Skip to main content
Agent skill

Tsp Model

Use when creating, modifying, or documenting TypeSpec domain models. Triggers include adding new entities, value objects, enums, extending base types, or when asked to create a "tsp model", "domain model", "entity", or work with files in the tsp/ directory. Part of the Shep autonomous SDLC platform — https://shep.bot

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Tsp Model when an AI agent needs a reusable SKILL.md workflow for this job: Use when creating, modifying, or documenting TypeSpec domain models. Triggers include adding new entities, value objects, enums, extending base types, or when asked to create a "tsp model", "domain model", "entity", or work with files in the tsp/ directory. Part of the Shep autonomous SDLC platform — https://shep.bot

When not to use it

Skip Tsp Model when the task is outside the creativity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/tsp-model
# Save SKILL.md to ~/.claude/skills/tsp-model/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/tsp-model/SKILL.md. For a shared project, commit the folder at .claude/skills/tsp-model/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Tsp Model skill for this task: Use Tsp Model when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
62/100
Source signals
70/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# TypeSpec Domain Model Generation

Generate TypeSpec domain models following this project's conventions for Clean Architecture entities.

## Directory Structure

``` tsp/ ├── common/ # Base types, scalars, enums │ ├── base.tsp # BaseEntity, SoftDeletableEntity, AuditableEntity │ ├── scalars.tsp # UUID scalar type │ ├── ask.tsp # Askable interface pattern │ └── enums/ # One file per enum ├── domain/ # Domain entities │ ├── entities/ # One file per entity │ └── value-objects/# Embedded value objects ├── agents/ # Agent system models └── deployment/ # Deployment configuration models ```

## File Conventions

**One model per file** - Each entity/enum/value-object gets its own file.

**Naming:**

- Files: `kebab-case.tsp` (e.g., `action-item.tsp`) - Models: `PascalCase` (e.g., `ActionItem`) - Enums: `PascalCase` with values in `PascalCase` (e.g., `TaskStatus.InProgress`)

## Required Template

Every `.tsp` file MUST follow this structure:

````typespec /** * @module Shep.Domain.Entities.<EntityName> * * Brief description of the entity's purpose. * * ## Entity Relationships (if applicable) * ASCII diagram showing relationships * * @see docs/concepts/<relevant-doc>.md * @see <related-entity>.tsp */ import "../../common/base.tsp"; import "../../common/scalars.tsp"; // other imports...

/** * Entity Name * * Detailed description. * * ## Properties * * | Property | Type | Required | Description | * |----------|------|----------|-------------| * | ... | ... | ... | ... | * * @example * ```json * { ... } * ``` */ @doc("One-line description for OpenAPI") model EntityName extends BaseEntity { /** * Property description. * @example "example value" */ @doc("One-line property description") propertyName: PropertyType; } ````

## Base Types

**Choose the right base:**

| Base Type | Use When | | --------------------- | ------------------------------------------------------ | | `BaseEntity` | Standard entity with id, createdAt, updatedAt | | `SoftDeletableEntity` | Entity that can be soft-deleted (adds deletedAt) | | `AuditableEntity` | Entity needing audit trail (adds createdBy, updatedBy) |

## Enum Definition Pattern

```typespec /** * @module Shep.Common.Enums.<EnumName> */ /** * Enum description */ @doc("One-line enum description") enum EnumName { @doc("Description of this value") ValueOne,

@doc("Description of this value") ValueTwo, } ```

## Documentation Requirements

1. **Module JSDoc** at file top with `@module`, relationships, `@see` links 2. **Model JSDoc** with property table and JSON examples 3. **Property JSDoc** with `@example` tags 4. **`@doc()` decorator** on every model and property (for OpenAPI)

## Validation Commands

After creating/modifying TypeSpec:

```bash pnpm tsp:compile # Verify compilation pnpm tsp:format # Format TypeSpec files ```

## Quick Reference

| Task | Location | Example | | ---------------- | ------------------------------------- | ----------------- | | New entity | `tsp/domain/entities/<name>.tsp` | feature.tsp | | New enum | `tsp/common/enums/<name>.tsp` | lifecycle.tsp | | New value object | `tsp/domain/value-objects/<name>.tsp` | gantt.tsp | | Agent model | `tsp/agents/<name>.tsp` | feature-agent.tsp |

## Common Mistakes

- **Missing `@doc()` decorators** - Required for OpenAPI generation - **Forgetting index.tsp exports** - Add to directory's index.tsp - **Wrong import paths** - Use relative paths from current file - **Missing examples** - Always include `@example` with realistic JSON

Intended uses

  • Use Tsp Model when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.