Skip to content
TrustedSkillsbeta
Back to all skills

Coderabbit

Listed
itechmeat·vlatest·backend·MIT

Coderabbit helps developers quickly generate code snippets and solutions to programming problems, boosting productivity and accelerating development workflows.

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add itechmeat/llm-code --skill coderabbit -a claude-code
  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

itechmeat

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: cli.coderabbit.ai, coderabbit.ai.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    cli.coderabbit.aiundeclaredcoderabbit.aiundeclared

    What it found (3 of 7)

    • skills/coderabbit/SKILL.md:35contacts cli.coderabbit.ai
      which coderabbit || echo "MISSING: install with: curl -fsSL https://cli.coderabbit.ai/install.sh | sh"
    • skills/coderabbit/references/agent-integration.md:35contacts cli.coderabbit.ai
      curl -fsSL https://cli.coderabbit.ai/install.sh | sh
    • skills/coderabbit/references/cli-usage.md:6contacts cli.coderabbit.ai
      curl -fsSL https://cli.coderabbit.ai/install.sh | sh
  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 5 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found (3 of 5)

    • skills/coderabbit/SKILL.md:35remote script piped into a shell
      which coderabbit || echo "MISSING: install with: curl -fsSL https://cli.coderabbit.ai/install.sh | sh"
    • skills/coderabbit/references/agent-integration.md:35remote script piped into a shell
      curl -fsSL https://cli.coderabbit.ai/install.sh | sh
    • skills/coderabbit/references/cli-usage.md:6remote script piped into a shell
      curl -fsSL https://cli.coderabbit.ai/install.sh | sh
  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • Pinned to a commit: passed

    Scanned itechmeat/llm-code at 7ae8a00524.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Scanned
15 files, 1,782 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

CodeRabbit is an AI-powered code review tool that helps developers identify and address issues in their codebase. It analyzes pull requests and local changes, providing feedback on potential problems based on a wide range of linters (over 40 supported). The skill integrates with Claude, Cursor, and Codex workflows to assist with code quality assessment and improvement.

When to use it

  • Reviewing Pull Requests: Before merging code into a main branch, use CodeRabbit to ensure quality and catch potential errors.
  • Local Development Checks: Run CodeRabbit on local changes before committing them to the repository.
  • Identifying Merge Conflicts: Use the fix merge conflict command to automatically attempt resolving conflicts.
  • Simplifying Code: Apply targeted simplifications to changed files using the @coderabbitai simplify command.

Key capabilities

  • AI-powered code review for pull requests and local changes.
  • Support for over 40 linters.
  • Integration with Claude, Cursor, and Codex workflows.
  • Commands for incremental reviews (@coderabbitai review) and complete reviews (@coderabbitai full review).
  • Ability to fix merge conflicts automatically.

Example prompts

  • coderabbit review --prompt-only --type uncommitted --no-color (Run a quick, AI-focused review of local changes)
  • @coderabbitai simplify (Apply simplifications to changed files in a pull request)
  • coderabbit review --plain --type uncommitted --no-color (Generate human-readable output for code review analysis.)

Tips & gotchas

  • Prerequisites: Before running CodeRabbit, ensure the CLI is installed and authenticated (coderabbit auth login). The repository must also have at least one commit.
  • Authentication Required: Authentication requires user interaction; the agent cannot authenticate on behalf of the user. If authentication fails, the agent should stop and prompt the user to log in.
  • Base Branch Specification: If your base branch isn't 'main', use the --base flag (e.g., --base master).