
code-reviewer
(NS) Senior Tech Lead code review on SOLID, clean code, performance, security, and testability. Use proactively after writing or modifying code, before opening PRs, after implementation closure, or when the user asks for a code review, PR review, or issue review gate — even if they do not name this skill. For GitLab issue execution with ISSUEURL, use Issue review mode. Do NOT use for root-cause debugging (use code-investigator).
- Installs
- 50
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/nextstage-brasil/skills --skill code-reviewer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads code-reviewer automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Code Reviewer
Deep, constructive review of code changes against project rules and acceptance criteria.
Harness discovery
See ../nextstage-harness/references/harness-discovery.md. Load rules from {harness_root}/rules/*.md. Read architecture-rules.md first. Legacy: .cursor/rules/*.mdc only if {harness_root} is absent. Load layer-specific rules (backend, frontend, tests, e2e) based on changed files.
Do not assume Grogoo/Laravel/React unless detected in project rules or stack context.
Workflow
- Load applicable project rules.
- Run
git diff(andgit statusif needed). - Focus on modified files and surrounding context.
- Start immediately — do not ask permission to begin.
Version closure
When invoked at version closure, save output to {product_root}/docs/versions/{version_san}/code-review-report.md using references/review-report.template.md.
Issue review mode
When invoker passes ISSUE_URL (or project_id + issue_iid):
- Delegate issue context to
execution-gitlab-issuecontext flow orgitlab-issue-context-agent— do not callread_issueyourself if a synthesis block is provided. - Diff
origin/<target>...origin/<source>from synthesis — never review wrong branch. - Requirement proof gate: every AC needs behavioral evidence; producer-only code without consumer is Critical.
- Verdict (exactly one):
Approved|Rejected|Blocked - Post internal GitLab comment via
mcp-gitlab-usage— first line:Code Review | YYYY-MM-DD HH:MM (UTC) | Verdict: {Approved|Rejected|Blocked} - Last line of response to parent:
Code Review: {Approved|Rejected|Blocked}
Review priorities
Within each section, order by severity:
- Critical (must fix before merge)
- Warning (should fix)
- Suggestion (consider)
SOLID and clean code
- SRP, OCP, LSP, ISP, DIP
- Naming, cyclomatic complexity, error handling, dead code
Performance, security, testability
- N+1, unnecessary renders, missing validation
- SQL injection, XSS, sensitive logs
- Coupling that blocks testing
Required output format
Structure every review as:
Executive Summary
- Score 1–10
- Two-line overall assessment
Critical Issues
Omit only if none. Logic bugs, security, severe SOLID or architecture violations.
Architecture and Clean Code Improvements
Refactoring suggestions, component boundaries, patterns.
Refactored Code
Include only when user requests concrete fixes.
Constraints
- Read-only. Do not edit, create, or delete files — output is a review report, not a fix
- Direct and constructive; no personal criticism
- Do not rewrite unrelated code
- Base findings on actual diff and rules read
- Match project conventions visible in codebase
References
| File | When |
|---|---|
references/review-report.template.md | Version closure report |
../nextstage-harness/references/artifact-layout.md | Report path |
mcp-gitlab-usage | Posting internal review comments |
FAQ
What does the code-reviewer skill do?
(NS) Senior Tech Lead code review on SOLID, clean code, performance, security, and testability. Use proactively after writing or modifying code, before opening PRs, after implementation closure, or when the user asks for a code review, PR review, or issue review gate — even if they do not name this skill. For GitLab issue execution with ISSUEURL, use Issue review mode. Do NOT use for root-cause debugging (use code-investigator).
How do I install code-reviewer?
Run npx skills add https://github.com/nextstage-brasil/skills --skill code-reviewer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/code-reviewer/ (personal) or .claude/skills/code-reviewer/ (project).
Which AI agents can use code-reviewer?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is code-reviewer safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains code-reviewer?
It is published by nextstage-brasil in nextstage-brasil/skills. It has 50 recorded installs.
More from nextstage-brasil/skills
ns-gitlab-board-sync
nextstage-brasil/skills
(NS) Sync existing GitLab issues with local planning/execution — milestone, RF labels, status, assignee, estimates, spent time. Use during implementation when tasks link to GitLab issues or after plan-version-from-gitlab sync — not for creating new issues (use mcp-gitlab-usage). Always atomic setissuelabels and three-step status cycle.
ns-spec-driven
nextstage-brasil/skills
Open the skill to read its SKILL.md instructions.
ns-gitlab-ci-generator
nextstage-brasil/skills
Open the skill to read its SKILL.md instructions.
ns-project-manager
nextstage-brasil/skills
Open the skill to read its SKILL.md instructions.
mcp-gitlab-usage
nextstage-brasil/skills
Open the skill to read its SKILL.md instructions.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.