Data Scientists

Pandas Polars

DataFrame operations with pandas and polars — groupby, joins, reshaping, performance. Use when manipulating tabular data, choosing between pandas and polars, optimizing DataFrame code, or translating between the two libraries.

Embedding Vectordb

Vector embeddings and vector DB patterns — model choice, similarity metrics, index tuning. Use when choosing an embedding model, picking or migrating between vector databases, optimizing semantic search quality or latency, or building a hybrid (dense + sparse) retrieval pipeline.

Data Quality

Data quality framework — completeness, accuracy, consistency, validation, and contracts. Use when implementing data validation, setting up quality checks for a pipeline, defining data contracts between teams, or investigating data anomalies.

Sales & Marketing

Data Visualization

Chart selection, color accessibility, annotation, and dashboard design. Use when creating charts, designing dashboards, choosing visualization types, improving chart readability, or reviewing data presentations for clarity.

Ml Pipeline

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Ai Fundamentals

Core ML/AI concepts — model types, training pipelines, evaluation metrics, neural architectures. Use when explaining or comparing ML/AI concepts, choosing a model approach for a problem, designing or reviewing a training pipeline, picking evaluation metrics, or debugging issues like overfitting, data leakage, and class imbalance.

Sales & Marketing

Bmad Agent Analyst

Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.

Compass-Brand0

Data Science

Python data analysis, statistics, and data science workflows. Use when the goal involves loading data, cleaning, aggregating, computing statistics, building models, or producing plots and reports.

Compdeep0

Debugging

Model Recommender

Recommends the right AI model for a task by scoring models across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile. Use when the user says "which model should I use", "recommend a model for this", "what LLM is best for X", "compare these models", "help me pick an AI model", "which Claude should I use", or "route these tasks to the right model". Also analyzes a task plan and clusters subtasks by model fit, showing which work to do with which model — like Dispatch matching heroes to missions by overlapping skill polygons.

Technical Docs

Research Report Skill

Generate well-structured research experiment reports as Markdown files with matplotlib plots saved as PNGs. Use this skill whenever the user asks you to write up results, summarise an experiment, create a report from experimental data, produce findings, or document research outcomes — even if they don't say "report" explicitly. Also trigger when the user says things like "plot the results", "write up what we found", "summarise these runs", "make a report for my supervisor", or "document this experiment". This skill covers ML/AI safety research reports with comparisons against baselines, training curves, and evaluation metrics. If the task involves presenting experimental results in any written form, use this skill.

xycoord0

Rag Engineering

Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, vector stores, retrieval, evaluation. Use when building a RAG pipeline, choosing chunking strategies or embedding models, debugging retrieval quality or hallucinations, evaluating an existing RAG system, or scaling/migrating vector stores.

Embedding Vectordb

Bioinformatics

Perturbation Type Router

Routes perturbation datasets to the correct analysis branch (chemical, CRISPR, RNAi, or combinatorial) with route-specific preprocessing parameters. Use after paper assessment to determine analysis pathway, or when a user asks "how should I analyze this perturbation data" or "what preprocessing parameters for a CRISPR/drug screen".

conradry0

Data Quality

Transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

strmt70

Debugging

Model Recommender

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Lab Tools

Experiment Tracker — Maycrest Group

Data-driven experiment design and tracking lead for TIE Platform and SlothFit — manages A/B tests, feature flags, and hypothesis validation using Supabase data and Expo app instrumentation. Trigger phrases: "design an experiment", "track this test", "A/B test", "feature flag", "experiment results", "hypothesis validation", "test this idea", "measure this change", "experiment plan", "rollout strategy".

coreymaypray0

Analytics Dashboard Generator

Create dashboards with KPIs and real-time metrics.

cornmanwtf0

Cdc Pipeline

Implement change data capture and event-driven sync.

cornmanwtf0

Computational Chemistry

Datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Sologa0

Guidance for using Pandas, NumPy, Statistics, and Machine Learning within the SimUCI context.

coslatte0

Finance & Investment

Technical Analysis Logic

Structured guide for implementing and verifying financial technical indicators and trading signals with accuracy and performance.

cosmic13300

Debugging

Hugging Face Evaluation

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

cpich3g0

Lab Tools

Research Organizer

整理 ML/VLM 研究專案的資料夾結構：規劃標準目錄配置、整理散亂的實驗結果、建立 checkpoint 和 log 的命名規範，讓專案在幾個月後還能看懂。

DivaGabriel0

Finance & Investment

Axiom Macro Pipeline

Run AXIOM's full institutional macro intelligence pipeline (E1→E8). Classifies market regime via logistic regression on 9 FRED indicators, retrieves historical analogues from an 82-event corpus, generates bull/base/bear scenarios, and produces multi-asset + stock-level allocations with Monte Carlo risk metrics.

crazymage050