WHEN: Deep AI-powered code analysis, multi-model code review, security scanning with Codex and Gemini WHAT: Comprehensive code review using external AI models with severity-based findings, deduplication, and secret detection WHEN NOT: Simple lint checks -> code-reviewer, Quick security only -> security-scanner, Style formatting -> code-quality-checker
/plugin marketplace add physics91/claude-vibe/plugin install claude-vibe@physics91-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Leverages external AI models (OpenAI Codex CLI and Google Gemini CLI) for deep code analysis beyond Claude's built-in capabilities. Provides multi-perspective code reviews with result aggregation and consensus scoring.
At least one of the following must be installed and authenticated:
codex auth to authenticategemini auth login to authenticateUses OpenAI Codex for comprehensive code analysis.
Uses Google Gemini for code analysis.
Aggregates results from both Codex and Gemini with deduplication.
Detects hardcoded secrets, API keys, credentials, and sensitive data.
Retrieves status of async analysis operations.
Ask user for analysis preference:
Question: "What type of AI analysis do you need?"
Options:
Question: "Which AI model should be used?"
Options:
Question: "What's the project context?"
Options:
Call the appropriate MCP tool based on selections.
Format findings in structured markdown with:
## AI Code Review Results
**Analysis ID**: [id]
**Models Used**: [codex/gemini/combined]
**Cache Status**: [hit/miss]
**Duration**: [Xms]
### Overall Assessment
[AI-generated overall assessment of code quality]
### Summary
| Severity | Count |
|----------|-------|
| Critical | X |
| High | X |
| Medium | X |
| Low | X |
| **Total** | **X** |
### Findings
#### Critical Issues
1. **[Title]** (Line X)
- **Description**: [...]
- **Suggestion**: [...]
- **Code**: `[snippet]`
#### High Priority
[...]
### Recommendations
1. [Prioritized action item 1]
2. [Prioritized action item 2]
3. [...]
---
*Analysis by [model(s)] | Confidence: [X]% | Duration: [X]ms*
code-reviewer for comprehensive analysissecurity-scanner with external AI perspective/cr express commandThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.