agentsclimarketplace

Fresh eye

Skill victoriacheng15/dev-toolchain/fresh-eye

A portable library of standardized AI agent skills and orchestration scripts, built on the SKILL.md open standard to streamline consistent engineering workflows across diverse LLM clients.

Install
npx -y skills add victoriacheng15/dev-toolchain --skill fresh-eye

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Analyzes git diffs to perform local code quality reviews, outputting feedback directly to standard output.

SKILL.md

1.7 KB, as published. Nobody here has run it

Code Review Sanity Checks

Overview

Self-review is a critical step in the software development lifecycle. This skill automates the analysis of staged and unstaged code modifications (git diff) to identify common errors, logic gaps, debug statements, and coverage omissions before code is committed. It prints findings directly to standard output (stdout) and sets exit codes to gate commits.


Automated Execution

To run the automated code review script, execute it from the root of the workspace:

./fresh-eye/fresh-eye.sh

Exit Codes

  • 0: Success. No blocker or high-priority issues were detected.
  • 1: Failure. Blocker or high-priority issues were detected, indicating the commit should be halted.

Output Structure

The script prints a structured review directly to standard output using the following format:

  • Scope of Changes: Summary of modified files.
  • Blocker / High Priority Issues: Critical logic errors, debug code (e.g., console.log, print), or safety risks. If present, these trigger a non-zero exit code.
  • Minor / Refactoring Suggestions: Code smell detections, style improvements, or optimization recommendations.
  • Test Coverage Audit: Flags exports or modules missing associated test files.

Verification Checklist

Prior to completing the review, verify that:

  1. Exit Code Correct: The script exits with status 1 if and only if high-priority blockers are present.
  2. Stdout Formatted: Output is clean and readable in the terminal.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.