review — community review, nixfiles, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Code Review Agents needing comprehensive content analysis and pre-commit checks. NixOS setup

TheCactusBlue TheCactusBlue
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The review skill by TheCactusBlue is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for Code Review Agents needing comprehensive content analysis and pre-commit checks.

Core Value

Empowers agents to analyze diffs for bugs, security problems, and style inconsistencies using Git commands like `git diff --staged` and `git diff`, providing findings for user review and decision-making.

Capabilities Granted for review

Automating pre-commit checks for code quality
Debugging security issues in staged changes
Reviewing style inconsistencies in unstaged code

! Prerequisites & Limits

  • Requires Git installation and configuration
  • Does not auto-fix issues, only presents findings for user decision
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

review

Install review, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Pre-Commit Self-Review

Overview

Review the current changeset for issues before committing. Analyzes the diff for bugs, security problems, leftover debug code, and style inconsistencies. Presents findings for the user to decide on — does not auto-fix.

The Process

Gather the changeset:

  • Run git diff --staged to get staged changes
  • If nothing is staged, fall back to git diff for unstaged changes
  • If both are empty, inform the user there's nothing to review

Check project conventions:

  • If CLAUDE.md exists at the project root, read it for project-specific rules
  • Note any conventions around naming, error handling, imports, or formatting
  • Use these as additional review criteria alongside the defaults

Analyze changes for issues:

  • Bugs and logic errors - Off-by-one, null/undefined access, wrong comparisons, missing edge cases, race conditions
  • Leftover debug code - console.log, debugger, print() statements, TODO/FIXME/HACK comments added in this diff
  • Security issues - Hardcoded secrets, SQL injection, XSS, unsanitized input, overly permissive permissions
  • Missing error handling - Unhandled promise rejections, unchecked return values, bare except/catch blocks
  • Style inconsistencies - Naming convention mismatches, inconsistent patterns compared to surrounding code

Present findings:

  • Group issues by severity:
    • Blocking - Bugs, security issues, or errors that must be fixed before committing
    • Warning - Likely problems worth addressing but not strictly required
    • Nitpick - Style or preference issues, take-or-leave
  • For blocking issues, suggest a specific fix with code
  • For warnings and nitpicks, describe the issue and location
  • If the changeset is clean, confirm with a brief summary of what was reviewed

Key Principles

  • Diff-focused - Only review what changed, not the entire file
  • Advisory, not automatic - Present findings for the user to act on
  • Convention-aware - Respect project-specific rules from CLAUDE.md
  • Severity-driven - Clearly separate must-fix from nice-to-have
  • Concise - Don't repeat the code back; reference file and line, describe the issue, suggest the fix

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is review?

Ideal for Code Review Agents needing comprehensive content analysis and pre-commit checks. NixOS setup

How do I install review?

Run the command: npx killer-skills add TheCactusBlue/nixfiles. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for review?

Key use cases include: Automating pre-commit checks for code quality, Debugging security issues in staged changes, Reviewing style inconsistencies in unstaged code.

Which IDEs are compatible with review?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for review?

Requires Git installation and configuration. Does not auto-fix issues, only presents findings for user decision.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add TheCactusBlue/nixfiles. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use review immediately in the current project.

Related Skills

Looking for an alternative to review or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI