Data Science

Use this skill when you need to perform comprehensive security vulnerability assessments on a codebase. This skill launches the security-orchestrator agent to conduct systematic security reviews by breaking down the codebase into architectural units and performing deep security analysis.

This skill should be used when the user asks to "analyze data", "build a model", "explore this dataset", "run analysis", or needs a structured data science workflow. Orchestrates brainstorm, plan, implement, review, and verify phases with output-first verification.

Senior Business Analyst with 10+ years bridging business and technical teams. Use when conducting market research, competitive analysis, gathering requirements, creating business process models, cost-benefit analysis, or validating assumptions with data.

Test coverage analysis and improvement strategies for Solidity contracts. Use when analyzing or improving test coverage.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Create, evaluate, and optimize GitHub Actions workflows and custom actions. Use when building CI/CD pipelines, creating workflow files, developing custom actions, troubleshooting workflow failures, performing security analysis, optimizing performance, or reviewing GitHub Actions best practices. Covers Ruby/Rails, TypeScript/Node.js, Heroku and Fly.io deployments.

Create Jupyter notebooks for FF Analytics following project conventions. Use this skill when the user requests analysis notebooks for player evaluation, roster health, trade scenarios, market trends, or projection quality analysis. Guides through notebook structure, DuckDB connections, mart queries, visualization standards, and freshness banner patterns.

Bidirectional conversion between pandas DataFrames and Python dataclasses. Use this skill for type-safe conversion between SQL results, DataFrames, and dataclass instances.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Orquesta analisis semantico del vault (conceptos, grafo, embeddings y busqueda) con procesamiento por lotes y manejo de errores.

Comprehensive analysis framework for Fixed Indexed Annuities (FIAs). Use when analyzing, comparing, or evaluating FIA products including surrender charges, index options, crediting methods, riders, commissions, and suitability. Creates detailed product profiles with 40-question suitability assessments and LLM-friendly scoring methodology. Use for internal product analysis, client suitability determination, or when building product comparison documents.

Create, edit, run, and convert marimo reactive Python notebooks. Use when working with .py marimo notebook files, creating reactive/interactive notebooks, exploratory data analysis in notebook format, or converting from Jupyter (.ipynb) to marimo. Marimo notebooks are pure Python files with @app.cell decorators that enable reactivity. Also covers wigglystuff widgets for advanced interactivity.

PHANTOM v6: Ultimate cognitive architecture for debugging, code review, generation, and self-analysis. Combines Abductive Fault Inversion, Spectral Execution Tracing (Ghost/Demon dual traces), Dialectical Assumption Collapse, Cognitive Immune System (CIS) with 16 antibodies, Intelligence Amplification Framework (IAF) with 7 enhancement methods, Cognitive Capability Activation (CCA), 7-Level Architecture (ARCH), and Mem0 as primary unlimited memory system. Features 58 capabilities, monitoring checkpoints, persona verification (Constructor/Destroyer/Defender/Judge), calibrated confidence, Responsive Generator Model (RGM), GRIMOIRE spell format, and cross-conversation persistence via Mem0. Activates for: debugging, code review, "why isn't this working", architecture design, high-stakes reasoning, ULTRATHINK sessions, or understanding code/cognitive behavior.

Multi-round web search with low-frequency query generation. Prioritize GitHub/StackOverflow for actionable code, extract AI Overview insights, and perform deep link analysis. Use proactively for complex problems requiring external knowledge or when stuck on implementation challenges.

Verify claims in tacosdedatos content before publication. Use this skill when reviewing drafts for factual accuracy, checking code examples work correctly, validating statistics and sources, or verifying quotes and attributions. Produces a structured fact-check report with verdicts for each claim. For deep verification requiring extended research, delegate to the fact-checker subagent instead.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Search your LinkedIn posts/shares by topic, find connections by title or company, and get LinkedIn statistics. Use when analyzing your LinkedIn data, finding specific connections, or reviewing past posts and shares.

Knowledge engineering pipeline that transforms messy human intent and repository analysis into living operational domain profiles

Orchestration workflow for Bayesian statistical analysis. Invoke when performing Bayesian modeling, statistical analysis with Stan, or building probabilistic models.

Use this skill for multi-step development tasks. Latent Chain Mode reduces token usage by 70-80% through hidden-state reasoning with 4-phase workflow: analysis → plan → impl → review.