Skip to content
TrustedSkillsbeta
Back to all skills

Critical Code Reviewer

Checked
posit-dev·vlatest·backend·MIT

This skill analyzes your backend code for potential vulnerabilities and bugs, boosting security and reliability through automated reviews.

Repository

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 posit-dev/skills --skill critical-code-reviewer -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

posit-dev

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 passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • 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 undeclared network calls: passed

    Makes no network calls.

    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.

  • 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.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

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

  • Pinned to a commit: passed

    Scanned posit-dev/skills at 1bb49b8eec.

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

Commit
1bb49b8eec
Manifest
posit-dev/critical-code-reviewer/SKILL.md
Scanned
1 file, 268 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

This skill acts as an automated, highly critical code reviewer for backend projects. It analyzes submitted code with a “zero tolerance” approach, identifying potential vulnerabilities, bugs, inefficiencies, and bad coding practices. The focus is on rigorous scrutiny and actionable feedback to improve code quality and protect the codebase from errors – not on providing positive or encouraging comments.

When to use it

  • During pull request reviews for backend projects.
  • To proactively identify potential security risks in new code.
  • When seeking a brutally honest assessment of code quality, beyond standard linting.

Key capabilities

  • Slop Detection: Identifies obvious comments, lazy naming conventions, copy-pasted code, and misused patterns (e.g., incorrect useEffect dependencies).
  • Structural Analysis: Flags issues with code organization like functions performing multiple tasks, disorganized files, inconsistent patterns, and excessive component sizes.
  • Adversarial Testing: Simulates worst-case scenarios such as unhandled Promise rejections, unexpected null values, malformed API responses, and malicious user input to identify potential failure points.
  • Language-Specific Checks: Includes specific red flags for Python code (e.g., bare except clauses).

Example prompts

  • "Review this pull request with a critical eye."
  • "Analyze this code for security vulnerabilities and inefficiencies."
  • "Conduct a thorough review of this Python script, assuming the worst possible coding practices."

Tips & gotchas

  • The skill operates under a "guilty until proven exceptional" mindset. Expect direct and potentially harsh feedback.
  • It ignores PR descriptions, commit messages, and comments – focusing solely on the code itself. Promises of future fixes or explanations are disregarded.
  • This is not intended to replace human review entirely but rather to provide an initial, rigorous assessment.