borghei/Claude-Skills / engineering/code-reviewer
code-reviewer
VerifiedHeuristic code-review pre-pass for TS, JS, Python, Go, Swift and Kotlin: PR risk, smells, SOLID issues, and a two-axis (standards vs spec) review method. Use when reviewing a PR or preparing a review checklist.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.0 KB |
| assets/two-axis-review-template.md | markdown | 1.0 KB |
| references/code_review_checklist.md | markdown | 6.9 KB |
| references/coding_standards.md | markdown | 12.1 KB |
| references/common_antipatterns.md | markdown | 16.1 KB |
| references/tool_reference.md | markdown | 10.9 KB |
| references/two-axis-review.md | markdown | 6.3 KB |
| scripts/code_quality_checker.pyexecutable | script | 17.1 KB |
| scripts/pr_analyzer.pyexecutable | script | 14.2 KB |
| scripts/review_report_generator.pyexecutable | script | 17.5 KB |
| scripts/review_scope.pyexecutable | script | 7.9 KB |
assets/two-axis-review-template.md
View on GitHub# Review: <branch or PR title>
**Base:** `<base ref>` (`<base sha>`) · **Head:** `<head sha>` · **Diff:** `git diff <base>...<head>`
**Commits:** <n> · **Files:** <n> · **Lines changed:** <n>
**Spec source:** <path, issue link, or "none found">
**Standards sources:** <files>
## Standards
<Report from the standards pass, lightly cleaned. One finding per bullet.>
- `<file:line>` — <what is wrong>. Rule: <source file> — "<rule>". **Hard** | **Judgement**
**Summary:** <n> findings; most serious: <one line>.
## Spec
<Report from the spec pass. Quote the spec line for every finding.>
### Missing or partial
- "<spec line>" — <what is missing>
### Not asked for
- `<file:line>` — <behaviour>. Bucket: enabling | unrequested | speculative
### Built wrongly
- "<spec line>" — <how the implementation differs>
**Summary:** <n> findings; most serious: <one line>.
## Overlaps
- <finding raised by both passes, listed once here>
## Verdict
**<Approve | Request changes | Block>** — <one sentence naming the deciding finding(s)>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |