Specialized code review tool for the vm0 project to detect smells and remove defensive code patterns.
Install
mkdir -p .claude/skills/code-quality && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1716" && unzip -o skill.zip -d .claude/skills/code-quality && rm skill.zipInstalls to .claude/skills/code-quality
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.
Deep code review and quality analysis for vm0 projectKey capabilities
- →Review pull requests by ID
- →Analyze commit ranges or single hashes
- →Generate automated review reports in markdown
- →Cleanup defensive try-catch code patterns
- →Cross-reference changes against bad-smell documentation
How it works
Parses the input scope, populates a structured folder, and iterates through commits comparing code changes against a predefined bad-smell markdown file.
Inputs & outputs
When to use code-quality
- →Review pending pull requests for vm0
- →Analyze quality of recent commits
- →Clean up unnecessary defensive code
- →Generate code review reports for project history
About this skill
Code Quality
Operations
review <pr-id|commit-range|description>: review the identified change. For a PR, follow REVIEW.md; it owns practice routing, evidence, verdicts, and posting. For a commit range, apply the same relevant practices and report findings to the caller without inventing a PR destination.cleanup [scope]: implement removal of redundant error handling in the requested scope. The existingdefensive-code-cleanupcommand routes here.
Read code quality and select additional guidance from the documentation index. Searches identify candidates; inspect actual behavior before reporting a violation.
Error-Handling Cleanup
Search the requested source for catches that only log and rethrow, fabricate a generic success/empty result, or duplicate a framework-owned error response. For an unbounded cleanup request, select up to ten related, justified removals.
Before removing each catch, trace its caller and owning error boundary. Establish what the caller observes after removal and why the existing handler is redundant. Do not remove:
- meaningful rollback, resource cleanup, retry, or recovery;
- domain-error conversion to a contractual HTTP response;
- explicitly owned best-effort operations or per-item failure isolation;
- authentication, permission, or other fail-closed security handling;
- required cross-version behavior or expected external-reference misses.
Apply fallback rules, deployment compatibility, and reference authority when those boundaries are involved. A catch containing only a log is not automatically redundant: verify whether it owns necessary diagnostics or rejection handling.
Remove unused imports and adjust callers only when the preserved contract
requires it. Keep async work attached to its owning cancellation signal;
detach() is not a replacement for error handling inside signals.
Completion
Show each finding or removal with its file, behavior, and evidence. Do not assign severity from a regex match or file length alone. Run checks for the changed scope and relevant consumers under project verification. Report remaining uncertainty explicitly. Create a PR when the caller requested one; a research or review request alone does not authorize implementation.
When not to use it
- →Projects unrelated to the vm0 codebase
- →When only simple linting is required
Limitations
- →Depends on local docs/bad-smell.md file
- →Strict directory structure requirement
- →Requires git history access
How it compares
It enforces project-specific architectural standards and documentation-based quality checks rather than general-purpose style rules.
Compared to similar skills
code-quality side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-quality (this skill) | 4 | 3mo | Review | Intermediate |
| effective-go | 323 | 11mo | No flags | Beginner |
| solid-principles | 57 | 11mo | No flags | Intermediate |
| typescript-review | 39 | 3mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by vm0-ai
View all by vm0-ai →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.
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.
typescript-review
metabase
Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing TypeScript/JavaScript code.
ast-grep
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
serena
massgen
This skill provides symbol-level code understanding and navigation using Language Server Protocol (LSP). Enables IDE-like capabilities for finding symbols, tracking references, and making precise code edits at the symbol level.
typescript
lobehub
TypeScript code style and optimization guidelines. Use when writing TypeScript code (.ts, .tsx, .mts files), reviewing code quality, or implementing type-safe patterns. Triggers on TypeScript development, type safety questions, or code style discussions.