Skill UI

This skill is designed to accurately convert complex, Hugo-managed documentation sites and content into standard Markdown format. It goes beyond generic knowledge by inspecting the entire local Hugo repository structure, including `hugo.toml`, custom shortcodes, layouts, and content files. It preserves the original content's semantic meaning while materializing Hugo-specific constructs into clean Markdown.

This skill manages the end-to-end lifecycle of cloud test execution using HyperExecute for platforms like LambdaTest/TestMu AI. It provides comprehensive functionality to analyze projects, generate and validate complex YAML configurations, run CLI jobs, and debug failures. Ideal for integrating robust, scalable, and matrix-based testing into CI/CD pipelines.

This skill guides the structured development process for implementing new features or fixes based on Product Requirement Documents (PRDs) or predefined issues. It emphasizes best practices, including Test-Driven Development (TDD), regular type-checking, running comprehensive test suites, and completing the cycle with a formal review process.

This skill performs a deep comparison of two code versions to verify semantic equivalence, going beyond simple syntax diffing. It uses semi-formal tracing techniques to trace both versions against shared specifications and boundary conditions (e.g., null, zero, max/min). Ideal for confirming if a refactor, rewrite, or migration has unintentionally altered the code's behavior, answering the question: "Did I break anything?"

This skill provides an autonomous, repository-wide pipeline for auditing and fixing complex logical inconsistencies. It systematically executes stages including health checks, deep review, locating divergences, generating fixes, and performing diff-verification until the codebase is deemed clean. Ideal for maintaining high code quality and resolving deep, systemic bugs across entire projects.

This sophisticated skill is designed to locate the root cause of a confirmed software failure. It performs a systematic, semi-formal tracing process: first tracing backward from the observed failure point (using provided stack traces, assertions, or error messages) to identify the original premise, and then tracing forward to confirm the symptom. It outputs a highly structured report detailing the divergence, premises, and remedy.

This skill is designed to identify subtle and complex logic bugs within a single code file or function. It employs a semi-formal execution tracing methodology, systematically breaking down the suspected bug into five stages: Premises (expected state), Trace (execution path), Divergence (actual deviation), Trigger (reproduction case), and Remedy (fix). It is ideal for scenarios where users suspect code is wrong but cannot specify a concrete failure point.

This skill provides comprehensive access to structured corporate content for listed stocks via Longbridge. Users can retrieve the latest news articles, analyze regulatory filings (such as 10-K, 10-Q, 8-K), check community discussions, and perform detailed SEC EDGAR document analysis. It supports querying risk factors, management discussions (MD&A), and regulatory rules.

This skill provides deep, cross-border financial analysis and valuation metrics for stocks across multiple markets (e.g., US, HK). Users can access detailed income statements, balance sheets, cash flow data, analyze business segments, compare valuation multiples (PE, PB), run sophisticated DCF models, and perform value screening. It is an essential tool for fundamental research, investment modeling, and corporate analysis.

This skill integrates with Monte Carlo's observability platform to provide a comprehensive health report for data assets. It checks critical metrics including data freshness, active alerts, monitoring coverage, asset importance, and the health of upstream dependencies. Activates when users inquire about the status, reliability, or quality of a data table.

This skill provides comprehensive monitoring advisory services for data assets and AI agents. It helps users assess data coverage gaps, analyze use-case criticality, and automatically create data quality monitors (table, metric, validation). Furthermore, it enables monitoring of AI agent performance, latency, and observability, ensuring robust data governance across the entire ML lifecycle.

This skill helps diagnose performance bottlenecks, slow jobs, and expensive queries across various data platforms (Airflow, dbt, Databricks). It uses a tiered investigation approach, starting with broad discovery to pinpoint problematic jobs or queries, bridging to affected tables, and finally drilling down to identify root causes, latency trends, and change-related regressions.