What problem does it solve? Turning knowledge extracted from a legacy codebase into formal, traceable specifications is slow and inconsistent. This Skill converts reverse-engineering findings into operational contracts that an AI agent could use to reimplement the system 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: Every claim is marked as confirmed, inferred, or a gap, and each task cites the legacy source file it was derived from. - Incremental, checkpointed workflow: Generates one file at a time with user confirmation, saves progress to state.json, and suggests preventive pauses on long sessions. - Use Case: After scanning a legacy monolith with the Reversa framework, use this Skill to produce a complete spec tree including OpenAPI definitions, user stories, and a code-to-spec traceability matrix. ## Quick Start Ask the agent to generate the executable specifications for the analyzed legacy system following the granularity defined in the reversa config.
