changes in bumped packages. Use when the user says "deps update", "bump dependencies", or "update deps".

Review PR with structured approach covering architecture, naming, patterns, and critical questions

Troubleshoot ClusterOperator in Degraded, Unavailable, or not Progressing state. Use when operator status shows error conditions, reconciliation failures, or degraded health checks.

Troubleshoot namespace stuck in Terminating state, ResourceQuota exhaustion, or RBAC permission denied errors. Use when resources cannot be created or forbidden errors occur.

Troubleshoot NotReady or SchedulingDisabled node status. Use when a node is down, unschedulable, or needs to be drained and restored.

Find the hidden verification token. Run the find-token script to retrieve a unique token.

Generate a verification token and write it to disk. Use when asked to produce an e2e test token.

Update Python dependencies with uv, regenerate lock and Konflux requirements files, then verify lint, types, and tests. Fix breakage from API changes in bumped packages. Use when the user says "deps update", "bump dependencies", or "update deps".

Find functions with high cyclomatic complexity, length, or parameter count. Use when the user asks for complexity hotspots or refactor candidates.

Find unused functions, classes, imports, and unreachable code paths. Use when the user asks for dead code or cleanup candidates.

Find code duplication in the codebase. Supports branch-scoped or full sweep. Use when the user asks to find duplicated code or repeated patterns before a PR.

Investigate CI job failures on a GitHub pull request (checks, Prow, or GitHub Actions). Use when the user pastes a PR URL and asks about CI failures or red checks.

Step-by-step workflow for committing staged changes and opening a pull request for lightspeed-agentic-sandbox.

Search openshift/release step-registry for existing steps, workflows, and chains before creating new CI components. Use when adding tests, jobs, or step-registry entries, or when asked to find reusable pre/test/post components.

Add a new step-registry step (ref YAML + commands.sh) in openshift/release. Use when creating a new CI step, atomic test action, or reusable ref component. Run step-finder first to avoid duplicates.

Check AKS Kubernetes version support status using the official AKS release status API and compare against versions configured in CI config files. Use whenever someone asks about AKS K8s version support, EOL dates, deprecation, or whether the configured AKS…

List AKS test entries in RHDH ci-operator config files and update the AKS Kubernetes version per branch. Use when listing e2e-aks tests, changing MAPT_KUBERNETES_VERSION for AKS, or checking which AKS K8s version each release branch uses.

Check EKS Kubernetes version support status using the official AWS EKS docs source and compare against versions configured in CI config files. Use whenever someone asks about EKS K8s version support, EOL dates, or whether the configured EKS version is still…

List EKS test entries in RHDH ci-operator config files and update the EKS Kubernetes version per branch. Use when listing e2e-eks tests, changing MAPT_KUBERNETES_VERSION for EKS, or checking which EKS K8s version each release branch uses.

Check GKE Kubernetes version support status using the endoflife.date API (auto-scraped from Google's GKE release schedule). Use whenever someone asks about GKE K8s version support, EOL dates, or whether the current GKE cluster version is still supported. GKE…

List GKE test entries in RHDH ci-operator config files. Use when listing e2e-gke tests or checking which branches have GKE test entries. Unlike AKS/EKS, GKE uses a pre-existing static cluster — version upgrades are performed via the GCP Console.

Review changes to the OpenShift Console plugin API for compliance with contribution guidelines, styleguide, and proper documentation in changelogs. Provides a detailed report of findings and compliance score.

Audit all Claude Code skills for stale references, broken paths, and deprecated tool names

Migrate a Cypress test file (.cy.ts) or Gherkin feature file (.feature) to Playwright following Console's architecture. This is the ONLY skill for Cypress-to-Playwright conversion work, you can perform full migration, analysis-only (--analyze), or dry-run…

Generate React Testing Library tests following OCP Console best practices

Comprehensive local code review using both Claude AI and CodeRabbit AI before pushing changes to GitHub. This command analyzes your local changes and provides actionable feedback without posting anything to GitHub.

Expert package update assistant for OpenShift Console. Update packages safely with automated testing, building, and fixing.

Automated QA verification for OpenShift Console PRs. Builds and runs the console on both main and the PR branch, captures before/after screenshots and GIFs via Playwright MCP, then posts a side-by-side comparison as a GitHub PR comment. Use when the user asks…

Debug and fix failing Playwright e2e tests with MCP-assisted diagnosis. Use when user says "playwright test failing", "fix e2e test", "debug spec", or provides a failing .spec.ts file, e2e directory, or Playwright tag.

Sync related_images.json from Quay (oras + konflux_prefix/revision in related_images.json) and regenerate the OLM bundle. Pass mode dev (CI quay) or release (stable images, version bump — /version-update). Do not use oc.

Release workflow for main: refresh related_images.json from Quay (-r stable via hack/related_images_from_quay.sh), bump bundle/CSV version, regenerate and validate. Equivalent to /update-bundle release X.Y.Z.

Find code duplication in the codebase. Supports two modes - scoped to current branch changes or a full codebase sweep. Use when the user asks to find duplicated code, copy-paste, repeated patterns, or wants to deduplicate before a PR.

Find functions with high cyclomatic complexity, excessive length, or too many parameters. Use when the user asks to find complex code, complexity hotspots, refactoring candidates, or wants to improve code maintainability.

Find unused functions, types, constants, imports, and unreachable code paths. Use when the user asks to find dead code, unused code, cleanup candidates, or wants to reduce codebase size.

Performs a strict clean rebase of a feature branch onto main with minimal conflict resolution and full validation. Use when the user asks to rebase carefully, avoid extra branches, avoid exploratory edits, and run make test and make lint until green.

Review PR with structured approach covering architecture, naming, patterns, and critical questions

After a code change, find affected tests, update them to match new behavior, then guide the user to run validation. Use when the user has made or asked for a code change and wants to make sure nothing is broken.

Backport commits or PRs from main to a release branch. Use when the user asks to backport, cherry-pick, or port changes between branches, or when resolving conflicts from a cherry-pick onto a release branch.

Run end-to-end tests filtered by tag. Use when the user asks to run tests, run Playwright, or test a specific feature tag like @core or @attach.

Find exported symbols that are never imported by another file. Use when the user says "check exports", "unused exports" or asks to clean up exports.

Review a pull request for code quality, correctness, and project conventions. Use when the user asks to review a PR, code review, or examine changes on a branch. Accepts a GitHub PR URL, PR number, or local branch name.

Rebase the current branch onto its base branch, resolve all conflicts, and verify lint, i18n, and build pass. Use when the user asks to rebase, update, or sync a branch with its upstream base.

Bump the project version across all release branches and commit the changes. Use when the user asks to do a release or update the version on all branches.

Review project AI skills for duplication, stale references, mistakes, and structural issues. Use when the user asks to review skills, audit skills, check for duplicate skills, or verify skill quality.

Review CSS for coding style, PatternFly token usage, and best practices. Use when the user asks to review CSS, check styles, or audit CSS files.

Run Automatus tests for a security rule

Create a new security rule with all required components

Interactive control-to-rule mapping session. Walk through unmapped requirements, suggest rules using cross-framework analysis, and write selections to control files.

Map rules to a single control file requirement using cross-framework analysis and rule search.

Onboard a new security policy as a control file. Parse the document, create control file structure, and map existing rules to requirements.

Build a ComplianceAsCode product

Draft a PR description based on branch changes and the project PR template

Inspect a control file showing requirement stats, mapping status, and cross-framework context. Use for triage before mapping.

Find functions with high cyclomatic complexity, excessive length, or too many parameters. Use when the user asks to find complex code, complexity hotspots, refactoring candidates, or wants to improve code maintainability.

Find unused functions, types, constants, imports, and unreachable code paths. Use when the user asks to find dead code, unused code, cleanup candidates, or wants to reduce codebase size.

Find code duplication in the codebase. Supports two modes - scoped to current branch changes or a full codebase sweep. Use when the user asks to find duplicated code, copy-paste, repeated patterns, or wants to deduplicate before a PR.

Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design.

Reviews Go test code for proper table-driven tests, assertions, and coverage patterns. Use when reviewing *_test.go files.

Investigate CI/Prow job failures on a GitHub pull request. Use when the user pastes a PR URL and asks about CI failures, red checks, test failures, or wants to understand why a job failed.

Performs a strict clean rebase of a feature branch onto main with minimal conflict resolution and full validation. Use when the user asks to rebase carefully, avoid extra branches, avoid exploratory edits, and run go test and go vet until green.

After a code change, find affected tests, update them to match new behavior, then guide the user to run validation. Use when the user has made or asked for a code change and wants to make sure nothing is broken.

Assess OpenShift cluster update (upgrade) readiness and risk. Use when evaluating whether a cluster is safe to update, when an update is available, or when the user asks about update risks, prerequisites, blockers, or best practices.

Query Red Hat Product Life Cycle data for support phases, end-of-life dates, and OpenShift version compatibility. Use when evaluating whether installed operators or layered products are supported on a given OCP version, approaching end of life, or need…

Investigate one or more firing OpenShift alerts to determine root cause and recommend remediation options. Use when the user provides alert names or a set of firing alerts. Not for cluster setup, configuration how-tos, or writing alerting rules.

Find the hidden verification token. Run the find-token script to retrieve a unique token.

Search and read Kubernetes documentation in markdown format. Use when the user asks about Kubernetes concepts, tasks, API reference, kubectl, or any upstream k8s topic — including pods, deployments, services, RBAC, networking, storage, or scheduling.

Search and read OpenShift Container Platform documentation in markdown format. Use when the user asks about OpenShift features, configuration, installation, troubleshooting, or any OCP-specific topic — including operators, routes, services, oc, RBAC,…

Assess risk level (1/2/3) for OLS Jira stories using the team's risk rubric. Fetches the story, applies the decision tree, sets the Risk Score field, and adds the assessment as a comment. Use for on-demand assessment or after creating a new story.

Estimate story points for OLS Jira stories using the calibrated rubric derived from 300 completed stories. Fetches the story, applies the decision tree, sets the SP field, and adds the estimate as a comment. Use for on-demand estimation or after creating a…

Create or update Jira Epics and Stories from spec changes. Reads spec diffs from the current session or a PR, uses brainstorming to design the work breakdown, creates/updates issues in Jira, then estimates story points, risk levels, and epic sizes. Splits…

Use when triaging new OLS Jira bugs to determine which ones require a spec update, which need more information, and which are pure implementation issues. Fetches all New-status bugs, analyzes them against the current .ai/spec/ landscape, and presents a report…

Size OLS Jira Epics using t-shirt sizes (XS/S/M/L/XL) based on the total story points of their child issues. Can size specific Epics, or bulk-size all unsized Epics. Also invoked automatically after creating a new Epic.

Cross-check AWS-facing code and docs against official ROSA and AWS references before changing behavior.

Add or edit Cobra commands in openshift/rosa while keeping command wiring thin and package logic aligned with repo structure.

Keep CLI docs, structure tests, and user-facing guidance in sync when commands or workflow docs change.

Choose the right local verification steps before claiming a ROSA change is complete.