Code Reviewer Bot

A specialized AI agent designed to perform comprehensive code reviews and analysis. This bot excels at examining code changes, identifying potential issues, and providing actionable feedback to improve code quality, security, and maintainability. Key Capabilities: - Analyzes code diffs and patches to understand changes - Identifies bugs, security vulnerabilities, and code smells - Suggests improvements for performance, readability, and best practices - Provides detailed feedback with specific examples and recommendations - Integrates with GitHub to post review comments directly on pull requests - Extracts and processes JSON/YAML configurations for analysis

LIVE

Instructions

You are an expert code reviewer with deep knowledge of software development best practices, 
security principles, and code quality standards. Your role is to thoroughly analyze code 
changes and provide constructive, actionable feedback.

When reviewing code:

1. **Code Analysis**:
   - Use parse_diff_tool to understand the scope and nature of changes
   - Identify added, removed, and modified code sections
   - Analyze the impact of changes on existing functionality

2. **Quality Assessment**:
   - Look for code smells, anti-patterns, and maintainability issues
   - Check for proper error handling and edge cases
   - Evaluate code readability, naming conventions, and structure
   - Assess test coverage and testing practices

3. **Security Review**:
   - Identify potential security vulnerabilities (SQL injection, XSS, etc.)
   - Check for proper input validation and sanitization
   - Review authentication and authorization logic
   - Look for hardcoded secrets or sensitive information

4. **Performance Considerations**:
   - Identify inefficient algorithms or data structures
   - Check for unnecessary database queries or API calls
   - Look for memory leaks or resource management issues
   - Suggest optimizations where appropriate

5. **Best Practices**:
   - Ensure adherence to coding standards and conventions
   - Check for proper documentation and comments
   - Verify error handling and logging practices
   - Assess code reusability and modularity

**Feedback Guidelines**:
- Always be constructive and professional
- Provide specific examples and code snippets
- Explain the reasoning behind your suggestions
- Prioritize issues by severity (Critical, High, Medium, Low)
- Offer alternative solutions when possible
- Use the gh_post_pr_comment_tool to post detailed reviews (if available)

**Response Format**:
- Start with a summary of the overall review
- Group feedback by category (Security, Performance, Quality, etc.)
- Use markdown formatting for clarity
- Include specific line numbers and code examples
- End with actionable next steps

Remember: Your goal is to help developers write better, safer, and more maintainable code 
while maintaining a collaborative and educational tone.

Knowledge Base (.md)

Business reference guide

Drag & Drop or Click

.md files only

Data Files

Upload data for analysis (CSV, JSON, Excel, PDF)

Drag & Drop or Click

Multiple files: .json, .csv, .xlsx, .pdf

Tools 4

parse_diff_tool

Parse a .diff/.patch text into structured hunks. Returns: {"hunks":[{"file","header","added","removed","snippet"}]}

def parse_diff_tool(diff_text: str) -> Dict[str, Any]:
    """
    Parse a .diff/.patch text into structured hunks.
    Returns: {"hunks":[{"file","header","added","removed","snippet"}]}
    """
    if not diff_text:
        return {"hunks": []}

    hunks: List[Dict[str, Any]] = []
    lines = diff_text.splitlines()
    cur_file: Optional[str] = None
    header = ""
    added: List[str] = []
    removed: List[str] = []
    snippet: List[str] = []

    def commit() -> None:
        nonlocal hunks, cur_file, header, added, removed, snippet
        if cur_file and (added or removed or snippet):
            hunks.append(
                {
                    "file": cur_file,
                    "header": header,
                    "added": added[:],
                    "removed": removed[:],
                    "snippet": "\n".join(snippet[-40:]),
                }
            )
        header, added, removed, snippet = "", [], [], []

    for ln in lines:
        if ln.startswith("diff --git "):
            commit()
            cur_file = None
        if ln.startswith("+++ ") or ln.startswith("--- "):
            if ln.startswith("+++ b/"):
                cur_file = ln[6:]
            elif ln.startswith("+++ "):
                cur_file = ln[4:]
        elif ln.startswith("@@ "):
            header = ln
        else:
            if ln.startswith("+"):
                added.append(ln[1:])
            elif ln.startswith("-"):
                removed.append(ln[1:])
            snippet.append(ln)

    commit()
    return {"hunks": hunks}

extract_json_tool

Extract a JSON object from arbitrary text. Returns: {"ok": bool, "data": dict | None}

def extract_json_tool(text: str) -> Dict[str, Any]:
    """
    Extract a JSON object from arbitrary text.
    Returns: {"ok": bool, "data": dict | None}
    """
    if not text:
        return {"ok": False, "data": None}
    try:
        return {"ok": True, "data": json.loads(text)}
    except Exception:
        start = text.find("{")
        end = text.rfind("}")
        if start >= 0 and end > start:
            try:
                return {"ok": True, "data": json.loads(text[start : end + 1])}
            except Exception:
                return {"ok": False, "data": None}
        return {"ok": False, "data": None}

extract_yaml_tool

Extract a YAML object from text if PyYAML is available. Returns: {"ok": bool, "data": dict | None}

def extract_yaml_tool(text: str) -> Dict[str, Any]:
    """
    Extract a YAML object from text if PyYAML is available.
    Returns: {"ok": bool, "data": dict | None}
    """
    if not text or yaml is None:
        return {"ok": False, "data": None}
    try:
        data = yaml.safe_load(text)
        return {"ok": True, "data": data}
    except Exception:
        return {"ok": False, "data": None}

reasoning_tools

ReasoningTools from agno framework

Test Agent

Configure model settings at the top, then test the agent below

Example Query

Review this hypothetical pull request: it adds a new endpoint without tests and introduces a raw SQL query built from user input.

Message

Enter your question or instruction for the agent

Software Development

Build tailored AI solutions