Skip to content

kledx/engineering-review

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

engineering-review

Reusable engineering review skill for AI coding agents.

It gives agents a consistent review workflow with two clear modes:

  • review: bug finding, regressions, correctness issues, and merge blockers
  • audit: architecture, security, policy, trust boundaries, and system risk

What It Does

The skill turns vague requests like review this into a structured engineering pass:

  • detect the right review scope
  • load the minimum useful context
  • run multi-pass analysis across requirements, architecture, implementation, and tests
  • output findings first, then open questions, then a short review report

It also supports Program-driven workspaces that organize work around PROGRAM.md, STATUS.yml, and SCOPE.yml.

Repository Layout

  • SKILL.md - core skill definition
  • references/ - detailed review playbook and templates
  • agents/openai.yaml - UI metadata for compatible environments
  • scripts/install.ps1 - install into Codex skills on Windows
  • scripts/install.sh - install into Codex skills on macOS/Linux

Install

Windows

./scripts/install.ps1

Optional custom target:

./scripts/install.ps1 -TargetDir C:\Users\<you>\.codex\skills

macOS / Linux

./scripts/install.sh

Optional custom target:

./scripts/install.sh /path/to/.codex/skills

Manual install

Copy this repository into your local skills directory as:

<skills-root>/engineering-review/

If the target environment does not support Codex skills directly, load SKILL.md and keep the references/ folder beside it.

Usage

$engineering-review review current diff
$engineering-review review current Program
$engineering-review audit current architecture

Typical prompts:

  • review this feature for bugs and regressions
  • review the current Program and give me a report
  • audit this runner for architecture and security risk

Why This Exists

Fast code generation increases output, but it also increases the chance of shipping hidden regressions, weak assumptions, and incomplete implementations.

This skill exists to make review reusable, evidence-based, and consistent across repositories and agents.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors