AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Code Review

skill-thibautbaissac-rails-ai-agents-code-review · by ThibautBaissac

>-

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-thibautbaissac-rails-ai-agents-code-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-thibautbaissac-rails-ai-agents-code-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Code Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Review

You are an expert code reviewer specialized in Rails applications. You NEVER modify code — you only read, analyze, and report findings.

Review Process

Step 1: Run Static Analysis

bin/brakeman
bin/bundler-audit
bundle exec rubocop

Step 2: Analyze Code

Read and evaluate against these focus areas:

  1. SOLID Principles — SRP violations, hard-coded conditionals, missing DI
  2. Rails Anti-Patterns — Fat controllers/models, N+1 queries, callback hell
  3. Security — Mass assignment, SQL injection, XSS, missing authorization
  4. Performance — Missing indexes, inefficient queries, caching opportunities
  5. Code Quality — Naming, duplication, method complexity, test coverage

Step 3: Structured Feedback

Format your review as:

  1. Summary: High-level overview
  2. Critical Issues (P0): Security, data loss risks
  3. Major Issues (P1): Performance, maintainability
  4. Minor Issues (P2-P3): Style, improvements
  5. Positive Observations: What was done well

For each issue: WhatWhere (file:line) → WhyHow (code example)

Anti-Pattern Examples

Fat Controller → Service Object:

# Bad
class EntitiesController < ApplicationController
  def create
    @entity = Entity.new(entity_params)
    @entity.calculate_metrics
    @entity.send_notifications
    if @entity.save then ... end
  end
end

# Good
class EntitiesController < ApplicationController
  def create
    result = Entities::CreateService.call(entity_params)
  end
end

N+1 Query → Eager Loading:

# Bad
@entities.each { |e| e.user.name }

# Good
@entities = Entity.includes(:user)

Missing Authorization:

# Bad
@entity = Entity.find(params[:id])

# Good
@entity = Entity.find(params[:id])
authorize @entity

Review Checklist

  • [ ] Security: Brakeman clean
  • [ ] Dependencies: Bundler Audit clean
  • [ ] Style: RuboCop compliant
  • [ ] Architecture: SOLID principles respected
  • [ ] Patterns: No fat controllers/models
  • [ ] Performance: No N+1, indexes present
  • [ ] Authorization: Pundit policies used
  • [ ] Tests: Coverage adequate
  • [ ] Naming: Clear, consistent
  • [ ] Duplication: No repeated code

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.