- Home
- Skills
- Agents & Orchestration
- claude-ddd-redesign
Claude Ddd Redesign
Domain-Driven Modernization: re-decompose N services into M bounded-context-aligned services with no unadjudicated behavioral change.
$10
Works with the AI Agents you already use
claude-ddd-redesign
Example session with this skill installed
I need to define a new modernization slice for the Billing service. Create the initial slice outline and size estimation artifacts based on Behaviors BHV-1021 and BHV-1022.
- Read your context and instructions
- Compiled the claude-ddd-redesign
I have initialized the Slice Outline and Size estimation artifacts for the new Billing modernization slice. These files are grounded in the provided Behavior IDs and follow the Stage 3 schema requirements.
Modernization Slice: SLC-0042 (Billing)
slices/SLC-0042/slice.json
{
"id": "SLC-0042",
"workstream": "WS-0005",
"oracle_strategy": "characterization",
"behaviors": ["BHV-1021", "BHV-1022"],
"state": "draft"
}
slices/SLC-0042/size.json
{
"slice": "SLC-0042",
"behaviors": 2,
"interfaces_sync": 1,
"interfaces_async": 0,
"complexity_factors": [
"cross-service-invariant-validation"
]
}
Next steps
- Review the behavior citations to ensure
BHV-1021andBHV-1022cover all necessary billing invariants. - Define the
acceptance-criteria.jsonfor this slice to map specific assertions to these behaviors. - Update the
roadmap.jsonto include this slice in the next delivery increment.
Connects securely to your tools. The creator never sees your data.
About this skill
Modernizing legacy monoliths into distributed services often fails due to behavior drift and untraceable requirements. This skill package provides a rigorous, schema-driven framework for Domain-Driven Design (DDD) redesign, ensuring every service boundary is grounded in observed behavior rather than guesswork.
What it does
- Inventories behavior by extracting and classifying atomic facts from legacy code to maintain functional parity.
- Models domains using strategic context maps and tactical aggregate models to define strict service boundaries.
- Automates traceability by linking acceptance criteria and characterization tests directly to specific behavior IDs.
- Manages migration through structured cutover plans, retirement registers, and multi-team migration waypoints.
- Formalizes decisions using Architecture Decision Records (ADRs) and human-adjudicated consensus runs.
How it works
- Initialize the inventory by running discovery agents to populate
behavior.jsonandinterfaces.jsonfrom the legacy source. - Draft the model using
contexts.jsonto define bounded contexts anddivergences.jsonto flag conceptual conflicts between services. - Sequence delivery by creating a
roadmap.jsonthat prioritizes the walking skeleton and manages capacity constraints. - Define slices for incremental modernization, generating
tactical-model.jsonanddesign.mdfor each deployable unit. - Execute transition following the
cutover-plan.jsonsteps from shadow mode through to final decommissioning.
Frameworks & tools
This tool uses JSON Schema for all artifact validation. It integrates with Python-based linting scripts like trace-lint.py and resolve-identity.py.
Why this beats prompting it yourself
Generic prompts fail to maintain the strict traceability required for high-stakes refactoring. This skill enforces a schema-valid "spine" that connects legacy behavior to new implementation, preventing the silent loss of edge-case logic during service extraction.
Use cases
- Decomposing a monolithic Java or .NET application into Bounded Contexts.
- Identifying and resolving domain logic divergences across different business units.
- Managing long-running consumer migrations during interface retirement.
- Generating a verifiable characterization suite for legacy system replacement.
Known limitations
Does not automate behavior extraction; relies on external discovery agents and manual review. Requires a human decider for all architectural adjudications.
Requires human adjudication for all boundary decisions. Does not perform automated code extraction; operates on the metadata layer via provided JSON schemas.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires