Search Skills

Parses SARIF files to analyze security scan results, aggregate findings, deduplicate alerts, and integrate into security workflows.

Performs static code analysis with Semgrep to detect security vulnerabilities, enforce code patterns via custom rules, and integrate into CI/CD pipelines.

Enables continuous fuzzing for open source projects to identify security vulnerabilities via automated input testing.

Detects timing side channels in cryptographic code to identify vulnerabilities during security audits.

Scans Substrate and Polkadot pallets for critical security vulnerabilities including arithmetic overflow and bad origin checks, aiding runtime audits.

Verifies that git commits address security audit findings without introducing bugs, ensuring remediation aligns with security reports.

Assesses codebase maturity against Trail of Bits' security framework, delivering evidence-based ratings and actionable security recommendations.

Generates Claude Code skills for security testing tools and techniques using the Trail of Bits Testing Handbook.

Performs CodeQL static analysis for security vulnerability detection, taint tracking, and data flow analysis in code audits and CI/CD pipelines.

Enables line-by-line code analysis to establish architectural context for security audits and vulnerability detection.

Analyzes cryptographic code for timing side-channel vulnerabilities across multiple programming languages.

Guides PyTorch-native reinforcement learning training with Meta's torchforge library for clean abstractions and scalable experiments using Monarch and TorchTitan.

Guides LLM post-training with reinforcement learning (RLHF, PPO) using verl (Volcano Engine RL) for scalable infrastructure-backed implementation.

Generates publication-ready ML/AI research papers for top conferences with LaTeX templates and citation verification.

Guides LLM post-training with RL using slime framework (Megatron+SGLang) for GLM models and custom data workflows.

Guides enterprise RL training with miles (slime fork) for large MoE models using FP8/INT4 quantization and speculative RL for high throughput.

Enables scalable distributed LLM pretraining with torchtitan using 4D parallelism for models like Llama 3.1 and DeepSeek V3.

Builds headless authentication systems in Laravel using Fortify, including login, registration, 2FA, and profile management.

Provides on-demand access to specific sections of official Claude Code documentation for accurate implementation of hooks, skills, and MCP servers.

Compares z.ai GLM 4.7 and code-searcher responses to provide dual-AI perspectives on code analysis and questions.

Reviews recent conversations to identify improvements for CLAUDE.md documentation files.

Reads an asset file and executes a script to reveal a hidden secret code.

Retrieves comprehensive system details including OS, kernel, CPU, and memory for infrastructure diagnostics and monitoring.

Gathers detailed network configuration and connectivity data including interface details, routing tables, and DNS settings for infrastructure diagnostics.