reversa-reconstructor

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

Updated May 22, 2026
One-click install
npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-reconstructor-gleisonoliveira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-reconstructor
Source: https://github.com/GleisonOliveira/dockerpilot-mcp/tree/main/.agents/skills/reversa-reconstructor
Command: npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-reconstructor-gleisonoliveira

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reimplementing software from reverse-engineered specifications is error-prone and token-expensive when done ad hoc. This Skill turns the specs produced by Reversa into an ordered, executable reconstruction plan and implements each task on demand, one at a time, reading only the files each task needs. ## Core Features & Use Cases - Bottom-up plan generation: Builds _reversa_sdd/reconstruction-plan.md from architecture, dependencies, and gap reports, ordering tasks from database schema up to API and user flows. - Migration-aware reconstruction: Detects completed migrations and lets you rebuild either from the original specs or from the target-stack migration specs, including cutover and parity validation tasks. - Token-efficient execution: Each task reads only the files listed in its Lê: field, pauses on spec gaps, and waits for user confirmation before advancing. - Use Case: After running Reversa on a legacy codebase, copy _reversa_sdd/ into a fresh project and invoke the Skill to regenerate the entire system module by module, resuming at any point. ## Quick Start Ask your AI agent to run /reversa-reconstructor in a directory containing the _reversa_sdd folder to generate the plan, then say INICIAR to execute the first 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 Reconstructor in a directory containing the _reversa_sdd folder generated by Reversa. It creates a reconstruction-plan.md with tasks ordered bottom-up from database schema to API layer, then executes one task at a time when you say INICIAR or CONTINUAR.

How to reconstruct software from migration specs instead of original specs?▼

If _reversa_sdd/migration/handoff.md exists, the Skill asks whether to rebuild from original specs or migration specs. Choosing migration generates a plan based on target architecture, data migration plan, cutover plan, and parity tests.

Can I pause and resume a reconstruction plan across sessions?▼

Yes. Task status is persisted in _reversa_sdd/reconstruction-plan.md as pending, in_progress, or done. On the next invocation the Skill reads the plan header and offers to continue from the first pending task or recreate the plan.

What happens when a specification has gaps during reconstruction?▼

Gaps marked in gaps.md or the confidence report become pre-flight alerts tied to specific tasks. During execution, any blocking gap pauses the task and asks the user for a decision before continuing.

What are the prerequisites for running the Reconstructor?▼

The _reversa_sdd directory must exist in the current working directory, produced by running Reversa on the original project. For migration-based reconstruction, the migration must be completed with a handoff.md file present.