Agent skill
quality
Run a comprehensive code quality review. Checks security, performance, maintainability, project conventions (CLAUDE.md), architecture, and testing. Runs rustfmt and bazel test. Use when user asks for 'review', 'check', 'validate', 'quality', 'lint', or before committing. (project)
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/unknown-vantle-vantle
SKILL.md
Code Quality Review
Activation
- EVALUATE: Does this request involve code review, quality checks, validation, or pre-commit checks?
- DECIDE: "This task requires /quality because..."
- EXECUTE: Follow the workflow below
Expert code reviewer. Comprehensive multi-pass review covering conventions, security, performance, and architecture.
Process
1. Prepare
Identify target files (user-specified or git status), then run automated checks:
bazel run //:format.rust -- --check $(find . -name "*.rs" -not -path "*/bazel-*")
bazel test //...
Report any failures before proceeding.
2. Conventions
Verify against CLAUDE.md CRITICAL sections:
- Naming: single words, no underscores, no abbreviations
- Module Organization: no mod, pub use only, one-level depth
- Code Quality: miette errors, turbofish, no comments
Flag violations from NEVER sections immediately.
3. Security
Check for (see security.md for patterns):
- Secrets: hardcoded passwords, tokens, API keys
- Injection: user input in
Command::new(),format!()paths, SQL strings - Boundaries: external input validated before use
- Errors: no sensitive info (paths, connection strings) in error messages
4. Performance
Check for (see performance.md for patterns):
- Allocations: unnecessary
.clone(),.to_string() - Iteration:
.collect()when streaming works, multiple passes - Complexity: O(n^2) where O(n log n) possible
- Async: blocking in async context, sequential when parallel possible
5. Architecture
- Single responsibility per function/module
- No circular dependencies
- Consistent with existing patterns
- No over-abstraction
Output Format
## Quality Review Summary
| Category | Status | Issues |
|----------|--------|--------|
| Formatting | PASS/WARN/FAIL | N |
| Tests | PASS/WARN/FAIL | N |
| Conventions | PASS/WARN/FAIL | N |
| Security | PASS/WARN/FAIL | N |
| Performance | PASS/WARN/FAIL | N |
| Architecture | PASS/WARN/FAIL | N |
**Overall**: PASS/WARN/FAIL
## Findings
### [Category]
**[file:line]** - Issue description
**Fix**: Suggested fix
Non-Negotiable Violations
Flag these immediately (from CLAUDE.md NEVER sections):
- Underscores in identifiers
- Comments in code
moddirective usage- Deep or glob re-exports
- Type annotations instead of turbofish
- Missing miette diagnostics
- Hardcoded secrets
- Unsanitized input at boundaries
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?