reversa-migrate

Orchestrates a six-agent pipeline that converts legacy system specs into migration-ready specifications.

Updated Jun 12, 2026
One-click install
npx skills add https://github.com/lacsousa/mediclaw-system --skill reversa-migrate-lacsousa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-migrate
Source: https://github.com/lacsousa/mediclaw-system/tree/main/.agents/skills/reversa-migrate
Command: npx skills add https://github.com/lacsousa/mediclaw-system --skill reversa-migrate-lacsousa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Planning a legacy system migration requires coordinating many decisions—paradigm choice, business rule curation, strategy, architecture, screen translation, and parity validation. This Skill orchestrates that entire pipeline after the /reversa discovery step has populated _reversa_sdd/, so no decision is skipped or lost. ## Core Features & Use Cases - Six-Agent Pipeline: Sequentially invokes Paradigm Advisor, Curator, Strategist, Designer, Screen Translator, and Inspector, each producing versioned artifacts in _reversa_sdd/migration/. - Human Decision Gates: Pauses after each agent with summaries and explicit decision points, with resumable state tracked in .state.json and support for --resume, --regenerate, and --auto modes. - Handoff Generation: Consolidates ambiguity logs and produces a handoff.md that tells a coding agent exactly what to read first and how to implement the new system. - Use Case: After running /reversa on a legacy COBOL or monolith codebase, invoke /reversa-migrate to interview stakeholders, decide the target paradigm and topology, plan data migration and cutover, and hand off parity-tested specs to a coding agent. ## Quick Start Run /reversa-migrate after /reversa has populated _reversa_sdd/ to start the guided migration pipeline for my legacy system.

Frequently Asked Questions about reversa-migrate

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

FAQPage Schema
How do I plan a legacy system migration with AI agents?▼

Run the /reversa discovery step first to generate specs in _reversa_sdd/, then invoke /reversa-migrate. It interviews you for a migration brief, then runs six specialized agents covering paradigm selection, business rule curation, strategy, architecture, screen translation, and parity validation.

What artifacts does a legacy migration pipeline produce?▼

The pipeline produces a migration brief, paradigm and topology decisions, target architecture and data models, a data migration plan, screen modernization specs, parity test features, a risk register, a cutover plan, an ambiguity log, and a final handoff.md for the coding agent.

Can I resume an interrupted migration pipeline?▼

Yes. State is persisted in _reversa_sdd/migration/.state.json after every checkpoint. Use --resume to continue from the last agent, or --regenerate=<agent> to redo a specific agent and all downstream artifacts with automatic backup.

Does the migration pipeline work without human approval steps?▼

Yes, via the explicit --auto mode, which applies documented defaults for each decision gate and logs every auto-decided item in ambiguity_log.md for later review. It always displays the full list of defaults and asks for confirmation before starting.

What happens if the legacy system has no user interface?▼

The Screen Translator agent detects the absence of UI and completes with status skipped, recording the justification in ambiguity_log.md. The pipeline continues to the Inspector without a screen-related pause, and handoff.md notes that no screens exist.