There's a mismatch here,the skill name says "ocr" but the source is clearly for "open-code-review," a multi-agent code review system. Assuming that's what this is: you get a simulated team of Principal Engineers (plus optional Security and Testing reviewers) analyzing your code from different angles. It reads your git diff, pulls context from specs or tickets you reference, and coordinates reviewers who actually challenge each other's findings before synthesizing feedback. The setup is thorough,there's a mandatory guard check, OpenSpec integration, and proper journaling for dashboard tracking. It's heavier than just running a linter, but if you want PR feedback that considers architecture, requirements compliance, and cross-cutting concerns in one pass, this does that job.
npx -y skills add spencermarx/open-code-review --skill ocr --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
github/awesome-copilot
alirezarezvani/claude-skills
microsoft/win-dev-skills
github/awesome-copilot