Skill UI

This advanced GEO-first tool performs comprehensive audits designed for the modern AI search landscape (ChatGPT, Gemini, Google AI Overviews). It moves beyond traditional SEO, assessing citability scoring, E-E-A-T, technical foundations, structured data validation, and brand authority signals. It provides actionable, client-ready reports to ensure maximum visibility in AI-driven search traffic.

Audit, validate, and enhance GEO structured data by detecting existing JSON-LD/microdata/RDFa, checking schema.org compliance, and generating ready-to-use JSON-LD to boost AI discoverability.

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.

Analyzes structured and unstructured threat intelligence feeds to extract indicators, normalize data into STIX 2.1, enrich IOCs, deduplicate, and distribute via TAXII to SIEM/EDR systems—ideal for assessing CTI feed quality or automating feed ingestion pipelines.

Build collaborative incident timelines with Timesketch by ingesting Plaso, CSV, or JSONL data to normalize multi-source events, leverage analyzers, search, and story tools, and guide structured attack reconstruction during investigations.

Provides structured methodologies for authorized AWS, Azure, and GCP penetration tests, covering scoping, reconnaissance, IAM privilege escalation, SSRF-to-metadata validation, and MITRE ATT&CK Cloud reporting.

Detect data staging activity before exfiltration by monitoring archive tool execution, staging directories, large file consolidation, sensitive path access, and producing structured hunt reports that map events to MITRE ATT&CK techniques.

A comprehensive multi-phase tool designed to rigorously check the novelty of proposed research methods or technical ideas against current academic literature. It systematically extracts core claims, performs multi-source literature searches (including arXiv, major conferences, and web databases), and uses advanced cross-model verification to generate a structured, actionable Novelty Report, advising on the unique contribution and research positioning.

This skill automates the generation of publication-quality figures and comparison tables for academic papers. It converts structured experimental data (e.g., JSON, CSV) into various plots, including line graphs, bar charts, scatter plots, and heatmaps, ensuring consistent styling suitable for LaTeX submissions. It handles the core data visualization needs for ML and research reports, greatly streamlining the process of creating professional results sections.

This skill generates a comprehensive, structured outline for an academic paper using raw inputs such as research narratives, experiment results, and reviewer conclusions. It can intelligently integrate structural guidance from reference papers (via style-reference) to optimize section ordering, figure budget, and overall academic flow, ensuring the plan meets specific venue standards (e.g., ICLR, NeurIPS). Ideal for researchers who need to transition from scattered data and ideas into a cohesive, publication-ready plan.

This skill guides the programmatic creation, enrichment, and secure sharing of threat intelligence within a MISP platform. Using the official PyMISP Python library, users can manage Indicators of Compromise (IOCs), apply MITRE ATT&CK tags, configure sharing groups, and export structured data in STIX 2.1 format. It is essential for security assessments, incident response, and automated threat intelligence pipelines.

PydanticAI is a robust Python framework that integrates Pydantic's type-checking and validation capabilities into Large Language Models (LLMs). It allows developers to build production-ready AI agents that guarantee structured, validated outputs, moving beyond simple raw strings. Key features include supported tool calling, dependency injection for testability, and multi-model compatibility across major providers like OpenAI, Anthropic, and Gemini. Use this when reliability and correct data structure are paramount.