reversa-reconstructor

Generates and executes bottom-up reconstruction plans from Reversa specification files.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reimplementing a software system from reverse-engineered specifications is error-prone and token-expensive when done ad hoc. This Skill turns the specs produced by the Reversa framework into an executable, task-by-task reconstruction plan that reads only the files each task needs. ## Core Features & Use Cases - Plan Generation: Reads architecture, dependencies, gaps, and confidence reports from _reversa_sdd/ to produce a bottom-up reconstruction-plan.md ordered by the dependency tree (database schema first, then domain entities, units, API layer, and user flows). - Migration-Aware Reconstruction: Detects completed migrations via _reversa_sdd/migration/handoff.md and lets the user choose between rebuilding from original specs or from target-stack migration specs, using a dedicated migration plan template. - On-Demand Task Execution: Executes one task at a time, reading only the files listed in each task's Lê: field, marking status in the plan, and pausing on spec gaps so work can be resumed at any point. - Use Case: After running Reversa on a legacy codebase, copy _reversa_sdd/ into a fresh repository and invoke this Skill to reimplement the system module by module with full traceability to the specs. ## Quick Start Ask the agent to run /reversa-reconstructor in a directory containing the _reversa_sdd folder, then say INICIAR to execute the first reconstruction task.

Frequently Asked Questions about reversa-reconstructor

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

FAQPage Schema
How do I rebuild a legacy system from reverse-engineered specifications?▼

Run the Reversa framework on the original project to generate the `_reversa_sdd/` specification folder, copy it into a new directory, then invoke this Skill. It creates a bottom-up reconstruction plan ordered by dependencies and executes one task at a time on your command.

How does the reconstruction plan order implementation tasks?▼

Tasks follow a bottom-up order derived from dependencies.md: database schema first, then domain entities, state machines, leaf units, intermediate units, the API layer, and finally user flows. Units with no dependents are always implemented before the units that depend on them.

Can I reconstruct from migration specs instead of the original system specs?▼

Yes. If `_reversa_sdd/migration/handoff.md` exists, the Skill asks whether to rebuild from the original specs or the migration specs targeting the new stack. Migration mode uses target architecture, data model, cutover, and parity test artifacts.

What happens if a specification is incomplete during execution?▼

The Skill pauses and asks the user before continuing whenever it hits a documented gap (🔴 LACUNA). It never invents behavior not present in the specs, and pre-flight alerts from gaps.md and ambiguity_log.md are attached to the affected tasks in the plan.

Can I pause and resume a reconstruction across sessions?▼

Yes. All progress is persisted in `_reversa_sdd/reconstruction-plan.md` with per-task status. On the next invocation the Skill reads the plan header, reports completed and pending tasks, and lets you continue from where you stopped or recreate the plan.