migrate-to-promptscript

Migrate existing AI instruction files to PromptScript format

16 stars

Best use case

migrate-to-promptscript is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Migrate existing AI instruction files to PromptScript format

Teams using migrate-to-promptscript should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/migrate-to-promptscript/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/ai-agents/migrate-to-promptscript/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/migrate-to-promptscript/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How migrate-to-promptscript Compares

Feature / Agentmigrate-to-promptscriptStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Migrate existing AI instruction files to PromptScript format

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

<!-- PromptScript 2026-01-27T21:55:57.840Z - do not edit -->

# Migrate to PromptScript

## Overview

This skill guides you through migrating existing AI instruction files
to PromptScript format, creating a unified source of truth for all
AI coding assistants.

## Step 1: Discovery

Search for existing instruction files using these patterns:

Claude Code:

- CLAUDE.md, claude.md, CLAUDE.local.md

Cursor:

- .cursorrules
- .cursor/rules/\*.md
- .cursor/rules/\*.mdc

GitHub Copilot:

- .github/copilot-instructions.md
- .github/instructions/\*.md

Other:

- AGENTS.md
- AI_INSTRUCTIONS.md
- AI.md
- .ai/instructions.md

Use Glob tool to find these files.

## Step 2: Read and Analyze

For each discovered file:

1. Read the full content using the Read tool
2. Identify sections by headers (##, ###) and patterns
3. Classify content type using the mapping table below
4. Note any tool-specific content that may need special handling

## Step 3: Content Mapping

Map source content to PromptScript blocks:

| Source Pattern                       | PromptScript Block |
| ------------------------------------ | ------------------ |
| You are, persona, identity, role     | @identity          |
| Tech stack, languages, frameworks    | @context           |
| Coding standards, conventions, rules | @standards         |
| Don't, Never, restrictions           | @restrictions      |
| Commands, shortcuts                  | @shortcuts         |
| API docs, references, knowledge base | @knowledge         |
| Parameters, config values            | @params            |
| File patterns, globs, applyTo        | @guards            |
| Skills, capabilities                 | @skills            |
| Agents, subagents                    | @agents            |
| Local-only settings                  | @local             |

## Step 4: Generate PromptScript

### Required: @meta block

Every PromptScript file needs metadata with id and syntax fields.

### Identity (persona)

Convert persona descriptions to @identity block with triple-quote string.

### Context (project info)

Convert tech stack to @context block with structured properties
like project, languages, frameworks.

### Standards (conventions)

Convert coding standards to @standards block organized by category:
code, naming, commits, etc.

### Restrictions (don'ts)

Convert restrictions to @restrictions block using dash prefix for each item.

### Shortcuts (commands)

Convert custom commands to @shortcuts block. Simple shortcuts use
key-value format. Complex shortcuts use object format with
prompt, description, and content fields.

### Knowledge (references)

Convert API docs and reference material to @knowledge block
using triple-quote string for rich content.

### Guards (file patterns)

Convert file-specific rules to @guards block with globs array
specifying file patterns.

### Params (configuration)

Convert configuration parameters to @params block with type annotations:
range(), enum(), boolean.

### Skills (capabilities)

Convert skill definitions to @skills block with description,
trigger, and content fields.

### Agents (subagents)

Convert agent definitions to @agents block with description,
tools, model, and content fields.

## Step 5: File Organization

Simple Projects - single file structure:

- .promptscript/project.prs
- promptscript.yaml

Complex Projects - modular file structure:

- .promptscript/project.prs (main with @use imports)
- .promptscript/context.prs
- .promptscript/standards.prs
- .promptscript/restrictions.prs
- .promptscript/commands.prs
- promptscript.yaml

## Step 6: Configuration

Create promptscript.yaml with:

- version: '1'
- project.id
- input.entry pointing to main .prs file
- targets for github, claude, cursor

## Step 7: Validation

After generating PromptScript files:

1. Validate syntax: prs validate
2. Test compilation: prs compile --dry-run
3. Compare output with original files
4. Iterate if content is missing or incorrect

## Common Patterns

### Merging Multiple Sources

When instructions exist in multiple files:

1. Identity: Take from most detailed source
2. Standards: Merge all, deduplicate
3. Restrictions: Combine all (union)
4. Commands: Merge, resolve conflicts

### Tool-Specific Content

Handle tool-specific content:

- GitHub prompts: Use @shortcuts with prompt: true
- Claude agents: Use @agents block
- Cursor rules: Map to @standards
- Local content: Use @local block

### Preserving Formatting

Use triple-quote multiline strings for:

- Rich markdown content
- Code examples
- Complex instructions

## Syntax Rules

Quick reference for PromptScript syntax:

- Strings: quoted or identifier
- Multi-line: triple quotes
- Arrays: [item1, item2] or - item prefix
- Objects: { key: value }
- Comments: # comment
- Required @meta fields: id, syntax

## Quality Checklist

Before completing migration:

- @meta block has id and syntax
- Identity is clear and specific
- Standards are organized by category
- Restrictions use dash prefix (-)
- Shortcuts work in target tools
- prs validate passes
- prs compile produces correct output
- No duplicate content across blocks

## Troubleshooting

### Missing @meta Error

Add required metadata block at the start.

### Multiline String in Object Error

Assign multiline strings to named keys, don't leave them loose
inside objects.

### Content Not Appearing in Output

Check block names match expected patterns and
verify syntax with prs validate --verbose.

Related Skills

migrate

16
from diegosouzapw/awesome-omni-skill

Guide migration to Astro from other frameworks or between Astro versions. Use when converting Next.js, Nuxt, Gatsby projects or upgrading Astro.

mcpserver-migrate-mcpapps

16
from diegosouzapw/awesome-omni-skill

Migrates an MCP server with interactive widgets from the OpenAI Apps SDK (window.openai, text/html+skybridge) to the MCP Apps standard (@modelcontextprotocol/ext-apps), covering server-side and client-side changes.

agent-ops-migrate

16
from diegosouzapw/awesome-omni-skill

Migrate a project into another, ensuring functionality and validating complete content transfer. Use for monorepo consolidation, template upgrades, or codebase mergers.

migrate-to-skills

16
from diegosouzapw/awesome-omni-skill

Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when the user wants to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

n8n-node-configuration

16
from diegosouzapw/awesome-omni-skill

Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type.

n8n-code-python

16
from diegosouzapw/awesome-omni-skill

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.

n8n-builder

16
from diegosouzapw/awesome-omni-skill

Expert n8n workflow builder that creates, deploys, and manages n8n workflows programmatically via the n8n REST API. Use when asked to create n8n workflows, automate n8n tasks, build automations, design workflow pipelines, connect services via n8n, or manage existing n8n workflows. Handles webhook flows, scheduled tasks, AI agents, database syncs, conditional logic, error handling, and any n8n node configuration.

N+1 Query Detection

16
from diegosouzapw/awesome-omni-skill

Detect N+1 query patterns in GORM repository and service code — identify loops that execute queries, missing preloads, and unbounded fetches

myth

16
from diegosouzapw/awesome-omni-skill

Complete guide for using the Myth .NET ecosystem - enterprise-grade libraries for building scalable applications with SOLID principles, clean architecture, CQRS, validation, pipelines, and DDD patterns

mypy

16
from diegosouzapw/awesome-omni-skill

mypy - Static type checker for Python with gradual typing, strict mode, Protocol support, and framework integration

mypa

16
from diegosouzapw/awesome-omni-skill

Personal communication hub. Send tezits to family/team members, manage messages, get briefings, interrogate context, and share mirrors. Voice-first with Library of Context preservation and Tezit Protocol support.