Skill UI

Provides detailed evaluation of machine learning models using plugin metrics to assess accuracy, precision, recall, F1, and other key indicators, helping users compare models and validate performance before deployment.

Python library for accessing SEC EDGAR filings, extracting XBRL statements, insider trading, and institutional holdings data to power financial analysis, screening, or structured data workflows across 10-K/10-Q/8-K/DEF-14A filings.

A comprehensive skill for building robust Command Line Interface (CLI) applications in Go using the spf13/cobra library. This skill covers the entire lifecycle of a CLI, including defining command/subcommand trees, managing persistent and local flags, implementing complex argument validators, and utilizing the hook chain (PreRunE, RunE, etc.). It is essential for creating professional, Unix-native command-line tools.

Details the use of spf13/viper for robust, layered configuration management in Go applications. It ensures that configuration values are resolved correctly from multiple sources—such as command flags, environment variables, configuration files (YAML, JSON), and default settings—following a strict precedence order. Essential for building complex CLI tools and daemons.

Generates championship-grade, F1-inspired test suites based on the WJTTC methodology. This skill enforces a 'tests first' philosophy, analyzing the codebase to define structured test plans. It covers standard industry unit tests (Layer 1) and deep expert edge cases (Layer 2). Furthermore, it includes Signal Integrity Audits to ensure the test suite's reliability is paramount, guiding development toward maximum code quality.

This skill applies rigorous, F1-inspired standards to software quality assurance. It executes comprehensive test plans, classifies failures across five critical tiers (Brake, Engine, Aero, Tyre, Pit), audits Continuous Integration (CI) signal integrity, and generates detailed WJTTC reports. Use it to validate functionality, reproduce complex bugs, or determine the readiness of a release.

A comprehensive guide for designing and auditing rigorous empirical evaluations for sensing systems, particularly Human Activity Recognition (HAR). It emphasizes best practices such as leave-one-subject-out cross-validation, using real human subjects under diverse conditions, reporting event-level metrics (e.g., Macro-F1) over raw accuracy, establishing fair baselines, and mitigating data leakage (e.g., subject or session leakage). This ensures that reported results are robust, generalizable, and defensible against academic skepticism.

This skill provides an in-depth, entity-level scorecard for clinical or biomedical Named Entity Recognition (NER) models. It calculates precision, recall, and F1 scores (both strict and partial match modes) using a user-supplied gold corpus. Key features include per-label error breakdown, a confusion matrix, and detailed False Negative/False Positive analysis, essential for debugging model performance in highly sensitive medical domains.

This skill evaluates de-identification and clinical NER models against rigorous leakage-first release gates (G1a-G8). Instead of relying on aggregate F1 scores, it focuses on detecting residual Protected Health Information (PHI) leakage and enforcing per-label recall floors, which is crucial for HIPAA compliance. Determines if a model is RELEASABLE or QUARANTINED.

F1-inspired test executor and reporter: runs test plans, reproduces and root-causes bugs, audits CI signal integrity, and files tiered WJTTC reports with Brake/Engine/Aero/Tyre/Pit verdicts.