masoncl/review-prompts

AI review prompts

What it solves

This project provides a set of specialized prompts for AI-assisted code review, specifically tailored for complex low-level systems programming projects like the Linux kernel, systemd, and iproute. It helps AI agents (such as Claude Code) apply project-specific patterns, protocols, and bug patterns to the review process.

How it works

The system uses a combination of skill files, slash commands, and subsystem files to provide context to the AI. Skill files automatically detect the working directory to load the correct project context. Slash commands (e.g., /kreview for the kernel) provide quick access to specific workflows for reviewing, debugging, and verifying code. Subsystem files provide domain-specific knowledge that is loaded on demand.

Who it’s for

Developers working on the Linux kernel, systemd, or iproute who use AI tools for code review and debugging.

Highlights

  • Project-Specific Context: Automatically loads context based on the project tree you are working in.
  • Workflow-Specific Commands: Dedicated slash commands for review, debug, and verify tasks.
  • Project-Specific Bug Patterns: Includes documentation on bug patterns for the kernel, systemd, and iproute.
  • Tool Integration: Optimized for use with semcode for semantic search and code navigation.

Related

  • Project
    Piebald-AI/claude-code-system-prompts

    A comprehensive collection of extracted system prompts from Claude Code, providing transparency into the instructions used by its various agents and tools.

  • Project
    cyberchitta/llm-context.py

    A context curation tool that enables AI coding agents to automatically identify, pack, and manage the specific files and code excerpts needed for a task to avoid token limits and missing information.

  • Project
    alibaba/open-code-review

    An AI-powered code review CLI tool that combines deterministic engineering with an agentic workflow to provide high-precision, line-level feedback on Git diffs and full files.

  • Project
    kunal12203/GrapeRoot

    A context engine for AI coding assistants that builds a semantic graph of a codebase to pre-load relevant code into prompts, reducing token usage and response times.

  • Project
    KKKKhazix/khazix-skills

    A collection of standardized AI agent skills (instruction sets) for goal definition, disk cleanup, deep research, and project documentation maintenance.