oprogramadorreal/optimus-claude Skills

This skill performs local-first code review — analyzes uncommitted changes (or PRs) against project coding guidelines using up to 6 parallel review agents (bug detection, security/logic, guideline compliance ×2, code simplification, test coverage). HIGH SIGNAL only: real bugs, logic errors, security concerns, and guideline violations.

This skill suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits.

This skill prepares a project for Claude Code — generates CLAUDE.md with progressive disclosure docs, auto-format hooks, and code-quality agents (code-simplifier, test-guardian). Also audits and syncs existing documentation against source code. Replaces /init. Supports single projects, monorepos, and multi-repo workspaces (separate git repos under a shared parent directory).

This skill configures Claude Code permissions for safe agent autonomy. Creates settings.json with allow/deny rules and a path-restriction hook.

This skill analyzes the codebase against project coding guidelines as on-demand code simplification — run after /optimus:init, when code quality drifts, or for periodic cleanup. Surfaces issues that span multiple files (duplication across modules, pattern inconsistency, architectural drift) and presents a simplification plan for approval before changes are applied.

This skill improves unit test coverage on demand — discovers testing gaps, provisions test infrastructure, and generates tests that follow project conventions. Conservative: only adds new test files, never refactors existing source code.