Stats
Actions
Tags
From code-review
Provides code review for openshift/hypershift repo by delegating to its .claude/ agents (API, control/data plane, cloud providers) and skills; verifies make test/verify/api and generated files. Invoke with --profile hypershift.
How this skill is triggered — by the user, by Claude, or both
Slash command
/code-review:profile-hypershiftThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This profile provides project-specific review guidance for the [openshift/hypershift](https://github.com/openshift/hypershift) repository. Instead of embedding domain knowledge, it points to the agents and skills already defined in the hypershift repo's `.claude/` directory.
This profile provides project-specific review guidance for the openshift/hypershift repository. Instead of embedding domain knowledge, it points to the agents and skills already defined in the hypershift repo's .claude/ directory.
Use this skill when --profile hypershift is specified.
The hypershift repository maintains its own Claude agents at .claude/agents/ that contain deep domain expertise (API, cloud providers, control plane, data plane, architecture). During review:
.claude/agents/ in the repo root. Pick the agents relevant to the changed files based on each agent's own description, and launch them as sub-agents.gh api repos/openshift/hypershift/contents/.claude/agents?ref=main (or the GitHub contents API) and use them.The repo also has skills at .claude/skills/ (code formatting, debugging, effective Go, git commit format, CLI conventions). Apply any that are relevant to the changed files.
make test — unit tests with race detectionmake verify — full verification suite (code generation, formatting, vetting, linting, tests)make api — required if any files in api/ were modified; regenerates deepcopy, clients, informers, and listersIf any files in the api/ directory were modified, verify that make api has been run and the generated files are included in the diff. Missing generated files are a blocking issue.
npx claudepluginhub openshift-eng/ai-helpers --plugin code-reviewConducts tiered code reviews for security (OWASP top 10), performance, and quality on staged git changes, PRs, or files before commits or releases.
Runs a structured code review using Codex, Claude, or other engines as a closeout check before commit or ship.
Multi-agent code review for GitHub pull requests using specialized agents for security, performance, style, architecture, and accessibility. Use when reviewing PRs or diffs before merge.