Understand 기존 소프트웨어. 재건축 계획. 요청시 빌드 및 유효성.

오픈 소스, REA와 함께 작동하는 모델에 의존하는 에이전트 기술. 요구 사항, 건축, 구현 로드맵 및 테스트 가능한 결과에 대한 역설계 증거를 켭니다.

시작 · 사용 예제 · REA 통합 · 문서 · 릴리즈 · Ko-fi 지원

| 목표 | 동료가 생산하는 것은 무엇 | 인포메이션 | 재건축하기 전에 앱 이해 | Evidence-backed behavior, requirements, unknowns and staged Roadmap. | | 지금 유사한 도구를 구축 | 검증 및 보고된 차이를 가진 테스트 가능한 증가에 대한 Scoped 구현. · | 특징, 기능, 형식을 조사 | 초점 계약 및 대표 수용 사례. · | 기존 재건축 개선 | 측정, 타겟 변경 및 영향을받는 행동의 재발견. |

**** 아래 설치 프롬프트로 시작하거나 수동 명령을 사용하십시오. 휴대용 코어에는 모델 SDK 또는 유료 API 요구 사항이 없습니다. 통합 및 주간 업데이트 체크는 별도의 선택입니다. 둘 다 설정하기 전에 설명됩니다.

AI 에이전트 설치

REA-Reconstruction-Companion

Understand existing software. Plan a reconstruction. Build and validate when requested.

An open-source skill for AI agents, designed to work with REA. A skill is a set of instructions and reference guides that an agent reads while working. This one helps you understand existing software and turn what you learn into a plan, a working reconstruction when requested, and checks of the result. It does not require a particular model or AI provider.

What it does · Get started · Use · Integration · Updates and recovery · Topic guides · Development

What the companion does

Use the companion when you want to understand how software behaves, plan a similar tool, rebuild a selected part, or improve a reconstruction you already have. The scope can be a whole app, one workflow, a file format, or a single function.

• Understand: turn observations, files or recordings into a clear description of behavior, requirements and unanswered questions. For example, find out what an editor keeps when a save fails.
• Plan: decide what to build first, what it depends on and how to check it. A specification describes the behavior to preserve; a reconstruction plan describes the steps for building it.
• Build when requested: implement the selected behavior in useful, testable steps. Asking to investigate or plan a possible future rebuild does not authorize implementation now.
• Validate and improve: compare results with the evidence, test relevant failures and measure proposed performance improvements. Report differences and anything still unverified.

REA supplies the tools for examining software and collecting evidence. The companion helps the same agent use that evidence for requirements, design, implementation and validation. Installing both does not create two independent background agents. You can also start from supplied REA evidence when live tools are unavailable.

Observed behavior, reasonable inferences and proposed design choices stay separate. Missing evidence remains a gap; neither a plausible reconstruction nor a passing local example proves that it matches every part of the original.

• Identifies the requested subject, evidence carrier, and objective from natural language. No form or bracketed prompt variables are required.
• Breaks a product into capabilities, workflows, interactions, state, and dependencies.
• Defines requirements, contracts, expected behavior, and acceptance criteria linked to evidence.