What problem does it solve? Reverse-engineering a legacy system into formal, traceable specifications is slow and inconsistent when done by hand. This Skill turns extracted knowledge about a legacy codebase into operational contracts that an AI agent could use to reimplement the system faithfully, without access to the original code. ## Core Features & Use Cases - Folder-per-unit spec generation: Creates requirements.md, design.md, and tasks.md for each unit, with the unit definition driven by configurable granularity (module, endpoint, use-case, hybrid, feature, or custom). - Confidence-tagged traceability: Marks every statement as confirmed, inferred, or a gap, and produces a code-to-spec traceability matrix plus optional OpenAPI and user-story artifacts. - Incremental, checkpointed workflow: Generates one file at a time with user confirmation, saves progress to state.json, and supports pause-and-resume across sessions. - Use Case: After running the earlier Reversa analysis phases on a legacy monolith, invoke this Skill to produce a complete specification tree where each module gets requirements, design, and implementation tasks linked back to the original source files. ## Quick Start Ask the agent to run the reversa-writer generation phase to produce the specification units from the existing Reversa analysis artifacts.
