Skill UI

Guidance lets you wrap LLM calls with grammars, regex, and selection constraints to ensure valid JSON/XML/code, enforce formats, heal tokens, and orchestrate multi-step workflows via Pythonic context managers for production-ready automation.

Enables Claude to monitor and analyze application CPU usage, detect hotspots, inefficient loops and regexes, and offer optimization strategies such as asynchronous processing or algorithmic improvements to boost performance.

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

A command-line utility designed to search, extract, and analyze data from Burp Suite project files (.burp). It allows users to search request/response headers and bodies using complex regex patterns, extract security audit findings, or gather proxy/site map data. Essential for deep analysis of captured HTTP traffic in web security testing, while providing safeguards against large data overflows.

A comprehensive guide to building robust, maintainable, and idiomatic Perl applications using modern features (Perl 5.36+). This resource covers best practices for object-oriented programming (Moo/Moose), advanced error handling (Try::Tiny), context sensitivity, complex regex usage, and efficient module design.

This tool provides a comprehensive framework for analyzing web server logs (Apache/Nginx) to detect various security threats. It uses advanced regex matching against OWASP attack signatures to identify SQL injection, Local File Inclusion, and Directory Traversal attempts, alongside behavioral analysis for brute-force attacks and web scanner fingerprints. The system also enriches data using GeoIP for source attribution, generating a prioritized report for SOC analysts.

A comprehensive tool and guide for detecting and exploiting NoSQL injection vulnerabilities in MongoDB, CouchDB, and similar databases. It simulates advanced attacks such as authentication bypass, blind data extraction using regex, and JavaScript execution via the $where operator. Ideal for penetration testers and security researchers assessing APIs and web applications backed by NoSQL backends.

Scans web server roots for high-entropy files, suspicious PHP/JSP/ASP payloads, and recent modifications to flag obfuscated webshells via entropy thresholds, regex signatures, and file metadata.

This guide details implementing comprehensive API security using Google Apigee. It covers multiple advanced policies, including JSON/XML content validation, regex injection detection (SQLi, XSS), rate limiting (SpikeArrest), and robust OAuth 2.0 enforcement. Use this when shielding critical APIs from OWASP API Top 10 threats and malicious client abuse patterns.

This skill guides the implementation of Gitleaks for robust secret scanning across development lifecycles. It covers setting up pre-commit hooks to prevent secrets from being committed, integrating scanning into CI/CD pipelines (like GitHub Actions), and writing custom regex rules to detect and remediate hardcoded credentials (API keys, passwords, tokens) in Git history, ensuring adherence to secure SDLC practices.

This skill automates the monitoring of public paste sites (e.g., Pastebin, GitHub Gists) to detect leaked credentials, API keys, and sensitive data dumps. It employs advanced regex patterns and keyword matching to provide early warning of security breaches, crucial for incident response, vulnerability assessment, and threat intelligence gathering.