agentleFS
Sign inStart free
vikisingh23vikisingh23/neuraforge-ai/skills/code-review/SKILL.md

code-review

Skill4 starsChanged 6 months agoApache-2.0View on GitHub

Review code against enterprise standards — auto-detects stack (.NET, NestJS, React, RN, Flutter)

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check architecture: thin controllers, no god classes, reuse existing, composition over inheritance

    line 26
  2. Very specific:

    Check empathy: loading/error/empty states, financial formatting, a11y

    line 27
  3. Distinctive:

    Check testing: tests exist for all components/services

    line 28

“Common” is measured: kept by at least 6 in 10 of the 184 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

enterprise Code Review

Review code against enterprise Rulebook standards. Auto-detects the stack.

Instructions

  1. Detect the stack from file extension and project structure
  2. Load the appropriate reviewer:
    • .cs files → Read agents/dotnet-reviewer.md
    • .ts files with @nestjs → Read agents/nestjs-reviewer.md
    • .tsx files with React → Read agents/react-reviewer.md
    • .tsx files with React Native → Read agents/rn-reviewer.md
    • .dart files → Read agents/flutter-reviewer.md
  3. Load shared rules: core/NAMING_CONVENTIONS.md, security/SECURITY_GUIDELINES.md
  4. Score 0-100. Critical/Major/Minor/Suggestions format
  5. Check architecture: thin controllers, no god classes, reuse existing, composition over inheritance
  6. Check empathy: loading/error/empty states, financial formatting, a11y
  7. Check testing: tests exist for all components/services

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free