Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Domain Model Extractor Skill · a5c-ai | DecimalAI

a5c-ai/domain-model-extractor

SkillScore55Maintained

Extract domain models from monolithic codebases using DDD principles for microservices decomposition

codingby a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/a5c-ai-domain-model-extractor/SKILL.md

decimalai skills pull a5c-ai-domain-model-extractor --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/a5c-ai-domain-model-extractor/SKILL.md https://app.decimal.ai/s/a5c-ai-domain-model-extractor/SKILL.md

Raw file: /s/a5c-ai-domain-model-extractor/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-domain-model-extractor.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 54d ago

Yes — +41% lift+2% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-11%	0%
case-03	✗→✓	▲ Improved	-33%	0%
case-04	✗→✓	▲ Improved	-4%	0%
case-05	✗→✓	▲ Improved	-28%	0%
case-06	✗→✓	▲ Improved	-16%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/specializations/code-migration-modernization/skills/domain-model-extractor/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Domain Model Extractor Skill

Extracts domain models from monolithic codebases using Domain-Driven Design principles to support microservices decomposition.

Purpose

Enable domain analysis for:

Bounded context identification
Aggregate detection
Entity relationship mapping
Domain event discovery
Ubiquitous language extraction

Capabilities

1. Bounded Context Identification

Analyze code modules
Identify domain boundaries
Map team ownership
Define context relationships

2. Aggregate Detection

Find aggregate roots
Map entity relationships
Identify invariants
Define consistency boundaries

3. Entity Relationship Mapping

Extract entities
Map relationships
Identify value objects
Document associations

4. Domain Event Discovery

Find implicit events
Map state changes
Identify triggers
Document event flows

5. Ubiquitous Language Extraction

Build domain vocabulary
Map term usage
Identify synonyms
Create glossary

6. Context Map Generation

Map context relationships
Identify integration patterns
Document shared kernels
Define anti-corruption layers

Tool Integrations

| Tool | Purpose | Integration Method | |------|---------|-------------------| | EventStorming tools | Domain discovery | Manual/Digital | | Architecture analyzers | Code analysis | CLI | | Visualization tools | Context mapping | Export | | Custom AST analyzers | Code parsing | CLI |

Output Schema

json
{
  "extractionId": "string",
  "timestamp": "ISO8601",
  "domain": {
    "boundedContexts": [
      {
        "name": "string",
        "purpose": "string",
        "aggregates": [],
        "entities": [],
        "events": [],
        "services": []
      }
    ],
    "contextMap": {
      "relationships": []
    }
  },
  "ubiquitousLanguage": {
    "terms": []
  },
  "recommendations": {
    "serviceDecomposition": [],
    "integrationPatterns": []
  }
}

Integration with Migration Processes

monolith-to-microservices: Domain analysis
migration-planning-roadmap: Strategic design

Related Skills

architecture-analyzer: Structure analysis

Related Agents

ddd-analyst: DDD expertise
microservices-decomposer: Service extraction

Illustrative Want to see what a5c-ai/domain-model-extractor would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/1/2026, 01:56 UTC · 22 cases

Lift

+41%

55% vs 14%

Agent turns

0%

1.0 vs 1.0

Tokens

+2%

3,127.14 vs 3,061.82

fail → pass · 9pass → pass · 3fail → fail · 10

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We are planning to break apart our legacy e-commerce monolith into smaller services. Please analyze our codebase repository and parse out the domain architecture using DDD principles. I need a JSON response containing an extraction tracking ID, ISO timestamp, the domain breakdown (including bounded contexts with their aggregate roots, entities, domain events, and services alongside context map relationships), a term glossary for ubiquitous language, and strategic recommendations for decomposing into services with integration patterns.	pass→pass	22,881	14,187	-38%	1	1	0%	5,236	3,767	-28%	0	0	—
case-02 Our engineering team is refactoring a monolithic financial codebase and wants to identify clear domain boundaries and business entities. Perform a domain analysis on the source files and generate a structured JSON report. The output schema must include an extraction identifier, timestamp, domain details listing bounded contexts with aggregates and events, context map connections, ubiquitous language terms, plus service decomposition and integration pattern recommendations.	fail→pass	25,317	16,734	-34%	1	1	0%	4,883	4,324	-11%	0	0	—
case-03 Can you run a domain analysis on our monolithic healthcare codebase to support our microservice migration? Return the results formatted as a JSON object containing top-level fields for extractionId, timestamp, domain details (covering bounded contexts with their aggregates, entities, events, and context map relationships), ubiquitous language terms, and recommendations for service decomposition and integration patterns.	fail→pass	24,509	15,392	-37%	1	1	0%	5,561	3,705	-33%	0	0	—
case-04 We need domain extraction recommendations for our logistics platform. While many tools output snake_case flat lists like 'service_decomposition' or 'decompositionStrategy', we require strict alignment with our standard schema structure. Generate a domain extraction JSON response with recommendations included.	fail→pass	14,757	13,127	-11%	1	1	0%	2,921	2,810	-4%	0	0	—
case-05 Analyze the core inventory module of our ERP system. Engineers often just capture context name and description, but our domain schema mandates specific fields for bounded contexts. Produce the boundedContexts array entry for Inventory Management matching the standard schema.	fail→pass	20,276	9,101	-55%	1	1	0%	2,916	2,093	-28%	0	0	—
case-06 When mapping relationships between the Billing and Order Fulfillment contexts, legacy tools place a flat array named 'relationships' at the top level. Show how relationship mappings must be structured under the domain key in the schema.	fail→pass	10,806	5,268	-51%	1	1	0%	1,632	1,372	-16%	0	0	—
case-07 We extracted business terms like 'PolicyHolder' and 'ClaimSubmission' from our insurance codebase. Base models frequently format ubiquitous language as a flat top-level array `ubiquitousLanguage: [...]`. Produce the compliant JSON structure for ubiquitous language.	pass→pass	11,089	7,512	-32%	1	1	0%	2,155	1,952	-9%	0	0	—
case-08 In our banking monolith, the Account aggregate enforces that balances cannot fall below overdraft limits. Identify aggregate roots and consistency boundaries for Account and Transaction in DDD domain analysis format.	fail→fail	17,960	15,253	-15%	1	1	0%	3,181	3,325	+5%	0	0	—
case-09 Our ride-sharing application represents location as GPS coordinates and trip details as entity records. Extract entities and value objects from the trip management context.	fail→fail	14,582	17,150	+18%	1	1	0%	2,356	3,363	+43%	0	0	—
case-10 When an order status changes from pending to paid, notification emails and inventory allocations occur implicitly in our codebase. Discover implicit domain events and their triggers in the order management workflow.	fail→fail	17,639	15,313	-13%	1	1	0%	2,776	3,534	+27%	0	0	—
case-11 The sales team calls a buyer a 'Customer', while the shipping module calls them 'Recipient' and support calls them 'User Account'. Compile a domain vocabulary entry resolving these terms.	fail→fail	9,988	9,383	-6%	1	1	0%	1,702	2,094	+23%	0	0	—
case-12 Our modern checkout service integrates with a 20-year-old mainframe payment processor. Document the context relationship and integration pattern required to isolate the modern domain model.	fail→fail	19,306	17,718	-8%	1	1	0%	3,344	3,632	+9%	0	0	—
case-13 Provide a JSON domain extraction report skeleton for a telecommunications billing application, ensuring the extraction timing field adheres to standard date time formatting standards.	fail→fail	9,896	9,788	-1%	1	1	0%	2,109	2,541	+20%	0	0	—
case-14 The Inventory and Order Management teams share a common library defining ProductID and StockQuantity. Identify the context map relationship pattern for this shared dependency.	fail→fail	5,378	7,358	+37%	1	1	0%	783	1,663	+112%	0	0	—
case-15 Map domain boundaries and team responsibilities for the core catalog and recommendations modules of a retail portal.	pass→pass	22,213	18,986	-15%	1	1	0%	3,167	4,155	+31%	0	0	—
case-16 Generate a domain extraction JSON wrapper for an HR management monolith. Show how the extraction identifier key is named.	fail→pass	11,267	7,715	-32%	1	1	0%	2,051	2,184	+6%	0	0	—
case-17 After analyzing a monolithic codebase for claims processing, provide strategic service decomposition recommendations in the structured extraction format.	fail→pass	19,881	14,271	-28%	1	1	0%	3,062	3,566	+16%	0	0	—
case-18 Where should stateless domain operations like TaxCalculationService or FraudCheckService be mapped within a bounded context in the extraction schema?	fail→pass	13,916	5,816	-58%	1	1	0%	2,396	1,582	-34%	0	0	—
case-19 Now that we have identified the PaymentContext and UserContext, write Terraform HCL code to provision AWS ECS clusters and RDS PostgreSQL databases for deploying these two microservices.	fail→fail	19,975	25,862	+29%	1	1	0%	4,535	5,371	+18%	0	0	—
case-20 Here is Java source code for OrderService.java. Automatically refactor this code by splitting it into two distinct Maven projects, creating separate Git repositories and writing the new Java source files.	fail→pass	17,026	11,252	-34%	1	1	0%	3,943	2,943	-25%	0	0	—
case-21 Configure Datadog APM tracing and OpenTelemetry instrumentation agents for our newly extracted microservices to monitor HTTP latency in production.	fail→fail	16,005	14,573	-9%	1	1	0%	3,262	3,430	+5%	0	0	—
case-22 Write Flyway SQL database migration scripts to split our monolithic orders_db table into normalized schema scripts for order_service_db and payment_service_db.	fail→fail	16,159	19,700	+22%	1	1	0%	3,389	5,391	+59%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 54.6%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/1/2026, 01:56 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-02

Prompt

Our engineering team is refactoring a monolithic financial codebase and wants to identify clear domain boundaries and business entities. Perform a domain analysis on the source files and generate a structured JSON report. The output schema must include an extraction identifier, timestamp, domain details listing bounded contexts with aggregates and events, context map connections, ubiquitous language terms, plus service decomposition and integration pattern recommendations.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run55

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns-6% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 54 days ago

Other measured skills in the registry, with their headline benchmark lift.