Skill UI

Analyzes PLC firmware to uncover vulnerabilities such as hardcoded credentials, insecure updates, backdoors, memory corruption, and undocumented debug interfaces. Covers extraction from Siemens, Allen-Bradley, and Schneider platforms, static and dynamic inspection, and baseline comparison to detect tampering.

This guide details a comprehensive methodology for penetration testing desktop (thick client) applications. It covers static and dynamic analysis, focusing on identifying vulnerabilities such as hardcoded credentials, insecure local storage, DLL hijacking, memory manipulation, and API communication flaws. Tools like dnSpy, Procmon, and Burp Suite are utilized for in-depth security auditing of enterprise and banking software.

Decode ransomware encryption routines via static and dynamic analysis to identify used ciphers, key-gen weaknesses, and whether decryption without ransom is viable during controlled malware testing.

An advanced debugging skill designed for AI agents. It utilizes gdb-cli to provide intelligent assistance for C/C++ programs, enabling the analysis of core dumps, debugging live processes, and investigating complex issues like crashes, deadlocks, and memory corruption. It correlates runtime state inspection with source code context for deeper insights.

This skill provides a systematic pipeline for safely executing large-scale code refactors across multiple files or subsystems. It first performs parallel, dependency-aware analysis to map the entire scope, synthesizing a single, actionable plan. The process then breaks the work into independent 'work packets,' which are executed sequentially or in parallel by specialized worker agents, ensuring strict dependency management and behavior parity throughout the entire process.

This skill provides a comprehensive, structured workflow for diagnosing performance bottlenecks in SwiftUI applications. It guides users through a code-first review to detect common issues like invalidation storms, layout thrash, or heavy main-thread work. When code review is insufficient, it provides detailed guidance on collecting runtime evidence using Instruments, enabling precise root cause analysis and targeted remediation strategies.

This skill provides comprehensive interaction with the DeerFlow AI agent platform via its robust HTTP API. It is designed for managing complex, multi-step AI workflows, including deep academic research, code execution, web browsing, and file analysis. Users can initiate and continue conversation threads, manage agent memory, upload documents (PDF, etc.), and delegate complex research tasks to the autonomous agent system.

This comprehensive guide provides detailed procedural steps for configuring and executing CodeQL code scanning. It covers both implementing automated workflows using GitHub Actions (`codeql.yml`) and running scans via the CodeQL CLI. Users will learn how to manage language matrices, set build modes, interpret SARIF outputs, handle monorepo structures, and troubleshoot complex security analysis setups across multiple languages (e.g., Python, Java, C++).

A structured methodology for coordinating multiple, simultaneous investigation threads to determine the root cause of complex system failures, performance regressions, or integration bugs. This skill decomposes a large problem into independent tracks (e.g., database, application code, infrastructure), assigns ownership, and manages structured sync points (Continue/Pivot/Converge) to converge on a solution faster than serial debugging. Essential for high-stakes production incident response.

Phoenix Evals lets teams build evaluators for AI/LLM apps by wiring deterministic code with LLM nuance, running Python or TypeScript workloads, validating against humans, and iterating through error analysis, RAG, and production workflows.

A universal assistant for conducting deep code reviews across major SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). It rigorously analyzes SQL code for critical vulnerabilities (like SQL injection), performance bottlenecks, maintainability issues, and adherence to industry best practices. Features include security audits, index optimization recommendations, query structure analysis, and schema design validation, ensuring robust and secure database development.

Conducts STRIDE-A threat modeling on repositories or systems, running either a full single-pass analysis with architectures, DFDs, prioritized findings, and executive assessments, or an incremental update that compares a baseline report to the current code and highlights deltas.