Data Analysis

social-graph-ranker is the weighted graph-ranking layer for warm intro discovery, bridge scoring, and network gap analysis across X and LinkedIn. Use the social-graph-ranker skill when you need a reusable ranking engine for Lead Research, not a full outbound or network-maintenance workflow.

regex-vs-llm-structured-text skill for choosing regex or LLM in structured text extraction. Start with deterministic parsing, add LLM validation for low-confidence edge cases, and use a cheaper, more reliable pipeline for documents, forms, invoices, and data analysis.

clickhouse-io is a ClickHouse-focused skill for schema design, analytical SQL, ingestion patterns, and performance tuning. Use it to guide MergeTree choices, partitioning, materialized views, and workload-specific query optimization.

data-analyst is a minimal GitHub skill that guides agents toward SQL, pandas, and basic statistical analysis for data exploration. Best for users who want code-backed queries, transformations, and interpretations from a single SKILL.md prompt layer.

retro is a project retrospective skill for engineering teams. It analyzes commit history, work patterns, and prior learnings to generate a structured weekly retro with continuity. Use retro for sprint reviews, what did we ship questions, and Project Management check-ins.

startup-metrics-framework helps founders, analysts, and operators calculate startup KPIs like CAC, LTV, burn multiple, runway, and growth metrics for SaaS, marketplace, consumer, and B2B startups.

Use the market-sizing-analysis skill to build structured TAM, SAM, and SOM estimates with top-down, bottom-up, and value-theory methods. Covers install context, key files, inputs, workflow, and practical usage for startup market sizing and Data Analysis.

startup-financial-modeling helps agents build 3-5 year startup finance models with cohort revenue, cost structure, burn, runway, and fundraising scenarios. Best for founders and finance leads who need install context, clear inputs, and practical usage guidance from the skill's SKILL.md.

risk-metrics-calculation helps compute portfolio risk metrics like VaR, CVaR, Sharpe, Sortino, beta, volatility, and drawdown. Use it to turn return series into structured risk reporting, Python implementation patterns, and practical interpretation for finance workflows.

The backtesting-frameworks skill helps design and review trading strategy backtests with stronger controls for look-ahead bias, survivorship bias, overfitting, transaction costs, and walk-forward validation in Finance.

spark-optimization is a practical guide to diagnosing slow Apache Spark jobs with partitioning, shuffle, skew, caching, and memory tuning. Use it to install the skill from wshobson/agents, read SKILL.md, and apply evidence-based fixes from Spark UI symptoms, cluster settings, and query patterns.

torchdrug is a PyTorch-native toolkit for molecular and protein machine learning. Use the torchdrug skill to choose tasks, datasets, and modular models for graph neural networks, protein modeling, knowledge graph reasoning, molecular generation, and retrosynthesis. It is best for custom model development and reproducible configs, not just canned demos.

torch-geometric skill guide for PyTorch Geometric graph neural networks. Use it for torch-geometric install help, torch-geometric usage, graph classification, node classification, link prediction, heterogeneous graphs, custom MessagePassing layers, and scaling GNNs for Machine Learning workflows.

Use the sympy skill for exact symbolic math in Python, including algebra, calculus, matrices, physics formulas, number theory, geometry, and code generation. It helps you keep expressions exact, choose the right SymPy modules, and avoid float-heavy mistakes. Best for users who need a practical sympy guide for symbolic workflows and sympy for Data Analysis.

The rdkit skill helps with precise cheminformatics workflows: parsing SMILES, SDF, MOL, PDB, and InChI; calculating descriptors; generating fingerprints; running substructure search; handling reactions; and building 2D/3D coordinates. Use this rdkit guide for advanced control, custom sanitization, and rdkit for Data Analysis workflows.

qiskit is an IBM quantum computing skill for building circuits, choosing backends, transpiling for hardware, and running jobs on simulators or IBM Quantum devices. It is a strong fit for qiskit usage in chemistry, optimization, and machine learning, especially when you need practical install-and-run guidance rather than a theory-only qiskit guide.

Open Notebook is a self-hosted, open-source research workspace for document analysis, notes, chat with sources, search, and podcast-style summaries. Use the open-notebook skill to organize notebooks, ingest PDFs, web pages, audio, video, and Office files, and support private, API-first workflows for Data Analysis.

hypogenic is a skill for generating and testing hypotheses on tabular or text-derived datasets with LLM support. It helps with hypogenic for Data Analysis by turning empirical questions into structured, testable workflows for classification interpretation, content analysis, and deception detection. Use it when you need evidence-backed hypotheses, not just brainstorming.

The hugging-science skill helps you find and use scientific AI resources from the Hugging Science catalog and the `hugging-science` Hugging Face org. It fits biology, chemistry, climate, genomics, materials, astronomy, and similar work when you need a dataset, model, Space, or blog post you can actually run or cite. Use it for hugging-science usage and hugging-science guide workflows instead of generic search.

histolab is a Python skill for whole-slide image preprocessing in digital pathology. It supports tissue detection, tile extraction, and stain normalization for H&E slides, making it useful for dataset prep, quick tile-based analysis, and lightweight data analysis workflows. Install and use histolab with practical guidance on masks, tilers, and slide management.

diffdock is a docking skill for predicting protein-ligand binding poses from PDB structures or protein sequences plus ligands in SMILES, SDF, or MOL2. Use the diffdock skill for structure-based drug design, virtual screening, and confidence-scored pose analysis. It is not for binding affinity prediction.

dhdna-profiler extracts cognitive patterns and thinking fingerprints from text or speech. Use it to profile how someone reasons, decides, values, and communicates, compare thinking styles, or answer “what’s my thinking style?” It is especially useful for structured analysis, repeated comparisons, and deeper insight into the mind behind a passage.

The user-personas skill creates 3 refined personas from research data with JTBD, pains, gains, and unexpected insights. Use it for user-personas for UX Research, segmentation, onboarding strategy, and product decisions when you have surveys, interviews, or other source material.

market-sizing helps estimate TAM, SAM, and SOM with top-down and bottom-up methods. Use it for Market Research workflows, market entry decisions, investor decks, and launch planning when you need a defensible logic trail, assumptions to validate, and a practical first-pass market estimate.