Search Skills

Provides comprehensive reference for top 100 web vulnerabilities including definitions, root causes, impacts, and OWASP-aligned mitigation strategies.

Tests for HTML injection vulnerabilities using proven attack techniques and methodologies to identify content injection risks.

Provides guidance for configuring and testing network services including web servers, HTTP/HTTPS, SNMP, and SMB for penetration testing environments.

Performs SMTP server security assessments including user enumeration, open relay testing, banner grabbing, and credential brute-forcing.

Provides step-by-step guidance for intercepting, modifying, and testing web application requests using Burp Suite's core security features.

Enables red team methodology, bug bounty hunting, and vulnerability enumeration with expert security tool configurations.

Provides techniques for identifying and exploiting privilege escalation vectors on Linux systems, including SUID binaries and sudo misconfigurations.

Performs API security assessments including fuzzing, IDOR detection, and penetration testing for bug bounty programs.

Provides structured ethical hacking methodology including penetration testing lifecycle, reconnaissance, vulnerability scanning, exploitation, and report writing.

Provides essential command references for penetration testing tools including Nmap, Metasploit, Hydra, and Nikto.

Automates creation of isolated Git worktrees in parent directories for plan file implementation, following project conventions.

Enables tracing, debugging, and optimization of LLM applications using TruLens and OpenTelemetry.

Systematically evaluates LLM application performance and reliability with TruLens for AI model assessment.

Curates evaluation datasets with ground truth for TruLens, enabling robust AI model assessment and benchmarking.

Configures feedback functions and selectors for evaluating LLM applications using the TruLens framework.

Executes TruLens evaluations for AI models and displays results, enabling quality assessment of LLM outputs.

Executes and displays Jupyter notebooks for TruLens AI model evaluation demos and quickstarts.

Quickly reviews small code changes (<100 lines) for basic quality, naming conventions, and obvious bugs.

Performs standard code reviews for medium-sized pull requests (100-500 lines), analyzing code quality, security basics, and test coverage.

Conducts comprehensive code reviews for large pull requests, analyzing architecture, performance, security, and maintainability.

Analyzes pull request diffs to generate automated code review comments on quality, security, and performance.

Replaces built-in search tools with a unified interface, requiring `mgrep` for Grep and `mgrep --web` for WebSearch to streamline developer workflows.

Creates Git commit messages with contextual reasoning explanations to improve repository history clarity and maintainability.

Searches arXiv for academic papers on agentic AI patterns, enabling discovery and review of the latest research in this domain.