Skill UI

This skill processes raw, unstructured materials (e.g., conversations, reports, controversies) into highly structured, reusable casebook entries. It focuses on identifying core facts, defining mechanism chains, and mapping responsibility links while ensuring rigorous data anonymization. It is designed for deep knowledge management and pattern recognition, helping users build a reliable, reusable knowledge base for future professional analysis, rather than generating immediate advice.

This skill facilitates structured, bidirectional reading and knowledge synthesis for academic texts, theories, and articles. It forces users to first capture the source material's original intent, before critically mapping its relationships, conflicts, and absorptions against the CrossFrame framework. It ensures structured output with clear source boundaries, making it ideal for deep learning and scholarly work.

This skill enables the creation and maintenance of highly structured, configurable research wikis. It manages source provenance, compiling raw source materials into organized concept pages, index maps, and derived artifacts. Ideal for systematically documenting complex knowledge bases, such as research notes, product documentation, or domain studies, ensuring full traceability and consistency.

This tool is designed to analyze source code by extracting core entities (classes, functions, modules, types) and mapping their complex relationships (imports, inheritance, calls, dependencies). It constructs a comprehensive Knowledge Graph (KG) in AgentDB. This is essential for detailed dependency analysis, understanding large codebase structures, and performing accurate impact assessments.

This skill utilizes hyperbolic space embedding (Poincare ball model) to represent complex data structures with inherent hierarchy, such as dependency trees, ontologies, or module taxonomies. Unlike standard Euclidean embeddings, hyperbolic space preserves hierarchical distances efficiently, allowing for accurate distance calculations (geodesic distance) that grow logarithmically with tree depth. It is ideal for advanced knowledge graph analysis and code architecture mapping.

A systematic methodology for resolving discrepancies between conceptual models (documentation, tests, diagrams, metrics) and actual observed behavior (live code execution or real data). This process mandates that observed reality (the 'territory') always overrules the theoretical map, ensuring system integrity and accurate knowledge updates.

Evidence-first reading analyst that reconstructs a document's central claims, argument tree, and evidence ledger. Supports quick, deep, map, Feynman, and whole-book modes, plus critique, knowledge maps, and recall plans.

A comprehensive guide covering advanced offensive methodologies for data exfiltration. Techniques include abusing DNS (dnscat2, iodine), tunneling over HTTPS/CDN, utilizing ICMP, and exploiting cloud storage services. This knowledge is critical for authorized red team engagements and post-exploitation simulations, mapping directly to MITRE ATT&CK tactics like T1048 and T1041.

This skill helps map audience awareness stages to messaging strategies during campaign planning. It diagnoses where customers sit on the awareness ladder (unaware to most aware) and calibrates psychological approaches, language, and persuasion tactics accordingly. Use it to identify audience awareness before writing offers or sequencing content, ensuring the right message matches their current knowledge and motivation levels for better conversion.

Turns articles, books, PDFs, and web pages into evidence-first reading reports. Five modes (quick, deep, map, feynman, book) separate claims, evidence, data, assumptions, counterarguments, and limitations, with knowledge maps, confidence tags, and Feynman recall checks.

Entropy Box is an agent-native knowledge compiler for embodied-AI development. It compiles fragmented papers, repositories, and documentation into a persistent knowledge artifact. It provides a Panorama Graph to map technical problems within embodied-AI systems. Users can consult solutions, search knowledge, verify evidence, and assemble grounded workflows. It covers domains like manipulation, navigation, and perception. Do not use for direct robot control or generic software development.

This senior product manager agent provides expertise across six knowledge domains including strategy, discovery, planning, execution, analytics, and communication. It applies over 30 proven frameworks like RICE and MoSCoW, utilizes 12 templates for PRDs and roadmaps, and calculates 32 essential SaaS metrics with exact formulas. Ideal for structured product analysis, prioritization, and decision-making without ad hoc brainstorming.