review

Review code for bugs, style issues, and correctness. Use when the user asks for a code review, review, or CR.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "review" with this command: npx skills add michaelrizvi/claude-config/michaelrizvi-claude-config-review

Code Review

Review the provided code (file, diff, or selection) systematically.

Review Checklist

  1. Correctness — Logic errors, off-by-ones, edge cases, wrong assumptions
  2. Bugs — Null/None handling, uninitialized variables, race conditions
  3. Types & shapes — Tensor dtype/device mismatches, shape errors, implicit casts
  4. Security — Injection, hardcoded secrets, unsafe deserialization
  5. Style — Naming, dead code, unnecessary complexity, consistency with surrounding code
  6. Performance — Unnecessary copies, repeated computation, memory leaks

Output Format

For each issue found:

  • File and line: where the issue is
  • Severity: critical / warning / nit
  • What: one-line description
  • Why: brief explanation
  • Fix: suggested change (code snippet if helpful)

If no issues are found, say so — don't invent problems.

Scope

$ARGUMENTS

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

pytorch-debug

No summary provided by upstream source.

Repository SourceNeeds Review
General

bash

No summary provided by upstream source.

Repository SourceNeeds Review
General

experiment

No summary provided by upstream source.

Repository SourceNeeds Review
Research

paper

No summary provided by upstream source.

Repository SourceNeeds Review