research-to-decision 是做什麼的？
將研究轉化為可追溯的技術或產品決策：定義決策與限制條件、蒐集有來源的證據、區分證據與假設、依據明確標準比較方案，並產出 ADR。適用於在技術或方法之間做選擇時（例如「Kafka vs SQS」、「自建 vs 採購」）、記錄已做出決策背後的推理過程，或是被要求「研究此主題並推薦一個方案」時使用。請勿用於實作所選方案（那是另一個技能），或是進行沒有明確決策結尾的開放式研究。
將研究轉化為可追溯的技術或產品決策：定義決策與限制條件、蒐集有來源的證據、區分證據與假設、依據明確標準比較方案，最終產出 ADR。
此技能「alphasafal/research-to-decision」旨在協助開發者或產品經理將研究結果轉化為結構化、可稽核的技術或產品決策。它能自動定義決策範疇與限制條件，從多方來源蒐集證據，並清楚區分實證與假設。透過明確的評估標準比較不同方案（例如「Kafka vs SQS」或「自建 vs 採購」），最終產出標準的架構決策記錄（ADR），讓決策過程透明且易於追溯。此技能適用於需要從技術方案中做出選擇、為已做出的決策補齊原因文件，或是被要求「研究此主題並推薦一個方案」的情境。它支援多種 AI 代理人平台（如 Claude Code、Cursor、Codex），並透過 markdown 格式的 SKILL.md 文件定義其行為與使用準則。請注意，此技能不應用於實作所選方案（那是另一個技能），也不適合進行無明確決策結尾的開放式研究。
npx skills add https://github.com/alphasafal/production-agent-skills/tree/main/skills/research-to-decision將研究轉化為可追溯的技術或產品決策：定義決策與限制條件、蒐集有來源的證據、區分證據與假設、依據明確標準比較方案，並產出 ADR。適用於在技術或方法之間做選擇時（例如「Kafka vs SQS」、「自建 vs 採購」）、記錄已做出決策背後的推理過程，或是被要求「研究此主題並推薦一個方案」時使用。請勿用於實作所選方案（那是另一個技能），或是進行沒有明確決策結尾的開放式研究。
This repo contains 7 individual skills — each has its own dedicated page.
Runs an end-to-end structured tabular data science workflow: problem framing, schema/leakage/missingness checks, EDA, baseline before modeling, feature engineering, model comparison against the baseline, and error/slice analysis. Use when asked to analyze a dataset, build a predictive model, evaluate a model's performance, or investigate a data quality issue in tabular data. Do not use for pure data engineering/ETL with no analysis or modeling question, for unstructured data (images/audio/free text at scale) without a tabular framing, or when the task is answerable by a single summary statistic with no need for the full workflow — say so and just answer it.
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.
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".