數據科學

Comprehensive security code audit using multi-phase analysis (Assessment → STRIDE Threat Modeling → Code Review → Report). Use when asked to perform security review, vulnerability assessment, code audit, pentest code review, find security bugs, or analyze code for vulnerabilities. Optimized for bug bounty hunting with concrete evidence and exploitability validation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Cross-domain pattern analysis and strategic reflection for weekly review

Multi-specialist collaborative analysis for complex decisions. Spawns parallel subagents with diverse domain expertise to analyze a topic from multiple angles. Use when user says "multi-mind", or for complex architecture decisions, technology choices, strategic planning, or any multi-faceted problem with no obvious right answer.

Deep line-by-line analysis of a function or method. Explains what each line does, why it's written that way, performance implications, edge cases, and design patterns. Use when user says "analyze-function", "analyze {function}", "deep dive on {function}", or "explain {function} line by line".

Facilitates structured brainstorming sessions, conducts comprehensive research, and generates creative solutions using proven frameworks. Trigger keywords - brainstorm, ideate, research, SCAMPER, SWOT, mind map, creative, explore ideas, market research, competitive analysis, innovation, problem solving, feature generation

Orchestrates BMAD workflows for structured AI-driven development. Use when initializing BMAD in projects, checking workflow status, or routing between 4 phases (Analysis, Planning, Solutioning, Implementation). Manages project configs, tracks progress through project levels 0-4, and coordinates with specialized workflows. Trigger on /workflow-init, /workflow-status, or when users need BMAD setup.

Analyze CSV and tabular data, create summaries, and generate insights

Product discovery and requirements analysis specialist. Conducts stakeholder interviews, market research, problem discovery, and creates product briefs. Use for product brief, brainstorm, research, discovery, requirements gathering, problem analysis, user needs, competitive analysis, and setting foundation before product planning. Hands off to product manager when analysis complete.

Facilitate data-driven technical decisions using embedded decision matrices and trade-off analysis. Use when relevant to the task.

Apply systematic root cause analysis and debugging methodologies to diagnose and fix bugs, test failures, and unexpected behavior. Use when encountering production issues, investigating test failures, diagnosing performance problems, tracing error sources through call stacks, analyzing logs and stack traces, reproducing inconsistent bugs, debugging race conditions, investigating memory leaks, or applying scientific method to problem-solving before proposing fixes.

Systematic and adaptable code review methodology using Language Server Protocol tools. Adapts to available LSP capabilities across programming languages. Use when user asks for code reviews, quality assessments, or specific analysis of codebases in any programming language.

Patterns for data loading, exploration, and statistical analysis

Use when optimizing GraphQL API performance with query complexity analysis, batching, caching strategies, depth limiting, monitoring, and database optimization.

Analyzes competitor SEO and GEO strategies including their ranking keywords, content approaches, backlink profiles, and AI citation patterns. Reveals opportunities to outperform competition.

Analyzes search engine results pages (SERPs) to understand ranking factors, SERP features, user intent patterns, and AI overview triggers. Essential for understanding what it takes to rank.

Performs metacognitive task analysis and skill selection. Use when determining task complexity, selecting appropriate skills, or estimating work scale. Returns skills with confidence scores and metadata.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Parallel codebase search with Warp-Grep MCP. Use for codebase discovery, understanding how things work, data flow analysis, or when the user asks "how does X work" about the codebase.

Run bioinformatics analyses using Lobster AI - single-cell RNA-seq, bulk RNA-seq, literature mining, dataset discovery, quality control, and visualization. Use when analyzing genomics data, searching for papers/datasets, or working with H5AD, CSV, GEO/SRA accessions, or biological data. Requires lobster-ai package installed.