🧩
AI EngineeringTypeScript

TSpec Model

by shep-ai

TSpec Model is an AI Engineering skill for Claude Code, published by shep-ai in shep.

247 stars53 forkson shep-ai/shepAdded 2026/09/02Repository updated 2026/08/28
View source on GitHubDownload repo ZIP
agent-orchestrationagentic-aiaiai-agentsai-code-generationai-codingai-nativeautomationclaudeclaude-codeclicursordeveloper-toolsdevtoolsgeminigit-worktreesparallel-developmentsdlctypescriptworktrees
Install in seconds
Install TSpec Model
Copy TSpec Model into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/shep-ai/shep/tree/main/.claude/skills/tsp-model ~/.claude/skills/tsp-model

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/shep-ai/shep.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.claude/skills/tsp-model/SKILL.md in shep-ai/shep
Installs to
~/.claude/skills/tsp-model
Collection
One of 19 skills cataloged from this repository
Category
AI Engineering — 3670 skills

What TSpec Model does

TSpec Model helps create, modify, and document TypeSpec domain models for Shep's Clean Architecture conventions. Use it when adding entities, value objects, enums, or working in the tsp/ directory.

TSpec Model is cataloged under AI Engineering on DirSkills. TSpec Model comes from a repository tagged agent-orchestration, agentic-ai, ai, ai-agents and ai-code-generation.

Documentation

README

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:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about TSpec Model

  • What else does shep-ai publish alongside TSpec Model?

    TSpec Model is one of 19 skills that DirSkills catalogs from shep-ai/shep, the repository it ships in. Its siblings there include Architecture Reviewer, Commit PR and Cross-Validate Artifacts. Each one is a separate skill with its own page in this directory, installs the same way TSpec Model does, and is maintained by shep-ai in that same repository. The rest of the collection is listed on the shep-ai/shep page.

  • How does TSpec Model compare to other AI Engineering skills?

    TSpec Model ranks #2364 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of TSpec Model against them. Open each page to compare what they document and how they install.

More from shep-ai/shep

TSpec Model is one of 19 skills cataloged on DirSkills from shep-ai/shep.

See all 19 skills →
🏗️
2026/09/02

Architecture Reviewer

Architecture Reviewer gives Clean Architecture guidance for TypeScript projects, including layer placement, dependency direction, ports, and pattern checks. Use it when planning features, reviewing PRs, or validating where code should live.
AI Engineering
24753
🔁
2026/09/02

Commit PR

Commit PR creates a branch, commits changes, pushes them, and opens a pull request with CI watching. It then checks review feedback and applies fixes until the PR is approved or it needs user input.
DevOps
24753
🧾
2026/09/02

Cross-Validate Artifacts

Cross-Validate Artifacts checks documentation and codebase artifacts for consistency, conflicts, and contradictions. Use it to audit docs or run a validate-and-fix pass across related files and paths.
Quality
24753
⚡
2026/09/02

Fast Loop

Fast Loop skips tests, builds, and commits so you can edit code and check changes in a running dev server. Use it for quick manual iteration when the user wants fast feedback.
Automation
24753
🧭
2026/09/02

Feature Status

Feature Status quickly orients you to the current branch, what has been completed, and what to do next. Use it when starting a session, resuming work, or checking progress on a feature branch.
Automation
24753
🗺️
2026/09/02

Mermaid Diagrams

Mermaid Diagrams helps create and document software diagrams with Mermaid syntax. Use it for class, sequence, flowchart, ERD, C4, state, git, and Gantt diagrams when mapping architecture, data models, or flows.
Writing
24753

More AI Engineering skills

TSpec Model is one of 3670 AI Engineering skills cataloged on DirSkills, ranked #2364 by stars among them.

Browse all AI Engineering skills →
📐
2026/08/13

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
2026/08/13

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
2026/08/13

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K