Ready to supercharge your AI agents?

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

Domain Modeling · rsmdt | DecimalAI

codingby rsmdt

Domain Modeling

rsmdt/domain-modeling

Source rsmdt/the-startup ↗License MIT

Unified domain and data modeling for business entities, invariants, schema design, aggregate boundaries, and evolution strategy.

NewMaintained

Automatic

Coding pack

Last verified 8/30/2026

What it changes

Passed 6 of 22 test cases with the skill, and 17 of 22 without it.

Without skill75%

With skill25%

Checks it passed that the model alone missed

The response includes a distinct valueObjects section.
The response structures output using the top-level keys of the DomainModel interface.

1 fixed18 passed either way0 still failing3 broke

Pass-rate lift: -50 pp
Tokens: 0%
Agent turns: 0%
Response time: -9%

Model gemini-3.6-flashMeasured 8/30/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/rsmdt-domain-modeling/SKILL.md https://app.decimal.ai/s/rsmdt-domain-modeling/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rsmdt-domain-modeling, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/rsmdt-domain-modeling/ and pins it in .decimal/skills.lock

decimalai skills add rsmdt-domain-modeling

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

curl -fsSL --create-dirs -o .claude/skills/rsmdt-domain-modeling/SKILL.md https://app.decimal.ai/s/rsmdt-domain-modeling/SKILL.md

Raw file: /s/rsmdt-domain-modeling/SKILL.md ↗ · machine-readable summary at /s/rsmdt-domain-modeling.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

We are re-architecting our warehouse fulfillment service to handle multi-warehouse inventory tracking, reservation holds, and shipment dispatching. Please analyze this domain target and provide a domain model that outlines the bounded contexts, main entities, value objects, aggregates, invariants, data persistence strategy, concrete schema decisions, and an evolution migration plan.

What was checked, without and with the skill
Checked	Without skill	With skill
The response includes a distinct valueObjects section.	Missed	Passed
The response structures output using the top-level keys of the DomainModel interface.	Missed	Passed

case-01 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md66 linessingle file

Persona

Act as a domain-modeling specialist who aligns business concepts, data structures, and consistency boundaries into an implementation-ready model.

Modeling Target: $ARGUMENTS

Interface

DomainModel { boundedContexts: string[] entities: string[] valueObjects: string[] aggregates: string[] invariants: string[] persistenceStrategy: string schemaDecisions: string[] migrationPlan: string[] }

State { target = $ARGUMENTS concepts = [] constraints = [] model = {} }

Constraints

Always:

Model business rules before table/field mechanics.
Define aggregate boundaries around consistency and transactional requirements.
Make invariants explicit and enforceable.
Choose schema patterns based on query and write behavior.
Include schema/version evolution strategy for non-trivial changes.

Never:

Let storage convenience override domain correctness.
Introduce cross-aggregate transactions without clear necessity.
Add denormalization/caching without read/write rationale.

Track record

Benchmark

6 / 22

test cases passed, vs 17 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

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

rsmdt / the-startup

plugins/team/skills/development/domain-modeling/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.