Prompt Library

Scaffolds a versioned prompt management system using YAML files with structured frontmatter for metadata, model configuration, and typed variables. Includes an optional TypeScript SDK for loading, validating, and rendering prompts programmatically, plus a validation test suite that checks all prompt files against a JSON Schema.

Name	`prompt-library`
Version	`0.1.0`
Category	ai-systems
License	Apache-2.0
Persona	engineering
Tags	prompts, yaml, versioning, llm, ai
Source	`templates/prompt-library`

Render it

Three front doors, one catalog. Pick whichever suits the caller.

# CLI
npx @nanohype/sdk render prompt-library --out ./my-app

# SDK
import { LocalSource, renderTemplate } from "@nanohype/sdk";
const result = await renderTemplate(source, "prompt-library", variables);

# MCP — from an agent
get_template({ name: "prompt-library" })

Prerequisites

Tool	Version	Why
`node`	`>=22`	Node.js runtime for the SDK and validation scripts

Variables

Required

ProjectName string: Kebab-case project name, used as package name and directory Must be lowercase kebab-case starting with a letter.

Optional

Description string — defaults to A versioned prompt library: Short project description for package.json and README
IncludeSdk bool — defaults to true: Include TypeScript SDK for loading, validating, and rendering prompts
IncludeTests bool — defaults to true: Include validation test suite for prompt files

What it produces

15 files. Placeholder names such as __APP_NAME__ are what the renderer substitutes into.

.env.example
.gitignore
biome.json
package.json
prompts/system/example.yaml
prompts/user/example.yaml
README.md
schema/prompt.schema.json
sdk/package.json
sdk/src/__tests__/loader.test.ts
sdk/src/index.ts
sdk/src/types.ts
sdk/tsconfig.json
sdk/vitest.config.ts
tests/validate.ts

Composes with

Pairs with agentic-loop
Pairs with eval-harness
Nests inside monorepo

Composites that use it

Chrome AI Extension — Chrome extension with AI sidepanel backed by MCP tool servers and optional prompt library..
Enterprise AI Infrastructure — Full enterprise AI stack with agents, tool servers, safety guardrails, evaluation, prompt management, observability, and Kubernetes deployment..
AI Evaluation Suite — Standalone evaluation infrastructure with test harness, versioned prompts, and guardrails validation.
MCP Toolkit — MCP server with evaluation harness, prompt library, and deployment.
Safe AI Agent — AI agent with safety guardrails, evaluation harness, and prompt management.
VS Code AI Extension — VS Code extension with AI provider integration, MCP tool servers, and versioned prompt management..