skills.rest
beratcelik1
beratcelik1COMMUNITY
Explore all skills by this author →
Website𝕏@beratcelik0GitHub

review-code

Review Python and TypeScript code changes with parallel agents and P1/P2/P3 severity findings.

1|Updated Mar 5, 2026
Search Tags:#automation#typescript#code review#pull request#security#python#multi-agent
One-click install
npx skills add https://github.com/beratcelik1/compound-claude --skill review-code-beratcelik1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-code
Source: https://github.com/beratcelik1/compound-claude/tree/main/skills/review-code
Command: npx skills add https://github.com/beratcelik1/compound-claude --skill review-code-beratcelik1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Long, inconsistent, or manual code reviews miss security, architectural, and style issues and slow merges; this Skill runs coordinated, exhaustive reviews across changed files or pull requests so problems are found and prioritized before merge.

Core Features & Use Cases

  • Target detection: Accepts a PR number, branch name, or 'latest' to determine the review scope and defaults to the current branch vs main when empty.
  • Language-aware parallel reviewers: Detects changed file types and runs appropriate agents such as python-reviewer and typescript-reviewer alongside always-on checks like simplicity-reviewer and security-sentinel.
  • Synthesis and triage: Aggregates agent outputs, removes duplicates, categorizes findings into P1/P2/P3 severity levels, and produces actionable remediation items and a summary report suitable for blockers and next steps.
  • Scale-aware behavior: Escalates to architecture-strategist and pattern-detective for large changes and can offer auto-fix suggestions for simple issues.

Quick Start

Run the review-code skill targeting the current branch by supplying 'latest' or a PR number to get a prioritized, actionable review report.

Frequently Asked Questions about review-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code review for a pull request across Python and TypeScript files?▼

Automate code review by running coordinated agents that detect changed file types, evaluate security and style, and synthesize findings into a prioritized P1/P2/P3 remediation report. Provide a PR number or branch name to set the review scope.

Can I run a multi-agent code review on my current branch without specifying a pull request number?▼

Run a multi-agent code review on your current branch by passing 'latest' as the target. The system defaults to comparing the current branch against main when no explicit PR number or branch name is provided.

What is the best way to triage security and architecture issues in a large pull request?▼

Triage security and architecture issues by escalating to specialized agents like architecture-strategist and security-sentinel. The system scales review behavior for large changes, categorizing aggregated findings into P1/P2/P3 severity levels with actionable remediation steps.

Does this automated code review support mixed-language repositories?▼

Automated code review supports mixed-language repositories by detecting changed file types and dispatching language-aware parallel reviewers, such as python-reviewer and typescript-reviewer, alongside always-on simplicity and security checks.

How are duplicate code review findings handled when multiple agents analyze the same changes?▼

Duplicate code review findings are handled during the synthesis and triage phase. The system aggregates outputs from parallel specialized agents, removes duplicates, and categorizes the remaining findings into P1/P2/P3 severity levels for a clean summary report.

When should I not use a multi-agent automated code review?▼

Avoid multi-agent automated code review for trivial single-file changes where manual inspection is faster, as the system escalates to architecture-strategist and pattern-detective agents designed for exhaustive, large-scale pull request evaluations.

Related Skills

Explore More Software Engineering Skills→
nbbaiernbbaier
1

workflows-review

Review pull requests with parallel AI agents and Git worktrees.

Community
Advanced
jovermierjovermier
1

quality-severity

Classify issues and code review findings into P1, P2, or P3 severity levels.

Community
Basic
arcasilesgrouparcasilesgroup
54

ai-pr

Automate governed pull request workflows with pre-push gates and squash merge.

Official
Advanced
barbosakjnbarbosakjn
1

lint-and-validate

Automates linting and static analysis for Node.js/TypeScript and Python projects.

Community
Intermediate