code-review
Guides reviews toward identifying bugs, data loss risks, and security issues.
Install
mkdir -p .claude/skills/code-review-ivegamsft && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15289" && unzip -o skill.zip -d .claude/skills/code-review-ivegamsft && rm skill.zipInstalls to .claude/skills/code-review-ivegamsft
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when reviewing code, pull requests, or diffs. Covers best practices for risk-focused review, severity ordering, and identifying missing tests or regressions.Key capabilities
- →Prioritize code review findings by severity
- →Identify bugs and behavioral regressions
- →Detect data loss, security, and correctness risks
- →Pinpoint missing validation or broken edge cases
- →Check for missing or weak tests for changed behavior
How it works
The skill reviews code by prioritizing findings based on severity, focusing on critical issues like bugs, security risks, and missing validation. It provides file references for each finding.
Inputs & outputs
When to use code-review
- →Review pull request
- →Audit code diffs
- →Identify security risks
- →Check for missing tests
About this skill
Code Review
Use this skill when the task is to review code rather than write it.
Review Priorities
- Bugs and behavioral regressions
- Data loss, security, and correctness risks
- Missing validation or broken edge cases
- Missing or weak tests for changed behavior
- Secondary maintainability concerns
Output Shape
- Findings first, ordered by severity
- File references for each finding
- Open questions or assumptions
- Short summary only after findings
Non-Goals
- Do not rewrite the code just because there is a different style preference.
- Do not bury real risks under a long summary.
Related Guardrails
- Code Review Escalation — When and how to escalate findings to blocking issues vs inline comments
When not to use it
- →When the task is to write code rather than review it
- →When the goal is to rewrite code based on style preferences
- →When the user wants a long summary that buries risks
Limitations
- →Does not rewrite code based on style preference
- →Does not bury real risks under long summaries
- →Focuses on risk-based severity ordering
How it compares
This skill provides a structured, risk-focused approach to code review, prioritizing critical issues over stylistic preferences and presenting findings clearly, unlike an unstructured or style-focused review.
Compared to similar skills
code-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-review (this skill) | 0 | 3mo | No flags | Intermediate |
| reviewing-code | 21 | 8mo | No flags | Intermediate |
| pr-review | 6 | 2mo | Review | Intermediate |
| code-review-checklist | 3 | 29d | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by ivegamsft
View all by ivegamsft →You might also like
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
fix-review
sickn33
Verify fix commits address audit findings without new bugs
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
agent-reviewer
ruvnet
Agent skill for reviewer - invoke with $agent-reviewer