nonoroazoro/code-review
plugins/skills/code-review/skills/code-review/SKILL.md
Code review
$ install --global
skillsauthnpx skillsauth add nonoroazoro/ai code-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 28, 2026, 11:36 AM208.2s1 file scanned
SKILL.md
- name:
- code-review
- description:
- Code review
- allowed-tools:
- Bash(git diff:*), Bash(git log:*), Bash(git blame:*), Bash(git rev-parse:*), Bash(git branch:*), Bash(git show:*), Bash(git status:*)
Code review for local code changes with confidence scoring and false positive filtering.
Workflow
-
Auto-detect diff scope from
git status. Ask the user if ambiguous. -
Gather context (3 parallel Haiku agents): CLAUDE.md file paths, change summary, modified file list.
-
Deep review (5 parallel Sonnet agents). Each returns
{file, line, description, evidence, category}:- CLAUDE.md compliance: only flag what CLAUDE.md explicitly requires.
- Bugs: focus on the diff. Ignore linter/typechecker-catchable issues.
- Security: only flag issues introduced by this change.
- Git history: flag repeated past mistakes or convention violations.
- Performance: only flag measurable impact.
-
Score each finding (parallel Haiku agents, one per finding) with diff context and CLAUDE.md paths. For CLAUDE.md-flagged issues, verify CLAUDE.md actually calls it out. Rubric (provide verbatim):
- 0: False positive, pre-existing, or does not hold up to scrutiny.
- 25: Unverifiable. Stylistic issue not explicitly in CLAUDE.md.
- 50: Real but minor. Unlikely in practice.
- 75: Verified. Will impact functionality, or directly violates CLAUDE.md.
- 100: Confirmed critical. Happens frequently. Evidence proves it.
-
Filter and classify findings scored >= 75. Report clean if none remain.
- P0 (Blocker): score 100 with security or data loss risk.
- P1 (Must fix): score >= 85, correctness or CLAUDE.md violation.
- P2 (Should fix): score >= 75, performance or maintainability.
-
Print results.
False Positives
Provide to scoring agents:
- Pre-existing issues or issues on unmodified lines
- Linter/typechecker/compiler-catchable issues
- General quality concerns unless CLAUDE.md requires them
- CLAUDE.md violations silenced by inline ignore comments
- Intentional functionality changes related to the broader change
Output Format
### Code Review
Found {n} issues:
1. [P0] {description} ({source: CLAUDE.md quote or code evidence})
{file}:{line}
2. [P1] {description} ({source})
{file}:{line}
If no issues survive filtering:
### Code Review
No issues found. Checked for bugs, security, performance, and CLAUDE.md compliance.
Related Skills
nonoroazoro/improve-prompt
testing
VerifiedTrustedCommunity
Optimize prompts for AI agents and skills. Use when refining SKILL.md files, agent definitions, or any AI instruction set. Focuses on token efficiency, clarity, and actionability.
5SKILL.mdUpdated Apr 28, 2026
nonoroazoro/implement-components
development
VerifiedTrustedCommunity
Implement all nodes from component spec with Figma design context, fix code based on audit results
5SKILL.mdUpdated Apr 28, 2026
nonoroazoro/figma-to-code
development
VerifiedTrustedCommunity
Convert Figma designs to frontend code by orchestrating an Agent Team
5SKILL.mdUpdated Apr 28, 2026
nonoroazoro/design-components
development
VerifiedTrustedCommunity
Architecture and component design expert, design the component spec based on Figma design data and frontend best practices.
5SKILL.mdUpdated Apr 28, 2026