What problem does it solve? Reverse-engineering a legacy system produces scattered knowledge that is hard to act on. This Skill converts extracted legacy knowledge into formal, traceable specifications organized as one folder per unit, each containing requirements.md, design.md, and tasks.md, so an AI agent can reimplement functionality without access to the original code. ## Core Features & Use Cases - Folder-per-unit spec generation: Creates requirements.md, design.md, and tasks.md per unit, with granularity driven by config (module, endpoint, use-case, hybrid, feature, or custom). - Confidence-tagged traceability: Marks every statement as confirmed, inferred, or a gap, and links tasks and requirements back to legacy source files and line numbers. - 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 codebase, use this Skill to produce a complete specification tree, including optional contracts, OpenAPI definitions, user stories, and a code-to-spec traceability matrix. ## Quick Start Ask the agent to run the reversa-writer generation phase to produce the specification folders for all units identified in the prior reverse-engineering analysis.
