agentsclimarketplace

Generated code review

Skill lubochka/xiigen-general-skills/codex/skills/generated-code-review

Open-source AI agent skills for safer Claude, Codex and Cursor coding workflows

Install
npx -y skills add lubochka/xiigen-general-skills --skill generated-code-review

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

  • 1 stars1 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

Review generated code before trusting it. Use after AI-generated code, scaffolding, migration output, or copied snippets.

SKILL.md

0.9 KB, as published. Nobody here has run it

Generated Code Review

Purpose

Review generated code before trusting it.

When to Use

Use after AI-generated code, scaffolding, migration output, or copied snippets.

Inputs

Generated files, expected behavior, APIs, tests, security constraints.

Steps

  1. Inspect logic and API compatibility.
  2. Check error handling and security-sensitive paths.
  3. Run relevant verification.
  4. Remove unused or hallucinated code.

Gates

Generated output is reviewed as code, not accepted as source of truth.

Evidence

Review findings, tests, build checks, or manual inspection notes.

Anti-Patterns

Assuming generated code is correct because it is syntactically plausible.

Related

review-fix-loop, code-examination

Gives 0 of the 12 instructions most code review skills give

Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06

  • push back with technical reasoning if wrongin 60 of 610, across 24 files
  • ask for clarification on unclear itemsin 51 of 610, across 16 files
  • fix critical issues immediatelyin 45 of 610, across 29 files
  • implement one item at a timein 45 of 610, across 11 files
  • group findings by severityin 44 of 610, across 43 files
  • verify feedback against the codebasein 42 of 610, across 8 files
  • dispatch a code reviewer subagentin 39 of 610, across 23 files
  • fix important issues before proceedingin 37 of 610, across 22 files
  • test each fix individuallyin 35 of 610, across 7 files
  • reply in github comment threadsin 33 of 610, across 5 files
  • check for security vulnerabilitiesin 31 of 610, across 27 files
  • factualize corrections without over-explainingin 30 of 610, across 2 files

Said here and by no other author read

  • inspect logic and API compatibility
  • run relevant verification
  • remove unused or hallucinated code
  • treat generated output as untrusted code

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

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.