MSFT-AI-BUILD-INTERNAL

Parse and analyze Excel (.xlsx) files using the project's parse_excel.py tool

Parse and analyze PowerPoint (.pptx) files using the project's parse_ppt.py tool

Reference project data files (Excel, CSV, JSON, etc.) in each project's data/ folder before starting work

파일 기반 세션 상태 관리 라이프사이클. 패턴 에이전트(debate_critic, generator_evaluator, planner_executor, leadership)가 세션 상태를 영속화하고 중단된 세션을 복구할 때 사용한다.

Use when the user asks for a code review, asks to find bugs, asks about code quality, or pastes code and asks for feedback. Performs a structured, high-signal review focused on correctness, security, and maintainability.

Use when the user reports an outage, a failing deployment, a CI/CD pipeline error, or a production incident, or asks how to debug Azure / Docker / FastAPI / nginx problems. Drives a structured incident-response workflow.

Use when the user writes or modifies code that handles authentication, secrets, user input, file uploads, HTTP requests, SQL/NoSQL queries, or anything touching credentials. Surfaces concrete security risks and remediations.

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.