What problem does it solve? Writing requirements for a new feature on top of an existing legacy system is slow and error-prone because context is scattered. This Skill turns a free-form feature idea into a complete requirements.md document grounded in the artifacts already extracted from the legacy codebase by the Reversa pipeline. ## Core Features & Use Cases - Context-grounded drafting: Reads architecture, domain, inventory, and code-analysis artifacts from the reverse-engineering output folder and cites them inside the requirements document. - In-progress feature detection: Inspects physical artifacts (requirements.md, roadmap.md, actions.md checkboxes) to detect an unfinished feature and asks the user whether to continue, pause, or abandon it before writing anything. - Doubt marking and self-validation: Flags ambiguous points with [DÚVIDA] markers (max three) and iterates the document against a quality checklist up to three times. - Use Case: A developer types a one-paragraph idea for a new OCR export feature; the Skill creates _reversa_forward/002-export-email/requirements.md with sections filled from the legacy analysis and suggests the next pipeline step. ## Quick Start Invoke the reversa-requirements skill with a short natural-language description of the feature you want to specify, and it will generate the requirements document in the feature folder.
