Científicos de datos

Skill: ComfyUI LoRA Data Gathering

Use this skill when the user wants to gather, collect, or prepare training images for LoRA fine-tuning. Covers the full pipeline: web research, image downloading, video frame extraction, dataset curation, image processing, and auto-captioning. Use it when the user mentions collecting images from the web, building a training dataset, finding reference images for a style or subject, or preparing images they already have into a LoRA-ready dataset. Also use it when they say things like "I want to train a LoRA but I don't have images yet" or "help me find training data." Do NOT use this skill if the user already has a prepared dataset and just wants to start training — that's comfyui-lora-training.

Bakery880

Bayesian Elicitation

Apply this skill when the task requires updating beliefs across multiple rounds of evidence rather than treating each turn independently. Use it for preference learning, recommendation refinement, repeated comparisons, adaptive QA exploration, or any workflow where choices, clicks, rejections, or observations reveal a hidden objective. Trigger on requests involving repeated selection, narrowing, prioritization, "learn what matters," "adapt the next step," or exploratory testing that should focus based on earlier findings.

noodleA10

Research System — Master Skill

The research system provides industry-backed financial guidance for every property assumption in the simulation. It operates as an 11-layer multi-LLM pipeline: N+1 orchestrator (dual analyst panels → API validation → Opus synthesis), 15 prompt-builder tools, 10 deterministic calc tools, 7 live market data sources, Pinecone vector similarity, post-LLM validation, guidance extraction, SSE streaming, and a 3-tier badge display hierarchy. Load this skill for any work touching research generation, badges, research config, or the orchestration pipeline.

Norfolk-Group0

Sator Python Pipeline

Async Python data pipeline development for 4NJZ4 TENET Platform. USE FOR: ETL pipelines, async data processing, PostgreSQL with asyncpg, epoch-based extraction. Location: packages/shared/axiom-esports-data/. DO NOT USE FOR: synchronous Python scripts, non-SATOR data pipelines, general Python development.

notbleaux0

Depuración

Analytics

Аналитика YouTube канала. Анализ последних видео, конкретного видео и аудитории.

novikoffalex0

Kpi Framework

Define, document, and socialize KPIs across your organization, from individual metric definitions to a full metrics hierarchy. Use when establishing metric definitions, building a metrics dictionary, aligning teams on KPI calculations, or running a north-star metric workshop. Produces a metrics dictionary, KPI hierarchy documentation, and dbt SQL implementations for core metrics.

nrakow0

Funnel Analysis

Build funnel analysis models that measure step-by-step conversion rates and identify where users drop off. Use when tracking conversion through a user flow, calculating drop-off rates between funnel stages, building a reusable funnel macro, or segmenting funnel performance by cohort, channel, or device. Produces dbt fact models, aggregation models, and a reusable Jinja funnel macro.

nrakow0

Staging Layer

Build dbt staging models (stg_ prefix) that clean and standardize raw source data one-to-one. Use when adding a new source, building the first layer of transformation, or auditing existing staging models. Triggers: 'staging layer', 'staging model', 'stg_ model', 'build staging', 'raw to staging', 'clean source data', 'new source model'.

nrakow0

Advanced Evaluation (LLM-as-Judge)

This skill should be used when the user asks for "LLM-as-judge evaluation", "advanced quality assessment", "multi-dimensional scoring", "pairwise comparison", "evaluate with position bias mitigation", "judge this output against criteria", or when high-stakes outputs need a rigorous, multi-pass quality assessment. Extends the base evaluation skill with pairwise comparison, position bias mitigation, self-consistency checks, and calibrated confidence scoring.

nsalvacao0

Ai Engineering

AI Engineering principles and decision-making for ML, DL, RL, and DRL. Framework selection, model architecture, training patterns, evaluation strategies, and deployment. Suitable from beginner to expert level. Use when working with machine learning, deep learning, reinforcement learning, model training, AI deployment, or MLOps tasks.

ntdev2040

Testing

Statistical Validation Testing

Test-driven validation for R-based statistical analyses. Use when writing unit tests, validating model outputs, or verifying data transformations.

ntluong950

Bioinformática

Cross Basis Construction

How to construct cross-basis matrices for DLNMs using dlnm::crossbasis(). Use when specifying exposure-lag-response relationships, choosing basis functions, or setting knot placement.

ntluong950

Académico

Reproducible Research Documentation

Standards for documenting R-based analyses for reproducibility. Use when writing R Markdown, Quarto documents, READMEs, or inline code comments.

ntluong950

Análisis de Datos

Analyze

Unified analysis skill - Python data analysis (--data) or KB gap identification (--kb)

nuggetswise0

Sentiment Analysis

Analyze sentiment (positive/negative) of text using a Python script and Hugging Face Transformers. Use when the user asks for the sentiment of a message, review, or any text.

azerothl0

Paquetes y Distribución

ML Dependency Minimizer

Minimize Python/ML project dependencies to their smallest working set. Use this skill whenever the user asks to analyze, shrink, extract, or clean up dependencies for any Python or Machine Learning project — even if they just say "fix my requirements.txt", "what packages do I actually need", "extract this module from a big repo", or "set up a clean environment". Also use when migrating ML code between machines (e.g. GPU → CPU) or debugging ModuleNotFoundError in a new environment.

Azhi-ss0

Fetch Static Model

Download OpenVINO static models from an online model zoo URL (remote disk HTTP directory listing) using a model table (name/framework/precision) and store artifacts under a local directory.

azhai2190

Bulk Rna Qc

Quality control pipeline for bulk RNA-seq datasets including normalization, PCA, sample correlation, and differential expression.

Nyha150

Desarrollo de Videojuegos

Big Data Analysis Skill

Use when analyzing data with Hive/Impala tables, writing SQL for data exploration, or building/deploying Spark ETL jobs on HDFS/YARN. ALWAYS trigger this skill — even if the user does not use these exact words — for any of the following: writing or reviewing a Spark Scala job, migrating SQL from Hive/Impala to Spark, creating or altering Hive tables, inserting data into partitioned tables, joining large tables in Spark SQL, using Spark UDFs, verifying table schema before coding, GROUP BY with text fields, OOM on large tables, INSERT column mismatch or silent data shifts, broadcast join stall or task explosion, DataFrame API being slow, cache() not materializing, metadata not visible after Spark write, date window off-by-one, control character regex not matching, Scala string interpolation bugs in Spark SQL, or any time the user says their Spark job is slow, wrong, or behaving unexpectedly.

Oak-B0

Train Model

Entrainer le modele ML AML

Ayoub-ouederni0

LLM & AI

Data Ai Ml

Build data pipelines, AI systems, and machine learning models with Python. USE THIS for data processing, model training, LLM integration, RAG systems, NLP, vector databases, prompt engineering, knowledge bases, data analysis, and AI/ML workflows. Include when user mentions AI, ML, data science, LLMs, embeddings, retrieval-augmented generation, or intelligent systems.

Aymaneerrachidi0

Salud y Fitness

Arena Report

Generate a structured comparison report for Adapter Arena benchmark results. Use after all runner agents have completed their tasks and results need to be compiled into a comparative analysis.

obe7110

Documentos

Paper Reader

AI/CS paper reader - analyzes PDF papers and extracts key points, contributions, and methods

obiyoag0

Patrones de Arquitectura

Plot

Plotly chart conventions and layout rules for AXIS

ax-foundry0

Semantic Search

Search toys using natural language powered by embeddings.

octocademy0

Ai Engineering Skill

Practical guide for building production ML systems based on Chip Huyen's AI Engineering book. Use when users ask about model evaluation, deployment strategies, monitoring, data pipelines, feature engineering, cost optimization, or MLOps. Covers metrics, A/B testing, serving patterns, drift detection, and production best practices.

odewahn0