codex-review
Uses an external model to review code written by the primary agent for unbiased quality checks.
Install
mkdir -p .claude/skills/codex-review-hyperb1iss && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19455" && unzip -o skill.zip -d .claude/skills/codex-review-hyperb1iss && rm skill.zipInstalls to .claude/skills/codex-review-hyperb1iss
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 this skill for code reviews using the Codex CLI from a Claude-hosted session. Activates on mentions of codex review, code review with codex, codex check, gpt review, codex exec review, run codex, review my code, review this PR, review changes, peer review, or second opinion.Key capabilities
- →Perform cross-model code reviews
- →Execute Codex CLI commands for validation
- →Review specific branches, commits, or working trees
- →Capture review output to files
How it works
The skill uses the Codex CLI to perform an independent code review, use a different architectural model to avoid self-review bias.
Inputs & outputs
When to use codex-review
- →Perform cross-model peer review
- →Check PRs for overlooked bugs
- →Get a second opinion on code logic
- →Verify code quality using external CLI
About codex-review
Facilitates independent code reviews by utilizing the Codex CLI as a secondary validator. By using a different architectural model for the review, it catches bugs that the primary model might overlook due to self-review bias.
Use this skill for code reviews using the Codex CLI from a Claude-hosted session. Activates on mentions of codex review, code review with codex, codex check, gpt review, codex exec review, run codex, review my code, review this PR, review changes, peer review, or second opinion.
When not to use it
- →Formatting or linting tasks
- →Evaluating product direction or UX
- →Self-reviewing Claude's own code
Prerequisites
Limitations
- →Not a replacement for human review
- →5–15% false positive rate
- →Output exceeding 100KB requires splitting
How it compares
It utilizes a separate model architecture for validation rather than relying on the primary model's self-assessment.
Compared to similar skills
codex-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| codex-review (this skill) | 0 | 1mo | Review | Advanced |
| effective-go | 323 | 10mo | No flags | Beginner |
| architect-review | 109 | 4mo | No flags | Advanced |
| resolve-conflicts | 81 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
effective-go
openshift
Apply Go best practices, idioms, and conventions from golang.org/doc/effective_go. Use when writing, reviewing, or refactoring Go code to ensure idiomatic, clean, and efficient implementations.
architect-review
sickn33
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
solid-principles
SmidigStorm
Enforce SOLID principles (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion) in object-oriented design. Use when writing or reviewing classes and modules.
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
codex
Lucklyric
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.