Skill UI

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

This skill guides users on querying Azure Monitor activity and sign-in logs using KQL to detect sophisticated security threats. It covers identifying suspicious administrative activities, impossible travel scenarios, privilege escalation attempts, and unauthorized resource modifications. Ideal for Security Operations Center (SOC) analysts building advanced threat hunting rules or developing cloud SIEM detections.

This skill guides the creation of high-quality, finished cyber threat intelligence reports. It tails content for specific audiences—from C-suite executives (strategic risk) to SOC analysts (tactical IOCs). Use it when synthesizing raw data into actionable intelligence products, generating threat briefings, or conducting post-incident assessments, ensuring adherence to industry standards like TLP and NIST.

Perform bounded, local exploratory analysis on supported scientific files like CSV, JSON, and HDF5. Inspect metadata, check missingness, and audit outliers without executing code or accessing networks. Generates deterministic reports for data validation before modeling.

This internal agent skill processes raw X/Twitter posts into structured bug candidates. It systematically performs parsing, content deduplication, PII redaction, reliability scoring, and classification. Finally, it clusters related reports using deterministic signatures, providing a highly organized output for efficient bug triage and analysis from large-scale social media streams.

This advanced skill acts as a hybrid router for complex research queries. It deterministically classifies the user's intent, delegating to specialized modules (e.g., funding grants, academic literature, patent search, company dossier) when applicable. If no specialist fits, it executes a robust fallback plan, synthesizing multi-source information into a detailed, cited briefing or document. Ideal for comprehensive investigative research across multiple domains.

Bilig WorkPaper provides a code-first runtime environment for complex spreadsheet business logic. It allows agents to interact with structured data using formulas and JSON workbooks via deterministic API calls (MCP/TypeScript). This is ideal for replacing unreliable UI automation in use cases like quote calculators, budget modeling, and data validation, ensuring calculation integrity through explicit read-back proof.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.

A comprehensive, professional single-page dashboard template designed for administration and analytics. It features a fixed sidebar, top navigation bar, KPI card grid, and dedicated space for 1-2 main charts (line, bar, area). It is ideal for operational monitoring, business reporting, and visualizing key performance indicators.

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

This guide provides comprehensive standards for designing, quantifying, and narrating scientific figures and tables for high-impact publications. It details best practices for maintaining image integrity (e.g., uncropped blots, linear adjustments), ensuring all data points are quantified across replicates, and structuring the visual evidence to advance a clear, mechanistic argument step-by-step.

This guide provides a comprehensive framework for conducting heterogeneity and conditionality analysis in Chinese Public Administration (CPA) research. It outlines theory-guided methods for selecting dimensions (e.g., administrative level, governance context, institutional structure) and details best practices for both quantitative (Chow test, interaction terms) and qualitative (QCA) comparison, ensuring findings are theoretically grounded and methodologically rigorous.