Skill UI

Validates SKILL.md files against the agentskills specification and Anthropic best practices, catching structure, semantic, naming, and quality issues in a single read-only pass before publishing or debugging skills.

Documented best practices for building applications with Anthropic Claude via Python and TypeScript SDKs, covering messaging, streaming, tools, vision, reasoning, caching, batching, and Agent workflows to optimize prompts, tokens, and cost.

A comprehensive guide to writing reliable and maintainable tests for Kotlin projects. This skill covers modern testing patterns using Kotest for various spec styles (FunSpec, BehaviorSpec), MockK for dependency mocking, and enforces TDD principles (RED/GREEN/REFACTOR). Learn how to implement unit tests, property-based testing, and ensure high code coverage with Kover.

This skill provides methods for reliably extracting typed, validated, and structured data from Large Language Models (LLMs), moving beyond simple text parsing. It covers best practices across major APIs (OpenAI's response_format, Anthropic's tool_use, Google's responseSchema) and local models. Key workflows include defining schemas (Pydantic/Zod), implementing constrained decoding, and building robust retry loops for production-grade data pipelines.

This comprehensive tool validates Claude Code plugins against official Anthropic specifications and internal enterprise standards. It performs two main types of checks: structural validation (checking `plugin.json` fields, file references, and permissions) and content validation (conducting deep grading using `SKILL.md`). Use this when building, auditing, or preparing plugins for marketplace submission to ensure compliance and quality.

This agent provides structured summarization for academic papers, reports, and articles. It goes beyond simple summarizing by extracting key findings, generating comparative matrices across multiple sources, and producing properly formatted citations (APA, IEEE, etc.). It is designed for analysts, product managers, and researchers who need actionable, deep insights from dense documentation.

A deep-dive tool for cybersecurity professionals to analyze malware Command and Control (C2) communication across multiple protocols (HTTP, HTTPS, DNS, custom). It helps reverse-engineer beaconing patterns, decode proprietary protocols, and map threat actor infrastructure, making it crucial for building robust detection signatures and attributing threats.

This skill analyzes DNS query logs to detect sophisticated threats such as data exfiltration via DNS tunneling, Domain Generation Algorithm (DGA) usage, and covert Command and Control (C2) channels. It utilizes advanced techniques like entropy analysis, query volume anomaly detection, and subdomain length analysis within SIEM platforms, helping SOC teams identify threats that bypass traditional network security controls.

A comprehensive toolset for digital forensics investigators, enabling the parsing of proprietary Microsoft Outlook PST and OST files. It extracts critical evidence including full message content, detailed email headers (for message routing/tracing), attachments, and deleted items from the Recoverable Items folder. Essential for e-discovery, legal investigations, and security incident response to reconstruct communication patterns and analyze message metadata.

A dedicated tool for forensic analysis of Windows PowerShell Script Block Logs (Event ID 4104) captured in EVTX files. It reconstructs multi-block scripts, applying advanced detection heuristics such as entropy analysis and pattern matching to identify obfuscated commands, encoded payloads (Base64), download cradles, and AMSI bypass attempts, crucial for threat hunting and incident response.

This skill provides a structured framework for developing comprehensive communication templates for various malware incidents (e.g., ransomware, wipers, worms). It ensures that stakeholders—including C-suite executives, IT teams, customers, and regulators—receive appropriate, severity-based information at the correct time, maintaining transparency and aiding rapid incident response and compliance.

This framework defines a comprehensive, context-driven matrix for managing security incidents within a Security Operations Center (SOC). It details tiered escalation paths, response Service Level Agreements (SLAs), and notification procedures based not only on severity (P1-P4) but also on business risk, asset criticality, and data sensitivity. It guides analysts through triage, investigation, and timely escalation to management (CISO/Legal) to ensure rapid containment and appropriate organizational response during a breach.