Multi-perspective Code Review

Trust Score 90/100

Run a comprehensive, multi-agent code review that covers quality, security, and database concerns and synthesises a severity-ranked findings table.

triggers:code reviewsecurity reviewis this securecheck for vulnerabilitiesreview changes

GitHub SKILL.md

What it does

This skill orchestrates parallel review agents to produce a thorough code review: a code-quality pass, a security-focused audit (OWASP Top 10 and project-specific checks), and a database/migration analysis. It synthesises findings into a severity-rated table and provides a GO/NO-GO verdict.

When to use it

Invoke this for PR reviews, branch audits, or when prompted with ‘security’ to run a focused vulnerability scan. Use for large diffs, release gating, or pre-deploy safety checks. For quick scans use the lighter review-diff skill.

What's included

Scripts: procedural steps for detecting scope (files, branches, uncommitted changes) and spawning reviewer agents in parallel.
References: none bundled but the skill describes checks to run (OWASP, N+1 detection, Prisma patterns).
Instructions: step-by-step: detect scope, spawn agents, run code quality checks, run security checks, run DB analysis, synthesise findings, and return a GO/NO-GO verdict.

Compatible agents

Fits with Claude Code/Codex-style multi-agent setups and CI integrations that can spawn parallel reviewer agents.

Audit Summary

Multi-perspective code review skill that spawns parallel agents for quality, security, and database concerns. Well-structured with clear step-by-step workflow, argument handling for file/branch/range scope, and a synthesized severity-ranked findings table with GO/NO-GO verdict. No bundled scripts — purely a prompt-orchestration skill. Clean security profile with no risky patterns.

Watch Out

Requires agent spawning capability to leverage full multi-agent parallel review
Small changes (<50 lines) only spawn code-reviewer agent by default

Notes

Prompt-only skill with no scripts to execute. The multi-agent approach (code-reviewer, security-reviewer, db-analyst) is well-designed and practical. OWASP Top 10 coverage in security review is a strong point.

Information

Repository: claude-code-blueprint
Stars: 22
Installs: 0

Trust Score

Overall90

Security100

Code Quality82

Architecture78

Usefulness72

More from claude-code-blueprint

E2E Check

Run end-to-end Playwright test suites or perform interactive browser walkthroughs to verify UI and user journeys for a project.

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

TradeOS

Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r

Java 25 & Spring Boot 4 Code Reviewer

Run focused, evidence-based code reviews for Java 25 and Spring Boot 4 projects — migration risks, architecture boundaries, null-safety (JSpecify), security, an

ArcKit — French Public Procurement (fr-marche-public)

Generates French public procurement (Dossier de Consultation des Entreprises) drafts aligned with the Code de la Commande Publique, UGAP frameworks, and DINUM d

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Neo4j Graph Database

Run Cypher queries and manage nodes/relationships against a local Neo4j instance exposed in the Docker network.

WhoDB

Database assistant for exploring and querying Postgres, MySQL, SQLite, MongoDB, Redis, Elasticsearch and ClickHouse — via MCP tools or CLI fallbacks.

Cursor Hello World Tutorial

A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.

Back to Skills