數據科學

SPARC Specification phase specialist for requirements analysis, constraint identification, use case definition, and acceptance criteria creation

Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity reports. Automatically processes conversation history from the project, enables RAG-powered semantic search, and generates insight reports with pattern detection. Provides optional dashboard for visualization. Not for real-time analysis or cross-project searches.

Autonomous GitHub repository discovery and integration agent that hunts relevant open-source projects for BidDeed.AI (foreclosure auctions) and Life OS (productivity/ADHD). Searches GitHub for repos matching domain keywords, evaluates relevance via README/tech stack analysis, auto-adds as submodules or archives to target repos, and alerts Ariel with actionable summaries. Use when (1) User requests "find relevant GitHub repos", (2) Exploring new integrations for BidDeed.AI workflows, (3) Discovering productivity tools for Life OS, (4) Keeping repositories updated with latest open-source innovations.

Energy-specific charts: project timelines, cost breakdowns, financial projections, geospatial maps. Interactive dashboards for investment decisions.

Design, standardize, and implement ECharts-based visualizations and themes for InsightPulseAI dashboards, Superset plugins, and OpEx UI (AntD + M3 + ECharts).

Python fundamentals, data structures, OOP, and data science libraries (Pandas, NumPy). Use when writing Python code, data manipulation, or algorithm implementation.

Run acoustic simulations on horn geometries using BEM analysis. Use when evaluatinghorn performance, analyzing impedance curves, calculating polar patterns, or scoringgeometry variations. Returns acoustic metrics and visualization data.

Analyzes data with rich metadata recommendations

Enterprise-grade company research, competitive analysis, and market intelligence using Bright Data's professional web scraping and search capabilities. Use this skill when asked to research companies, conduct competitive analysis, create market reports, analyze industries, compare products/services, or gather business intelligence. Triggers include requests like "research [company]", "competitive analysis of X vs Y", "create a market report", "analyze the [industry] landscape", or "compare [products/companies]".

Automated board presentation generation pulling live data from Asana, Salesforce, Finance GL for quarterly board meetings with executive narrative and data visualization

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when working with Excel files for data analysis, financial models, reporting, or any spreadsheet operations.

Fast ticker analysis for /analysis page. Provides quick BUY/SELL/HOLD recommendations based on technical indicators, recent news, and basic fundamentals within seconds. Optimized for speed over depth.

Fan Selection & Airflow Analysis Agent

Use when debugging web applications or automating browser tasks. Leverage Chrome DevTools MCP for inspection, performance analysis, and automated testing.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

WCM tech stack - Python, pandas, Stata, clinical data

Comprehensive web research via Parallel Search API. Use when user requests parallel search for deep multi-source research, technical analysis, learning new topics, current events, or comparative studies. Returns LLM-ready ranked URLs with extended excerpts (up to 30K chars). Single API call handles multiple query angles with automatic deduplication.

Pre-implementation research for design, architecture, and impact analysis. Use during brainstorming, architectural design, or before implementation to understand dependencies and integration points. Triggers on (1) designing or architecting a feature, (2) brainstorming implementation approaches, (3) analyzing impact of proposed changes, (4) exploring reference materials in extra/, (5) creating research reports before planning.

Oxford Nanopore read end reason QC analysis. Use when analyzing nanopore sequencing quality, checking for adaptive sampling efficiency, investigating read termination patterns, diagnosing sequencing issues, or running QC on POD5/Fast5 data. Integrates with ont-experiments for provenance tracking via Pattern B orchestration. Supports signal_positive, unblock_mux_change, data_service_unblock_mux_change analysis with quality thresholds.

Run long AI queries with Oracle CLI. Use for code reviews, summarization, or analysis that takes time. Always run in tmux.