Skill UI

This skill guides developers on building LLM-powered applications using the Claude API, Anthropic SDKs, or the Agent SDK. It provides comprehensive guidance on language detection, best practices (like default model versions and streaming), and choosing the correct development surface (API call, Workflow, or Agent) based on the use case.

Captures coding session learnings by extracting corrections, successes, and anti-patterns with confidence scoring so teams can track, reinforce, and reuse technical knowledge across projects.

This guide provides comprehensive patterns for designing and implementing secure multi-tenant SaaS applications using shared databases. It covers critical techniques like Row-Level Security (RLS) in PostgreSQL, implementing tenant-aware middleware in TypeScript (Express/Fastify), and enforcing data scoping at the ORM level (Prisma/Drizzle). Learn how to prevent data leakage and manage tenant isolation across shared schemas.

A comprehensive tool designed to systematically plan ablation studies for machine learning research papers. It guides the process by having an AI (Codex) simulate a rigorous reviewer, identifying necessary experiments to isolate component contributions and answer critical research questions. It also includes a feasibility review step to manage compute resources and implementation complexity.

This tool parses Software Bill of Materials (SBOM) in CycloneDX and SPDX formats. It correlates components against the NVD CVE database to identify known supply chain vulnerabilities. Key features include building dependency graphs, calculating transitive risk scores, and generating compliance reports for regulatory assessment.

This tool serves as a persistent memory and state manager for complex coding projects within the Claude environment. It allows users to initialize new projects with structured metadata, track detailed session progress (including summaries, decisions, and next steps), and save the entire context reliably. By ensuring project continuity across disconnected sessions, it drastically improves the flow and consistency of the development workflow.

This technique audits user interaction flows (like button clicks) to detect subtle bugs that static analysis often misses. It specifically tracks the full sequence of state changes, identifying instances where later actions unintentionally cancel, contradict, or leave the UI in an inconsistent state due to state store side effects or race conditions. Ideal for debugging complex state management architectures (Redux, Zustand).

A specialized skill designed for comprehensive literature reviews in the communications and networking domain. It supports topics including 5G/6G, Wi-Fi, satellite communications, routing, and cross-layer optimization. The skill employs a knowledge-base-first retrieval strategy, prioritizing local sources (Zotero, Obsidian) before searching major academic databases (IEEE, ACM) to ensure depth and relevance.

A comprehensive knowledge-base-first skill designed for deep literature reviews in advanced communication domains. Use it for topics like 4G/5G/6G, wireless networking, satellite communications, Wi-Fi, routing protocols, and cross-layer optimization. It systematically searches structured academic databases (IEEE, ACM, Zotero, etc.) to provide related work, survey papers, and landscape summaries.

This skill outlines the architecture and methodology for deploying canary files (honeytokens) across critical file systems. By placing decoy documents with known content in high-value locations, this system monitors for unauthorized modifications, deletions, or encryption attempts. It detects ransomware by triggering high-fidelity alerts via File Integrity Monitoring (FIM) systems, serving as a crucial deception layer that complements existing EDR/AV solutions.

This guide outlines the architecture and implementation steps for building a robust, production-ready design system. It covers core elements like design tokens, reusable components, and layout patterns. Ideal for teams needing to maintain design consistency, ensure accessibility, and synchronize design (Figma) with implementation (Storybook).

This skill detects AI-generated deepfake audio used in voice phishing (vishing) attacks. It functions by extracting critical spectral features (including MFCCs, spectral centroid, and zero-crossing rate) and passing them through advanced machine learning models (like Random Forest and Gradient Boosting). The system supports batch forensic analysis, provides confidence scores, and generates detailed reports to verify the authenticity of recorded voice calls, making it essential for cybersecurity incident response and fraud investigation.