執行端到端的結構化表格資料科學工作流程：問題框架、綱要/資料洩漏/缺失值檢查、探索性資料分析、建模前的基線建立、特徵工程、模型與基線比較，以及錯誤/切片分析。
此技能專為結構化表格資料設計，提供完整的資料科學工作流程，涵蓋從問題定義、資料品質檢查（如綱要驗證、資料洩漏與缺失值分析）、探索性資料分析（EDA）到建立基線模型、特徵工程、模型比較與後續的錯誤/切片分析。其核心價值在於自動化繁瑣但關鍵的資料科學步驟，確保在建立預測模型或分析資料集時，不會遺漏重要環節。支援的平台包括 AI 代理程式（如 Claude Code、Cursor、Codex 等），並嚴格限制使用情境：僅適用於明確的資料分析或建模請求，對於純資料工程/ETL、非結構化資料（如大規模圖片、音訊或自由文字）或只需單一統計摘要即可回答的問題，技能會主動拒絕並直接給出答案。透過系統化的步驟，幫助開發者與資料科學家提升工作效率與結果品質。
npx skills add https://github.com/alphasafal/production-agent-skills/tree/main/skills/data-scientist執行端到端的結構化表格資料科學工作流程：問題框架、綱要/資料洩漏/缺失值檢查、探索性資料分析（EDA）、建模前的基線建立、特徵工程、模型與基線比較，以及錯誤/切片分析。當使用者要求分析資料集、建立預測模型、評估模型效能或調查表格資料中的資料品質問題時使用。
請勿在以下情況使用：純資料工程/ETL 且無分析或建模問題、非結構化資料（大規模圖片/音訊/自由文字）且無表格化框架、或任務可透過單一統計摘要回答而不需完整工作流程時—此時應主動說明並直接回答該問題。
This repo contains 7 individual skills — each has its own dedicated page.
Agent skill 'debugging-investigator' from alphasafal/production-agent-skills.
Agent skill 'feature-to-production' from alphasafal/production-agent-skills.
Agent skill 'production-code-review' from alphasafal/production-agent-skills.
Agent skill 'product-manager' from alphasafal/production-agent-skills.
Agent skill 'repo-architect' from alphasafal/production-agent-skills.
Turns research into an auditable technical or product decision: defines the decision and constraints, gathers evidence with sources, separates evidence from assumption, compares alternatives against explicit criteria, and produces an ADR. Use when choosing between technologies/approaches ("Kafka vs SQS", "build vs buy"), documenting the reasoning behind a decision already made, or when asked to "research this and recommend one." Do not use for implementing the chosen option (that's a separate skill), or for open-ended research with no decision to make at the end.
Agent skill 'system-design-reviewer' from alphasafal/production-agent-skills.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".