language-detector
Detect language of text with confidence scores, support for 50+ languages, and batch text classification.
Detect language of text with confidence scores, support for 50+ languages, and batch text classification.
Transcribe audio/video with AssemblyAI (local upload or URL), plus subtitles + paragraph/sentence exports.
Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).
Audio transcription using local whisper.cpp server with CUDA acceleration. HTTP API for speech-to-text conversion.
Create interactive maps with markers, heatmaps, routes, and choropleth layers. Use when visualizing geographic data, plotting locations, or creating map-based reports.
Analyze text sentiment (positive/negative/neutral) with confidence scores, emotion detection, and visualization. Supports single text, CSV batch, and trend analysis.
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
Use TabularPredictor.predict_proba with full argument guidance for classification probability outputs; depends on autogluon-tabularpredictor-fit and supports autogluon-tabularpredictor-calibrate-decision-threshold/set-decision-threshold.
Compare two datasets to find differences, added/removed rows, changed values. Use for data validation, ETL verification, or tracking changes.
Detail every TabularPredictor.fit argument, including presets, ensembling, resources, HPO, and deployment settings; depends on autogluon-tabularpredictor-class and feeds autogluon-tabularpredictor-fit-summary, predict-proba, calibrate-decision-threshold, set-model-best, save/load.
分析多轮评估结果评分数据,统计各项指标,计算评级等级。适用于分析评分趋势、计算S/A/B评级
整合多情点分析结果为综合报告,通过去重、分类、排序、总结生成高质量分析。适用于整合多分析源、生成统一报告
Advanced matrix theory expert covering spectral theory, matrix factorizations, and numerical linear algebra
Analyze multi-round evaluation result scoring data, calculate various metrics, calculate rating grades. Suitable for analyzing scoring trends, calculating S/A/B ratings
Set binary decision thresholds with TabularPredictor.set_decision_threshold and understand its single argument; depends on autogluon-tabularpredictor-calibrate-decision-threshold or autogluon-tabularpredictor-predict-proba for threshold selection.
Consolidated AutoGluon Tabular tutorial summary (essentials + how-it-works + in-depth), explaining the workflow and every highlighted argument; depends on autogluon-tabularpredictor-class and autogluon-tabularpredictor-fit, plus autogluon-tabularpredictor-calibrate-decision-threshold/set-decision-threshold for threshold tuning.
This skill should be used when users need to write, review, or debug Stata code for data cleaning and analysis. Use this skill for tasks involving data import, variable management, data documentation, merging/appending datasets, creating analysis variables, and following IPA/DIME Analytics coding standards. This skill should be invoked when working with .do files, .dta files, or any Stata-related data processing tasks.
Professional Plotly visualization best practices for Field Agents including chart specifications, color palettes, formatting standards, and JSON structure requirements for executive-ready data visualizations
Comprehensive statistics expert covering probability theory, distributions, hypothesis testing, regression, and Bayesian methods
Calibrate binary classification decision thresholds with TabularPredictor.calibrate_decision_threshold, detailing every argument and trade-off; depends on autogluon-tabularpredictor-fit and pairs with autogluon-tabularpredictor-set-decision-threshold and autogluon-tabularpredictor-predict-proba.
Generate custom reports, query reports, and script reports for Frappe applications. Use when creating data analysis and reporting features.
Generate and interpret training summaries with TabularPredictor.fit_summary, detailing all arguments and outputs; depends on autogluon-tabularpredictor-fit and complements autogluon-tabularpredictor-set-model-best.
Create interactive Desmos graphs in Obsidian using desmos-graph code blocks. Use when visualizing functions, parametric curves, inequalities, or mathematical relationships with customizable styling and settings.