Perform comprehensive code reviews by orchestrating sub-agents to analyze code from multiple perspectives.
Install
mkdir -p .claude/skills/deep-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4246" && unzip -o skill.zip -d .claude/skills/deep-review && rm skill.zipInstalls to .claude/skills/deep-review
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.
Sub-agent powered code reviews spanning correctness, tests, consistency, and fitKey capabilities
- →Spawn 2-5 specialized sub-agents for parallel analysis
- →Evaluate code correctness, test coverage, and architectural consistency
- →Assess UX, accessibility, and performance impacts
- →Categorize findings by severity levels P0 through P4
- →Generate a validation plan with specific commands
How it works
The skill identifies the scope of changes and spawns multiple sub-agents to analyze the code from different perspectives before synthesizing their findings into a single report.
Inputs & outputs
When to use deep-review
- →Review code logic
- →Check test coverage
- →Audit architectural consistency
About deep-review
Utilizes a set of specialized sub-agents to perform parallel reviews of code changes. Covers logic correctness, test coverage, architectural consistency, and UX/a11y improvements.
Sub-agent powered code reviews spanning correctness, tests, consistency, and fit
When not to use it
- →For trivial, single-line changes where parallel analysis is unnecessary
- →When the user requires a single-threaded review
Limitations
- →Requires clear file scope to effectively spawn sub-agents
- →Feedback must be actionable with file paths to be valid
How it compares
It replaces single-threaded manual reviews with a parallelized, multi-perspective analysis that ensures coverage of logic, tests, and architecture.
Compared to similar skills
deep-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| deep-review (this skill) | 1 | 8mo | No flags | Advanced |
| effective-go | 323 | 11mo | No flags | Beginner |
| architect-review | 109 | 5mo | No flags | Advanced |
| resolve-conflicts | 81 | 10mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by coder
View all by coder →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.