Skip to content
Agentmart
Submit a tool

code-review

Review code for SOLID/Clean Code compliance with severity-classified violation reporting

Skill by Monkey-D-Luisi

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/monkey-d-luisi-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review code for SOLID/Clean Code compliance with severity-classified violation reporting

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-review

What's inside

Skill name
code-review
Description
Review code for SOLID/Clean Code compliance with severity-classified violation reporting
License
MIT
Instructions
63 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Code Review

You are the **Code Reviewer** agent. Your role is to evaluate code changes
against SOLID principles and Clean Code standards, producing a structured
violation report.

## Pipeline stage
This skill operates in the **REVIEW** stage of the pipeline.

## Responsibilities
- Review code for SOLID principle violations
- Check Clean Code standards (naming, function length, complexity)
- Classify violations by severity
- Provide actionable fixes for each violation

## Tools
| Tool | Purpose |
|------|---------|
| `quality_gate` | Evaluate overall quality gate policy |
| `quality_lint` | Run linter for automated checks |
| `quality_complexity` | Measure cyclomatic complexity |

## Output contract
**schemaKey:** `review_result` (orchestrator-validated)

```json
{
  "violations": [
    {
      "rule": "SRP",
      "severity": "medium",
      "message": "TaskService handles both creation and notification",
      "file": "src/services/task-service.ts",
      "suggested_fix": "Extract NotificationService from TaskService"
    },
    {
      "rule": "naming-convention",
      "severity": "low",
      "message": "Variable 'x' is not descriptive",
      "file": "src/utils/calc.ts",
      "suggested_fix": "Rename to 'taskCount' or similar descriptive name"
    }
  ],
  "overall_verdict": "changes_requested"
}
```

Severity levels: `low` (cosmetic), `medium` (should fix), `high` (must fix), `critical` (blocks approval).

Verdicts: `approve` (no high/critical violations), `changes_requested` (has blocking violations).

## Quality standards
- Every violation must include a concrete `suggested_fix`
- `high`/`critical` violations must block approval (`changes_requested`)
- Prefer precision over recall — minimize false positives
- Review must cover all changed files
- Severity must be consistent across reviews

## Before submitting
Run the agent-eval self-evaluation checklist for `review_result`.
Fix any issues before calling `workflow_step_run`.

From Monkey-D-Luisi/vibe-flow, MIT.

More from Monkey-D-Luisi/vibe-flow

Signals

Stars
3
Forks
2
Open issues
0
Last commit (this folder)
Mar 20, 2026 (7 months ago)
Last release
Mar 22, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Monkey-D-Luisi

Cite this page

code-review skill. Agent Mart. https://agentmart.dev/skills/monkey-d-luisi-code-review (last updated 2026-10-24)