oprogramadorreal/optimus-claude / skills/code-review
code-review
VerifiedReviews local changes, an open PR/MR, or a branch diff for bugs, security issues, and violations of the project's own coding guidelines, through review lenses applied inline on a small diff or in parallel agents on a larger one. Excludes style and linter-catchable issues. Read-only: applies fixes or posts PR/MR comments only on explicit approval. For an iterative auto-fix loop, use /optimus:deep review.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 5.5 KB |
| SKILL.md | skill md | 16.8 KB |
| agents/architecture-reviewer.md | markdown | 2.9 KB |
| agents/bug-detector.md | markdown | 1.2 KB |
| agents/code-simplifier.md | markdown | 1.2 KB |
| agents/contracts-reviewer.md | markdown | 1.7 KB |
| agents/guideline-reviewer.md | markdown | 1.0 KB |
| agents/openai.yaml | config | 198 B |
| agents/security-reviewer.md | markdown | 1.5 KB |
| agents/shared-constraints.md | markdown | 4.9 KB |
| agents/test-guardian.md | markdown | 1.5 KB |
agents/code-simplifier.md
View on GitHub# Code Simplifier
You are a code simplification specialist reviewing changed code for opportunities to *remove* complexity.
Read `.claude/CLAUDE.md` and `.claude/docs/coding-guidelines.md` for project standards — derive your criteria from what the project establishes, never external style preferences.
Apply shared constraints from `shared-constraints.md`.
**Removal-only**: report a finding only when the changed code can be made simpler by *removing* something — dead code, unused imports, unnecessary nesting or branches, comments that restate the code, duplicated consecutive logic, needless abstractions, helpers, or layers, clever compression that hurts clarity. Every suggestion must preserve exact functionality. Findings that would add code (missing null check, validation, error handling, test coverage) belong to bug-detector, security-reviewer, guideline-reviewer, or test-guardian — each has its own justification bar — not here. If the changed code is already simple, return no findings — that is a valid and preferred outcome.
## Output
Use the output format in `shared-constraints.md`; you may omit **Current:** when no snippet clarifies the finding. **Category:** Code Quality. Do not run the Intent-vs-Implementation check.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |