skills.rest
GleisonOliveira
GleisonOliveiraCOMMUNITY
Explore all skills by this author →
Website𝕏@classefinalGitHub

reversa-migrate

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

Updated May 22, 2026
Search Tags:#spec-driven#modernization#multi-agent#orchestration#pipeline#handoff#legacy migration
One-click install
npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-migrate-gleisonoliveira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-migrate
Source: https://github.com/GleisonOliveira/dockerpilot-mcp/tree/main/.agents/skills/reversa-migrate
Command: npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-migrate-gleisonoliveira

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Rebuilding a legacy system on a modern stack requires coordinated decisions about paradigm, architecture, data, screens, and parity testing. This Skill orchestrates that entire migration planning pipeline, turning the specs produced by a prior reverse-engineering pass into a complete, human-approved handoff package for a coding agent. ## Core Features & Use Cases - Six-Agent Migration Pipeline: Sequentially invokes Paradigm Advisor, Curator, Strategist, Designer, Screen Translator, and Inspector, each producing versioned artifacts in _reversa_sdd/migration/. - Human Decision Gates with State Recovery: Pauses for approval after each agent, tracks progress in .state.json, and supports --resume, --regenerate=<agent>, and per-phase regeneration for the Designer and Screen Translator. - Auto Mode and Handoff Generation: An explicit --auto mode applies documented defaults with logging, and the pipeline ends with a consolidated ambiguity_log.md and a handoff.md that tells the coding agent exactly what to read and build first. - Use Case: After running /reversa on a legacy COBOL or monolith system to populate _reversa_sdd/, invoke /reversa-migrate to interview stakeholders, decide the target paradigm and topology, plan data migration and cutover, and deliver parity test specs to the team rebuilding the system. ## Quick Start Run the reversa-migrate skill after /reversa has populated _reversa_sdd/ to start the migration interview and execute the six-agent pipeline with approval pauses.

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-migrate skill after a discovery pass has populated the _reversa_sdd/ directory. It interviews you for a migration brief, then runs six specialized agents covering paradigm selection, business rule curation, strategy, architecture, screen translation, and parity testing, with human approval pauses between steps.

What artifacts does a legacy migration pipeline produce?▼

The pipeline writes everything into _reversa_sdd/migration/, including migration_brief.md, paradigm_decision.md, topology_decision.md, target_architecture.md, data_migration_plan.md, cutover_plan.md, parity_specs.md with feature test files, a consolidated ambiguity_log.md, and a final handoff.md for the coding agent.

Can I resume an interrupted migration pipeline?▼

Yes. Progress is tracked in _reversa_sdd/migration/.state.json, which records completed agents, the current agent's phase and status, and artifact hashes. Invoking with --resume continues from the last checkpoint, including re-presenting any pending human approval pause.

Does reversa-migrate work without the reversa discovery step?▼

No. The skill verifies that _reversa_sdd/ exists and that all required artifacts listed in expected_legacy_artifacts.yaml are present, including code-analysis.md, domain.md, architecture.md, dependencies.md, inventory.md, gaps.md, and confidence-report.md. If any are missing, it aborts and asks you to run /reversa first.

What does the --auto mode do in a migration pipeline?▼

The --auto flag skips human pauses and applies documented defaults, such as adopting the target stack's natural paradigm, the recommended strategy, and the proposed modern topology. Every auto-applied decision is tagged in ambiguity_log.md and listed in handoff.md for later human review.

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

The Screen Translator agent detects the absence of UI and completes with status skipped, producing no screen artifacts. The orchestrator records the justification in ambiguity_log.md, omits screen decisions from the handoff reading list, and continues the pipeline normally.

Related Skills

Explore More Software Engineering Skills→
MarunionMarunion

reverse

Reverse-engineer codebases to generate spec.md and arch.md documentation.

Community
Advanced
Marcu-LoretoMarcu-Loreto

reversa-inspector

Generate parity specifications and Gherkin feature files for system migrations.

Community
Advanced
DauQuangThanhDauQuangThanh
14

application-migration

Plan and manage application migrations from legacy systems to modern platforms.

Community
Advanced
EmeaAppGbbEmeaAppGbb

rewrite-planner

Plan component-by-component rewrites using the Strangler Fig pattern.

Official
Advanced