Skill UI

This skill provides a systematic framework for analyzing cyber campaign attribution. It involves collecting, weighting, and correlating diverse indicators—such as infrastructure overlaps, TTP consistency, malware code similarities, and operational patterns—to determine the responsible threat actor. Utilizing structured methodologies like Analysis of Competing Hypotheses (ACH) and the Diamond Model, users can build confidence-weighted assessments to enhance threat intelligence accuracy.

A specialized tool for digital forensics investigators that parses the Windows Amcache.hve registry hive. It extracts crucial evidence regarding program execution history, application installation metadata, and loaded driver binaries. By correlating SHA-1 hashes and reconstructing timelines, users can determine which executables ran on a system, aiding in incident response and threat detection.

This toolset guides users through advanced digital forensic techniques using tools like Foremost and Scalpel. It demonstrates how to perform file carving—recovering specific file types (images, documents, etc.) from raw disk images or unallocated space—by analyzing file headers and footers (magic bytes). This is critical for evidence extraction when traditional file system metadata is unavailable or corrupted.

This is an advanced, structured workflow designed to conduct deep, multi-source investigations. It synthesizes current public evidence with user-provided context to generate highly structured reports. The workflow explicitly differentiates between verifiable facts, user-supplied evidence, logical inferences, and actionable recommendations, making it ideal for complex comparative analysis or continuous monitoring tasks.

A powerful tool for scientific literature review and evidence synthesis. This skill searches a curated database of full-text scientific papers, going beyond traditional abstracts. It extracts and returns highly structured, quantitative data, including methodologies, quantitative results, sample sizes, quality scores, and 25+ metadata fields per paper, making it ideal for meta-analyses and systematic reviews.

Generates professional, publication-ready clinical decision support (CDS) documents for pharmaceutical and clinical research settings. Capabilities include biomarker-stratified patient cohort analyses, evidence-based treatment recommendation reports (with GRADE grading), and advanced statistical analyses (e.g., hazard ratios, survival curves). Outputs are optimized for regulatory submissions and medical guidelines.

A systematic tool for scientific inquiry, guiding users through the entire research process. It helps formulate testable, mechanistic hypotheses from raw observations or preliminary data, following the established scientific method. The workflow includes comprehensive literature review, evidence synthesis, generating competing explanations, and designing experiments, all while mandating the creation of scientific schematics for visualization.

This skill provides a systematic framework for evaluating the rigor of scientific claims, research methodology, and evidence quality. It guides users through assessing experimental design validity, identifying various types of biases (e.g., selection, cognitive), and applying established grading frameworks like GRADE or Cochrane Risk of Bias. Ideal for systematic reviews, peer review, and critical analysis of scientific literature.

This tool collects a comprehensive diagnostic archive for the Hex platform. It gathers crucial evidence, including API connectivity status, project inventory, recent run histories, data connection health, and current rate limit information. Use this bundle when encountering persistent bugs, preparing detailed support tickets, or troubleshooting complex data flow issues.

Performs rigorous, zero-context verification of all quantitative claims, comparisons, and scope statements reported in a research paper against the raw evidence files. It is designed to detect confirmation bias, such as rounding errors, data cherry-picking, or misreported deltas, ensuring strict fidelity between published claims and underlying raw results. Ideal for pre-submission quality control.

Collects comprehensive diagnostic evidence from Snowflake's ACCOUNT_USAGE views, QUERY_HISTORY, and environment details. This tool is essential for troubleshooting persistent performance issues, connection failures, or preparing detailed support cases for Snowflake support, ensuring all necessary logs, query metrics, and resource usage data are collected in one package.

This tool performs a rigorous Level 2 semantic epistemic review of Agent-Native Research Artifacts (ARAs). It assesses six critical dimensions—including evidence relevance, falsifiability, and methodological rigor—to determine the content's intellectual soundness. It is used after initial structural validation to provide objective, constructive criticism, scoring the work from Strong Accept to Reject.