Skill UI

This framework implements robust input and output validation guardrails for LLM-powered applications. It prevents prompt injection, detects and redacts PII, filters toxic content, and validates model outputs against defined schemas. Use it when deploying AI agents that handle sensitive data or require strict adherence to corporate policies, ensuring a secure and trustworthy AI interaction layer.

This tool monitors Modbus TCP communication within SCADA and ICS environments to detect security anomalies. It performs deep packet inspection, baselines normal communication patterns (e.g., typical function code distribution, register access), and applies statistical analysis to identify unauthorized register writes, reconnaissance attempts, or denial-of-service attacks targeting industrial control devices.

A sophisticated, multi-stage workflow designed to generate publication-quality technical illustrations, such as architecture diagrams and complex method figures, for academic papers. It utilizes a strict, iterative loop supervised by an advanced AI (Claude) to refine layout, color compliance, and structural correctness, ensuring high fidelity and professional standards across multiple rendering passes.

This skill is deprecated and superseded by /paper-poster-html. It was designed to generate academic posters using legacy LaTeX pipelines. Users must immediately switch to the updated HTML/CSS pipeline for current functionality and to avoid errors. Do not use this skill for new posters.

This skill converts a compiled academic paper into a structured, professional conference slide deck. It is designed for various talk formats (oral, spotlight, poster) and helps transform the dense research narrative into a clear, temporal story suitable for academic presentations. Outputs include LaTeX Beamer source and editable PPTX.

This skill uses advanced AI and LLM capabilities to correlate fragmented Open Source Intelligence (OSINT) data. It ingests findings from diverse sources—including username enumeration, email lookups, social media, domain records, and breach databases—to generate unified, intelligence-grade profiles. It provides link analysis and confidence scoring, transforming raw data into actionable threat intelligence for target profiling.

Assesses organizational readiness for migrating cryptographic systems to post-quantum standards (PQC), aligning with NIST guidelines. The tool performs comprehensive cryptographic inventory scanning to identify quantum-vulnerable algorithms (RSA, ECDH, ECDSA) and evaluates the feasibility of implementing hybrid TLS configurations using standards like ML-KEM and ML-DSA. Essential for implementing crypto-agility across enterprise infrastructure.

This tool facilitates comprehensive purple team exercises by executing Atomic Red Team tests mapped to MITRE ATT&CK techniques. It is primarily used for gap analysis, validating detection coverage (blue team visibility) against specific threat vectors, and building continuous, automated adversarial emulation pipelines in CI/CD environments.

This skill manages the entire academic rebuttal cycle. It parses external reviews from major conferences (like ICML/OpenReview), drafts safe, text-only responses while strictly enforcing grounding (no fabrication) and full issue coverage. It supports multi-round follow-ups and adheres to venue-specific constraints, ensuring every claim is provable.

The Santa Method is a multi-agent adversarial verification framework designed to improve output quality by requiring two independent reviewers (Agent B and Agent C) to pass the content before publication. It eliminates single-agent bias and systematically improves outputs through iterative refinement loops until convergence or manual escalation.

This skill searches for published academic papers from major venues like IEEE, ACM, and Springer via the Semantic Scholar API. It is ideal for finding peer-reviewed journal articles and conference proceedings, providing crucial metadata such as citation counts, venue details, and TLDR summaries. Use it when you need verified, published literature beyond raw arXiv preprints.

This tool assesses whether coding agents adhere to defined skills, rules, or agent definitions. It automatically generates scenarios with varying prompt strictness, executes the agent, and generates a comprehensive report detailing the compliance rate of tool calls against predefined workflow specifications using advanced LLM classification.