reversa-writer

Generates executable reverse-engineering specifications as per-unit folders with requirements, design, and tasks files.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-writer-helcio-nogueira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-writer
Source: https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026/tree/main/.agents/skills/reversa-writer
Command: npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-writer-helcio-nogueira

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reverse-engineered knowledge about legacy systems often stays scattered and informal, making it impossible to reimplement features faithfully. This Skill turns extracted legacy knowledge into formal, traceable operational contracts organized as folder-per-unit specifications. ## Core Features & Use Cases - Folder-per-unit spec generation: Creates requirements.md, design.md, and tasks.md for each 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 produces a code-to-spec coverage 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 suggests session breaks to preserve quality on large projects. - Use Case: After analyzing a legacy codebase with the Reversa pipeline, run this Skill to produce a complete specification set that an AI agent could use to reimplement each module without seeing the original code. ## Quick Start Ask the agent to generate the specification plan for the legacy project using the reversa-writer skill, then type CONTINUAR to produce each file step by step.

Frequently Asked Questions about reversa-writer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate specifications from a legacy codebase analysis?▼

Run this Skill after the earlier Reversa phases have produced state.json and surface.json. It builds a generation plan listing every unit and file, waits for your confirmation, then writes requirements.md, design.md, and tasks.md one file at a time.

What granularity options exist for organizing reverse engineering specs?▼

Six modes are supported: module, endpoint, use-case, hybrid, feature, and custom. The mode is set in the [specs] section of config.toml, and units are enumerated from surface.json modules, routes, Gherkin specs, or user-defined folders.

Can it generate OpenAPI definitions and traceability matrices?▼

Yes, but only when doc_level is set to completo or detalhado. It then produces openapi/<api>.yaml, user-stories files, and a traceability/code-spec-matrix.md mapping legacy files to units with coverage indicators.

Does the skill overwrite existing specification files?▼

No. It follows a non-destructive directive: existing unit folders are kept, missing files are added, and pre-existing canonical files are left untouched with a notice to the user.

Why does generation pause after each file instead of producing everything at once?▼

Generating all units in one response consumes excessive context and lowers quality on large projects. The one-file-at-a-time flow with checkpoints in state.json allows review, interruption, and safe resumption in a new session.