Skip to content
TrustedSkillsbeta
Back to all skills

Backend Code Review

Checked
langgenius·vlatest·backend

Helps with backend development, code review as part of developing backend services and APIs workflows.

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 langgenius/dify --skill backend-code-review -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

langgenius

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 langgenius/dify at e6f1d77ed5.

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

Commit
e6f1d77ed5
Manifest
.agents/skills/backend-code-review/SKILL.md
Scanned
5 files, 429 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 assists with reviewing, analyzing, and improving backend code written in Python (.py) located within the api/ directory. It supports three review modes: pending changes (reviewing files slated for commit), code snippets provided by the user, and focused reviews of specific files. The goal is to provide actionable fixes and suggestions based on defined checklists or general review rules.

When to use it

  • Reviewing current changes before committing them.
  • Getting feedback on a function, class, or module excerpt you've written.
  • Analyzing specific backend files for potential improvements (e.g., api/app.py).

Key capabilities

  • Pending-change review: Inspects staged/working-tree files.
  • Code snippets review: Analyzes code provided directly in the chat.
  • File-focused review: Reviews specific files or sets of files within the api/ directory.
  • Checklist-driven reviews: Follows rules for database schema design, architecture, repository abstraction, and SQLAlchemy patterns.
  • General Review Rules: Includes security (SQL injection, SSRF, etc.) and performance checks (N+1 queries, missing indexes).

Example prompts

  • "Can you review the changes I've staged for commit?"
  • "Please review this function: def calculate_something(): ..."
  • "Could you take a look at api/users.py and let me know if there are any improvements to be made?"

Tips & gotchas

  • The skill is specifically designed for backend code within the api/ directory. It does not handle frontend code (e.g., .tsx, .js).
  • Always provide specific files or code snippets for review; avoid broad requests.
  • Actionable fixes and suggestions are expected in the output, ideally with file and line number references when available.