prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints
Install
npx skills add https://github.com/AgentWorkforce/relay/tree/main/.claude/skills/prpm-json-best-practices-skill
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentworkforce-relay@llmmart
git clone https://github.com/AgentWorkforce/relay.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole agentworkforce/relay collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
PRPM JSON Best Practices
You are an expert at creating and maintaining prpm.json package manifests for PRPM (Prompt Package Manager). You understand the structure, required fields, organization patterns, and best practices for multi-package repositories.
When to Apply This Skill
Use when:
- Creating a new
prpm.jsonmanifest for publishing packages - Maintaining existing
prpm.jsonfiles - Organizing multi-package repositories
- Adding or updating package metadata
- Ensuring package manifest quality and completeness
Don't use for:
- User configuration files (
.prpmrc) - those are for users - Lockfiles (
prpm.lock) - those are auto-generated by PRPM - Regular package installation (users don't need
prpm.json) - Dependencies already tracked in lockfiles
Core Purpose
prpm.json is only needed if you're publishing packages. Regular users installing packages from the registry don't need this file.
Use prpm.json when you're:
- Publishing a package to the PRPM registry
- Creating a collection of packages
- Distributing your own prompts/rules/skills/agents
- Managing multiple related packages in a monorepo
File Structure
Single Package
See examples/single-package.json for complete structure.
Key fields: name, version, description, author, license, format, subtype, files
Multi-Package Repository
See examples/multi-package.json for complete structure.
Use when: Publishing multiple related packages from one repo
Key difference: Top-level packages array with individual package definitions
Collections Repository
See examples/collections-repository.json for complete structure.
Use when: Bundling existing published packages into curated collections Key points:
collectionsarray references packages bypackageId(not files)- Each collection has
id,name,description,packages - Packages can be
required: true(default) orfalse(optional) - Use version ranges (
^1.0.0) orlatest - Add
reasonto explain why package is included
Packages + Collections (Combined)
See examples/packages-with-collections.json for complete structure.
Use when: Publishing packages AND creating collections that bundle them Key points:
- Define packages in
packagesarray with files - Define collections in
collectionsarray referencing those packages - Collections can reference both local packages and external ones
- Publish both individual packages and collection bundles from same repo
Required Fields
Top-Level (Single Package)
| Field | Type | Required | Description |
|---|---|---|---|
name |
string | Yes | Package name (kebab-case, unique in registry) |
version |
string | Yes | Semver version (e.g., 1.0.0) |
description |
string | Yes | Clear description of what the package does |
author |
string | Yes | Author name and optional email |
license |
string | Yes | SPDX license identifier (e.g., MIT, Apache-2.0) |
format |
string | Yes | Target format: claude, cursor, continue, windsurf, etc. |
subtype |
string | Yes | Package type: agent, skill, rule, slash-command, prompt, collection |
files |
string[] | Yes | Array of files to include in package |
Optional Top-Level Fields
| Field | Type | Description |
|---|---|---|
repository |
string | Git repository URL |
organization |
string | Organization name (for scoped packages) |
homepage |
string | Package homepage URL |
documentation |
string | Documentation URL |
license_text |
string | Full text of the license file for proper attribution |
license_url |
string | URL to the license file in the repository |
tags |
string[] | Searchable tags (kebab-case) |
keywords |
string[] | Additional keywords for search |
category |
string | Package category |
private |
boolean | If true, won't be published to public registry |
dependencies |
object | Package dependencies (name: semver) |
scripts |
object | Lifecycle scripts (multi-package only) |
eager |
boolean | If true, skill/agent loads at session start (not on-demand) |
Multi-Package Fields
When using packages array:
| Field | Type | Required | Description |
|---|---|---|---|
name |
string | Yes | Unique package name |
version |
string | Yes | Package version |
description |
string | Yes | Package description |
format |
string | Yes | Package format |
subtype |
string | Yes | Package subtype |
tags |
string[] | Recommended | Searchable tags |
files |
string[] | Yes | Files to include |
private |
boolean | No | Mark as private |
eager |
boolean | No | Load at session start (skills/agents only) |
Collection Fields
When using collections array:
Top-level (repository with collections):
name,version,description,author,license- Requiredrepository,organization- Recommended- Note: No
format,subtype, orfilesrequired at top level
Each collection object:
| Field | Type | Required | Description |
|---|---|---|---|
id |
string | Yes | Unique collection identifier (kebab-case, 3-100 chars) |
name |
string | Yes | Display name (3-100 chars) |
description |
string | Yes | What the collection provides (10-500 chars) |
packages |
array | Yes | Array of packages to include (minimum 1) |
version |
string | Recommended | Semantic version of collection |
category |
string | Recommended | Collection category (development, testing, etc.) |
tags |
string[] | Recommended | Searchable tags (kebab-case, 1-10 items) |
icon |
string | Optional | Emoji or icon (max 10 chars) |
Each package within collection:
| Field | Type | Required | Description |
|---|---|---|---|
packageId |
string | Yes | Package to include |
version |
string | Optional | Version range (^1.0.0, ~2.1.0, 1.0.0, latest) |
required |
boolean | Optional | Whether package is required (default: true) |
reason |
string | Optional | Why package is included (max 200 chars) |
Format and Subtype Values
Format (Target AI Tool)
| Format | Description |
|---|---|
claude |
Claude Code (agents, skills) |
cursor |
Cursor IDE (rules, MDC files) |
continue |
Continue.dev extension |
windsurf |
Windsurf IDE |
copilot |
GitHub Copilot |
kiro |
Kiro IDE |
agents.md |
Agents.md format |
generic |
Generic/universal format |
mcp |
Model Context Protocol |
Subtype (Package Type)
| Subtype | Description | Typical Formats |
|---|---|---|
agent |
Autonomous agents | claude, agents.md |
skill |
Specialized capabilities | claude |
rule |
IDE rules and guidelines | cursor, windsurf |
slash-command |
Slash commands | cursor, continue |
prompt |
Prompt templates | generic |
collection |
Package collections | Any |
chatmode |
Chat modes | kiro |
tool |
MCP tools | mcp |
Eager vs Lazy Activation
Skills and agents can be configured to load eagerly (at session start) or lazily (on-demand when relevant).
When to Use Eager
Use eager: true when:
- The skill should ALWAYS be active (coding standards, style guides)
- Critical behavior that must never be skipped
- Small, foundational skills with minimal token cost
Keep lazy (default) when:
- Specialized skills for specific contexts
- Large skills with significant token overhead
- Skills that only apply to certain file types
Setting Eager in prpm.json
Package-level:
{
"name": "code-style-enforcer",
"version": "1.0.0",
"format": "claude",
"subtype": "skill",
"eager": true,
"files": [".claude/skills/code-style/SKILL.md"]
}
File-level (enhanced files format):
{
"files": [
{
"path": ".claude/skills/critical-skill/SKILL.md",
"format": "claude",
"subtype": "skill",
"eager": true
},
{
"path": ".claude/skills/optional-skill/SKILL.md",
"format": "claude",
"subtype": "skill",
"eager": false
}
]
}
Precedence
When installing, the final eager setting is determined by:
- CLI flag (
--eager/--lazy) - highest priority - File-level
eagersetting (enhanced files) - Package-level
eagersetting - Default: lazy (false)
Applicable Subtypes
| Subtype | Supports Eager |
|---|---|
skill |
Yes |
agent |
Yes |
rule |
No |
slash-command |
No |
hook |
No |
Eager loading only affects progressive disclosure formats (agents.md, gemini.md, claude.md, aider).
Tags Best Practices
Tag Structure
- Use kebab-case for all tags
- Be specific and searchable
- Include 3-8 tags per package
- Combine technology, domain, and purpose tags
Tag Categories
Technology Tags:
- Languages:
typescript,python,javascript,rust - Frameworks:
react,nextjs,fastify,django - Tools:
aws,docker,kubernetes,postgresql
Domain Tags:
deployment,testing,ci-cd,databaseinfrastructure,cloud,monitoringdocumentation,code-review,security
Purpose Tags:
troubleshooting,debugging,best-practicesautomation,quality-assurance,performancearchitecture,design-patterns
Meta Tags:
meta- For packages about creating packagesprpm-internal- For internal/private packagesprpm-development- For PRPM development itself
Tag Examples
Good Tags:
{
"tags": ["typescript", "type-safety", "code-quality", "best-practices", "static-analysis"]
}
Poor Tags:
{
"tags": [
"code", // Too generic
"stuff", // Meaningless
"TypeScript", // Wrong case
"type_safety" // Wrong format (use kebab-case)
]
}
Organization Best Practices
Multi-Package Organization
Order packages by:
- Privacy - Private packages first
- Format - Group by format (claude, cursor, etc.)
- Subtype - Group by subtype (agent, skill, rule)
Example organization:
{
"packages": [
// Private > Claude > Agents
{ "name": "internal-agent", "private": true, "format": "claude", "subtype": "agent" },
// Private > Claude > Skills
{ "name": "internal-skill", "private": true, "format": "claude", "subtype": "skill" },
// Private > Cursor > Rules
{ "name": "internal-rule", "private": true, "format": "cursor", "subtype": "rule" },
// Public > Claude > Skills
{ "name": "public-skill", "format": "claude", "subtype": "skill" },
// Public > Cursor > Rules
{ "name": "public-rule", "format": "cursor", "subtype": "rule" }
]
}
Naming Conventions
Package Names:
- Use kebab-case:
my-awesome-skill - Be descriptive:
typescript-type-safetynotts-types - Avoid duplicates across formats: use suffixes if needed
format-conversion-agent(Claude agent)format-conversion(Cursor rule)
File Paths:
- Use full paths from project root (where prpm.json lives)
- Agents:
.claude/agents/name.md - Skills:
.claude/skills/name/SKILL.md - Rules:
.cursor/rules/name.mdc - Commands:
.claude/commands/category/name.md
Version Management
Semver Guidelines
Follow semantic versioning:
- Major (1.0.0 → 2.0.0): Breaking changes
- Minor (1.0.0 → 1.1.0): New features, backward compatible
- Patch (1.0.0 → 1.0.1): Bug fixes, backward compatible
Version Bumping
When to bump versions:
- Patch: Bug fixes, typo corrections, minor improvements
- Minor: New sections, additional examples, new features
- Major: Complete rewrites, breaking changes, renamed fields
Keep Versions in Sync
For multi-package repos, keep related packages in sync:
{
"packages": [
{ "name": "pkg-one", "version": "1.2.0" },
{ "name": "pkg-two", "version": "1.2.0" },
{ "name": "pkg-three", "version": "1.2.0" }
]
}
File Management
Files Array
CRITICAL: File paths must be full paths from project root (where prpm.json lives).
Required:
- List all files to include in the package
- Use full paths from project root - not relative to destination directories
- Paths should start with
.claude/,.cursor/, etc. - Include documentation files
Why Full Paths?
File paths in prpm.json are used for:
- Tarball creation - Reads files directly from these paths
- Snippet extraction - Shows file preview before install
- Installation - CLI derives destination from format/subtype
Examples:
Claude agent (single file):
{
"format": "claude",
"subtype": "agent",
"files": [".claude/agents/my-agent.md"]
}
Claude skill (multiple files):
{
"format": "claude",
"subtype": "skill",
"files": [
".claude/skills/my-skill/SKILL.md",
".claude/skills/my-skill/EXAMPLES.md",
".claude/skills/my-skill/README.md"
]
}
Cursor rule:
{
"format": "cursor",
"subtype": "rule",
"files": [".cursor/rules/my-rule.mdc"]
}
Slash command:
{
"format": "claude",
"subtype": "slash-command",
"files": [".claude/commands/category/my-command.md"]
}
Enhanced File Format
Advanced: Files can be objects with metadata instead of simple strings. Useful for packages with multiple files targeting different formats or needing per-file metadata.
Enhanced file object structure:
{
"files": [
{
"path": ".cursor/rules/typescript.mdc",
"format": "cursor",
"subtype": "rule",
"name": "TypeScript Rules",
"description": "TypeScript coding standards and best practices",
"tags": ["typescript", "frontend"]
},
{
"path": ".cursor/rules/python.mdc",
"format": "cursor",
"subtype": "rule",
"name": "Python Rules",
"description": "Python best practices for backend development",
"tags": ["python", "backend"]
}
]
}
When to use enhanced format:
- Multi-file packages with different formats/subtypes per file
- Need per-file descriptions or tags
- Want to provide display names for individual files
- Building collection packages with mixed content types
Enhanced file fields:
| Field | Required | Description |
|---|---|---|
path |
Yes | Relative path to file from project root |
format |
Yes | File's target format (cursor, claude, etc.) |
subtype |
No | File's subtype (rule, skill, agent, etc.) |
name |
No | Display name for this file |
description |
No | Description of what this file does |
tags |
No | File-specific tags (array of strings) |
Note: Cannot mix simple strings and objects in the same files array. Use all strings OR all objects, not both.
Common Mistake:
{
// ❌ WRONG - Relative paths without directory prefix
"files": ["agents/my-agent.md"] // Will fail to find file
// ✅ CORRECT - Full path from project root
"files": [".claude/agents/my-agent.md"]
}
File Verification
Always verify files exist:
# Check all files in prpm.json exist
for file in $(cat prpm.json | jq -r '.packages[].files[]'); do
if [ ! -f "$file" ]; then
echo "Missing: $file"
fi
done
Duplicate Detection
Check for Duplicate Names
Run this check before committing:
# Check for duplicate package names
cat prpm.json | jq -r '.packages[].name' | sort | uniq -d
If output is empty, no duplicates exist. If names appear, you have duplicates to resolve.
Resolving Duplicates
Bad:
{
"packages": [
{ "name": "typescript-safety", "format": "claude" },
{ "name": "typescript-safety", "format": "cursor" }
]
}
Good:
{
"packages": [
{ "name": "typescript-safety", "format": "claude", "subtype": "skill" },
{ "name": "typescript-safety-rule", "format": "cursor", "subtype": "rule" }
]
}
Conversion Hints (Advanced)
Purpose: Help improve quality when converting packages to other formats. The conversion field provides format-specific hints for cross-format transformations.
Note: This is an advanced feature primarily used by format conversion tools. Most packages don't need this.
Structure:
{
"name": "my-package",
"version": "1.0.0",
"format": "claude",
"conversion": {
"cursor": {
"alwaysApply": false,
"priority": "high",
"globs": ["**/*.ts", "**/*.tsx"]
},
"kiro": {
"inclusion": "fileMatch",
"fileMatchPattern": "**/*.ts",
"domain": "typescript",
"tools": ["fs_read", "fs_write"],
"mcpServers": {
"database": {
"command": "mcp-server-postgres",
"args": [],
"env": {
"DATABASE_URL": "${DATABASE_URL}"
}
}
}
},
"copilot": {
"applyTo": ["src/**", "lib/**"],
"excludeAgent": "code-review"
}
}
}
Supported conversion hints:
Cursor Hints
{
"conversion": {
"cursor": {
"alwaysApply": boolean, // Whether rule should always apply
"priority": "high|medium|low", // Rule priority level
"globs": ["**/*.ts"] // File patterns to auto-attach
}
}
}
Claude Hints
{
"conversion": {
"claude": {
"model": "sonnet|opus|haiku|inherit", // Preferred model
"tools": ["Read", "Write"], // Allowed tools
"subagentType": "format-conversion" // Subagent type if agent
}
}
}
Kiro Hints
{
"conversion": {
"kiro": {
"inclusion": "always|fileMatch|manual", // When to include
"fileMatchPattern": "**/*.ts", // Pattern for fileMatch mode
"domain": "typescript", // Domain category
"tools": ["fs_read", "fs_write"], // Available tools
"mcpServers": {
// MCP server configs
"database": {
"command": "mcp-server-postgres",
"args": [],
"env": { "DATABASE_URL": "${DATABASE_URL}" }
}
}
}
}
}
Copilot Hints
{
"conversion": {
"copilot": {
"applyTo": "src/**", // Path patterns
"excludeAgent": "code-review|coding-agent" // Agent to exclude
}
}
}
Continue Hints
{
"conversion": {
"continue": {
"alwaysApply": boolean, // Always apply rule
"globs": ["**/*.ts"], // File patterns
"regex": ["import.*from"] // Regex patterns
}
}
}
Windsurf Hints
{
"conversion": {
"windsurf": {
"characterLimit": 12000 // Warn if exceeding limit
}
}
}
Agents.md Hints
{
"conversion": {
"agentsMd": {
"project": "my-project", // Project name
"scope": "backend" // Scope/domain
}
}
}
When to use conversion hints:
- Publishing cross-format packages that need specific settings per format
- Format conversion tools need guidance on how to transform content
- Package behavior should change based on target format
- Want to preserve format-specific metadata during conversions
Common Patterns
Private Internal Packages
{
"name": "internal-tool",
"version": "1.0.0",
"description": "Internal development tool",
"private": true,
"format": "claude",
"subtype": "skill",
"tags": ["prpm-internal", "development"],
"files": [".claude/skills/internal-tool/SKILL.md"]
}
Meta Packages (Creating Other Packages)
{
"name": "creating-skills",
"version": "1.0.0",
"description": "Guide for creating effective Claude Code skills",
"format": "claude",
"subtype": "skill",
"tags": ["meta", "claude-code", "skills", "documentation", "best-practices"],
"files": [".claude/skills/creating-skills/SKILL.md"]
}
Cross-Format Packages
When you have the same content for multiple formats:
{
"packages": [
{
"name": "format-conversion-agent",
"format": "claude",
"subtype": "agent",
"description": "Agent for converting between AI prompt formats",
"files": [".claude/agents/format-conversion.md"]
},
{
"name": "format-conversion",
"format": "cursor",
"subtype": "rule",
"description": "Rule for converting between AI prompt formats",
"files": [".cursor/rules/format-conversion.mdc"]
}
]
}
Collections in prpm.json
Collections CAN be defined in prpm.json alongside packages using the collections array. Collections bundle multiple packages together for easier installation.
Example with both packages and collections:
{
"name": "my-prompts-repo",
"author": "Your Name",
"license": "MIT",
"packages": [
{
"name": "typescript-rules",
"version": "1.0.0",
"description": "TypeScript best practices",
"format": "cursor",
"subtype": "rule",
"tags": ["typescript"],
"files": [".cursor/rules/typescript.mdc"]
}
],
"collections": [
{
"id": "my-dev-setup",
"name": "My Development Setup",
"description": "Complete development setup with TypeScript and React",
"version": "1.0.0",
"category": "development",
"tags": ["typescript", "react"],
"packages": [
{
"packageId": "typescript-strict",
"version": "^1.0.0",
"required": true,
"reason": "Enforces strict TypeScript type safety"
},
{
"packageId": "react-best-practices",
"version": "^2.0.0",
"required": true
}
]
}
]
}
For more details on creating collections, see the PRPM documentation at https://docs.prpm.dev or run prpm help collections.
Summary: prpm.json can contain both packages (skills, agents, rules, slash-commands, etc.) and collections.
Lifecycle Scripts
IMPORTANT: The scripts field only applies to multi-package manifests (prpm.json with a packages array). It does NOT work in single-package manifests.
Use the scripts field to run commands automatically during package operations, particularly for building TypeScript hooks before publishing.
When to Use Scripts
Primary use case: Building TypeScript Hooks
If your packages include Claude Code hooks written in TypeScript, you MUST build them to JavaScript before publishing:
{
"name": "my-packages",
"license": "MIT",
"scripts": {
"prepublishOnly": "cd packages/hooks && npm run build"
},
"packages": [
{
"name": "my-hook",
"version": "1.0.0",
"format": "claude",
"subtype": "hook",
"files": [
".claude/hooks/my-hook/hook.ts",
".claude/hooks/my-hook/hook.json",
".claude/hooks/my-hook/dist/hook.js"
]
}
]
}
Available Script Types
| Script | When it Runs | Use Case |
|---|---|---|
prepublishOnly |
Before prpm publish only |
Recommended - Build hooks, compile assets |
prepublish |
Before publish AND on npm install | Not recommended - causes unexpected builds |
Always use prepublishOnly instead of prepublish to avoid running builds when users install your packages.
prepublishOnly Examples
Single hook:
{
"scripts": {
"prepublishOnly": "cd .claude/hooks/my-hook && npm run build"
}
}
Multiple hooks:
{
"scripts": {
"prepublishOnly": "cd .claude/hooks/hook-one && npm run build && cd ../hook-two && npm run build"
}
}
With tests:
{
"scripts": {
"prepublishOnly": "npm test && cd packages/hooks && npm run build"
}
}
What Happens During Publishing
When you run prpm publish:
- PRPM checks for
scripts.prepublishOnlyin your prpm.json - If found, runs the script from the directory containing prpm.json
- If script succeeds (exit code 0), publishing continues
- If script fails (non-zero exit code), publishing is aborted
Script execution details:
- Working directory: Same directory as prpm.json
- Timeout: 5 minutes (300,000ms) default
- Environment: Inherits your shell's environment variables
- Output: Shown in real-time
Best Practices for Scripts
DO:
- ✅ Use
prepublishOnlyfor building hooks - ✅ Chain commands with
&&for dependencies:npm test && npm run build - ✅ Keep scripts fast (under 1 minute if possible)
- ✅ Test scripts locally before publishing
DON'T:
- ❌ Use
prepublish(runs on install too) - ❌ Forget to build hooks before publishing
- ❌ Use scripts in single-package manifests (not supported)
- ❌ Put long-running operations in scripts
Common Patterns
Hooks in packages/ directory:
{
"scripts": {
"prepublishOnly": "cd packages/hooks && npm run build"
}
}
Hooks in .claude/ directory:
{
"scripts": {
"prepublishOnly": "cd .claude/hooks/my-hook && npm run build"
}
}
Build multiple components:
{
"scripts": {
"prepublishOnly": "npm run build:hooks && npm run build:assets"
}
}
Debugging Script Failures
If your prepublishOnly script fails:
- Check the output - Error messages show what went wrong
- Run manually - Test the exact command in your terminal
- Verify working directory - Scripts run from prpm.json location
- Check dependencies - Ensure npm packages are installed
Example debugging:
# Test your prepublishOnly script manually
cd /path/to/prpm.json/directory
cd packages/hooks && npm run build
# If it works manually but fails in PRPM, check:
# - Working directory assumptions
# - Environment variables
# - Installed dependencies
Why This Matters
Without prepublishOnly:
- You might forget to build hooks before publishing
- Published packages contain stale/outdated JavaScript
- Users install broken hooks
- Manual builds are error-prone
With prepublishOnly:
- Hooks automatically build before every publish
- JavaScript always matches TypeScript source
- Prevents publishing broken code
- Consistent, reliable publishing workflow
Validation Checklist
Before publishing, verify:
Required Fields:
- All packages have
name,version,description - All packages have
formatandsubtype - All packages have
filesarray - Top-level has
authorandlicense
File Verification:
- All files in
filesarrays exist - File paths are relative to repo root
- No missing or broken file references
No Duplicates:
- No duplicate package names
- Package names are unique across entire manifest
Tags:
- Tags use kebab-case
- 3-8 relevant tags per package
- Tags include technology, domain, and purpose
Organization:
- Private packages listed first
- Packages grouped by format and subtype
- Consistent versioning across related packages
Lockfile Management
Understanding prpm.lock
The prpm.lock file is auto-generated and tracks installed packages. It serves as the source of truth for what's installed in your project.
IMPORTANT: Do NOT add packages to prpm.json if they already exist in prpm.lock:
prpm.locktracks installed dependencies (packages you use)prpm.jsondefines published packages (packages you create and share)
When to Use prpm.json vs prpm.lock
Use prpm.json when:
- You're creating a package to publish to the registry
- You want to define metadata for YOUR packages
- You're setting up a multi-package repository
Use prpm.lock (auto-generated) when:
- You install packages with
prpm install - You want to track which packages are installed
- You want reproducible installations across environments
Common Mistake: Duplicating Dependencies
❌ WRONG - Don't add installed packages to prpm.json:
// prpm.json
{
"name": "my-project",
"packages": [
{
"name": "typescript-safety", // ❌ This is an INSTALLED package
"version": "1.0.0",
"format": "cursor",
"subtype": "rule",
"files": [".cursor/rules/typescript-safety.mdc"]
}
]
}
// prpm.lock (auto-generated)
{
"packages": {
"@prpm/typescript-safety": {
// ✅ Already tracked here
"version": "1.0.0",
"format": "cursor",
"subtype": "rule"
}
}
}
✅ CORRECT - prpm.json only for YOUR packages:
// prpm.json - Only YOUR packages you're publishing
{
"name": "my-project",
"packages": [
{
"name": "my-custom-rule", // ✅ This is YOUR package
"version": "1.0.0",
"format": "cursor",
"subtype": "rule",
"files": [".cursor/rules/my-custom-rule.mdc"]
}
]
}
// prpm.lock - Installed dependencies (auto-generated)
{
"packages": {
"@prpm/typescript-safety": {
// ✅ Installed from registry
"version": "1.0.0",
"format": "cursor",
"subtype": "rule"
}
}
}
Key Principles
- Lockfile is Auto-Generated - Never manually edit
prpm.lock - Separation of Concerns:
prpm.json= What you PUBLISHprpm.lock= What you INSTALL
- Check Lockfile First - Before adding to
prpm.json, check if it's already inprpm.lock - Trust the Lockfile - It's the authoritative record of installed packages
Workflow Example
# Install a package (updates prpm.lock automatically)
prpm install @prpm/typescript-safety
# This creates/updates prpm.lock - DO NOT add to prpm.json!
# Only create prpm.json entries for packages YOU create:
# 1. Create your custom rule/skill/agent
# 2. Add entry to prpm.json
# 3. Publish with: prpm publish
Publishing Workflow
1. Validate Manifest
# Validate JSON syntax
cat prpm.json | jq . > /dev/null
# Check for duplicates
cat prpm.json | jq -r '.packages[].name' | sort | uniq -d
# Verify files exist
# (see File Verification section)
2. Bump Versions
Update version numbers for changed packages.
3. Test Locally
# Test package installation
prpm install . --dry-run
4. Publish
# Publish all packages
prpm publish
# Or publish specific package
prpm publish --package my-skill
Common Mistakes to Avoid
❌ Missing Required Fields
{
"name": "my-skill"
// Missing: version, description, format, subtype, files
}
❌ Wrong Tag Format
{
"tags": ["TypeScript", "Code_Quality", "bestPractices"]
// Should be: ["typescript", "code-quality", "best-practices"]
}
❌ Duplicate Names
{
"packages": [
{ "name": "my-skill", "format": "claude" },
{ "name": "my-skill", "format": "cursor" }
// Second should be: "my-skill-rule" or similar
]
}
❌ Missing Files
{
"files": [".claude/skills/my-skill/SKILL.md"]
// But .claude/skills/my-skill/SKILL.md doesn't exist in the repo
}
❌ Absolute Paths
{
"files": ["/Users/me/project/.claude/skills/my-skill/SKILL.md"]
// Should be: ".claude/skills/my-skill/SKILL.md" (relative to project root)
}
❌ Missing Directory Prefix
{
"files": ["agents/my-agent.md"]
// Should be: ".claude/agents/my-agent.md" (include .claude/ prefix)
}
Remember
prpm.jsonis only for publishing YOUR packages/collections, not for installed dependencies- Never add packages from
prpm.locktoprpm.json- they serve different purposes prpm.locktracks what you INSTALL,prpm.jsondefines what you PUBLISH- Use
collectionsarray to bundle existing packages (references by packageId) - Use
packagesarray to define packages with files - Can combine both
packagesandcollectionsin same repo - Always validate before committing
- Keep versions in sync for related packages
- Use consistent, searchable tags
- Verify all file paths exist
- Check for duplicate names
- Follow semver for version management
Goal: Create maintainable, well-organized package manifests and curated collections that are easy to publish and discover in the PRPM registry.
Files (relay)
-
examples
-
collections-repository.json 1.2 KB
{ "name": "@prpm/collections", "version": "1.0.0", "description": "Official PRPM collections for popular development workflows", "author": "PRPM Team", "license": "MIT", "repository": "https://github.com/prpm/collections", "organization": "prpm", "collections": [ { "id": "nextjs-pro", "name": "Next.js Professional Setup", "description": "Complete Next.js development environment with TypeScript, React best practices, and modern tooling", "version": "1.0.0", "category": "development", "tags": ["nextjs", "react", "typescript", "frontend"], "icon": "⚡", "packages": [ { "packageId": "react-best-practices", "version": "^2.0.0", "required": true, "reason": "Core React patterns and component guidelines" }, { "packageId": "typescript-strict", "version": "latest", "required": true, "reason": "TypeScript strict mode for type safety" }, { "packageId": "tailwind-helper", "version": "^1.5.0", "required": false, "reason": "Optional Tailwind CSS utilities" } ] } ] } -
multi-package.json 744 B
{ "name": "prpm-packages", "version": "1.0.0", "author": "yourgithubusername", "license": "MIT", "repository": "https://github.com/yourgithubusername/repo", "organization": "your-org", "packages": [ { "name": "package-one", "version": "1.0.0", "description": "Description of package one", "private": true, "format": "claude", "subtype": "agent", "tags": ["tag1", "tag2"], "files": [".claude/agents/package-one.md"] }, { "name": "package-two", "version": "1.0.0", "description": "Description of package two", "format": "cursor", "subtype": "rule", "tags": ["tag1", "tag3"], "files": [".cursor/rules/package-two.mdc"] } ] } -
packages-with-collections.json 1.4 KB
{ "name": "@username/my-prompts-repo", "author": "yourgithubusername", "license": "MIT", "repository": "https://github.com/username/my-collection", "packages": [ { "name": "tdd-skill", "version": "1.0.0", "description": "Guides you through TDD workflow", "format": "claude", "subtype": "skill", "tags": ["testing", "tdd"], "files": [".claude/skills/tdd.md"] }, { "name": "typescript-rules", "version": "1.0.0", "description": "Best practices for TypeScript development", "format": "cursor", "subtype": "rule", "tags": ["typescript", "frontend"], "files": [".cursor/rules/typescript.mdc"] } ], "collections": [ { "id": "testing-suite", "name": "Complete Testing Suite", "description": "A collection of testing tools and best practices for TDD", "version": "1.0.0", "category": "testing", "tags": ["testing", "tdd", "productivity"], "icon": "🧪", "packages": [ { "packageId": "tdd-skill", "version": "^1.0.0", "required": true, "reason": "Essential TDD workflow guidance" }, { "packageId": "@external/test-runner", "version": "^2.0.0", "required": false, "reason": "Optional external test runner" } ] } ] } -
single-package.json 435 B
{ "name": "my-awesome-skill", "version": "1.0.0", "description": "Clear, concise description of what this package does", "author": "yourgithubusername", "license": "MIT", "repository": "https://github.com/yourgithubusername/repo", "organization": "your-org", "format": "claude", "subtype": "skill", "tags": ["typescript", "best-practices", "code-quality"], "files": [".claude/skills/my-awesome-skill/SKILL.md"] }
-
-
prpm-manifest.schema.json 20 KB
{ "$schema": "http://json-schema.org/draft-07/schema#", "$id": "https://prpm.dev/schemas/manifest.json", "title": "PRPM Package Manifest", "description": "Schema for PRPM package manifest (prpm.json)", "type": "object", "required": ["name", "version", "description", "format"], "properties": { "name": { "type": "string", "description": "Package name in format: package-name or @scope/package-name", "pattern": "^(@[a-z0-9-]+\\/)?[a-z0-9-]+$", "minLength": 1, "maxLength": 214, "examples": ["react-rules", "@community/testing-skills", "@company/cursor-rules"] }, "version": { "type": "string", "description": "Semantic version (semver)", "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9.-]+)?(\\+[a-zA-Z0-9.-]+)?$", "examples": ["1.0.0", "2.1.3", "1.0.0-beta.1"] }, "description": { "type": "string", "description": "Package description", "minLength": 10, "maxLength": 500 }, "format": { "type": "string", "description": "Package format - the AI tool/platform this package is for", "enum": [ "cursor", "claude", "claude-plugin", "continue", "windsurf", "copilot", "kiro", "agents.md", "generic", "mcp" ] }, "subtype": { "type": "string", "description": "Package subtype - the functional category (optional, defaults to 'rule')", "enum": [ "rule", "agent", "skill", "slash-command", "prompt", "workflow", "tool", "template", "collection", "chatmode", "hook", "plugin", "server" ] }, "author": { "description": "Package author", "oneOf": [ { "type": "string", "examples": ["John Doe", "Jane Smith"] }, { "type": "object", "required": ["name"], "properties": { "name": { "type": "string", "description": "Author name" }, "email": { "type": "string", "format": "email", "description": "Author email" }, "url": { "type": "string", "format": "uri", "description": "Author URL" } } } ] }, "license": { "type": "string", "description": "SPDX license identifier", "examples": ["MIT", "Apache-2.0", "GPL-3.0", "BSD-3-Clause"] }, "license_text": { "type": "string", "description": "Full text of the license file for proper attribution" }, "license_url": { "type": "string", "format": "uri", "description": "URL to the license file in the repository" }, "repository": { "type": "string", "format": "uri", "description": "Repository URL", "examples": ["https://github.com/username/repo"] }, "homepage": { "type": "string", "format": "uri", "description": "Package homepage URL" }, "documentation": { "type": "string", "format": "uri", "description": "Documentation URL" }, "organization": { "type": "string", "description": "Organization name or ID to publish this package under. If not specified, publishes to personal account.", "examples": ["my-team", "my-company"] }, "private": { "type": "boolean", "description": "Whether the package is private. Private packages are only accessible to the owner/organization members. Defaults to false (public).", "default": false }, "eager": { "type": "boolean", "description": "Whether this package should be loaded eagerly (at session start) or lazily (on-demand). Only applies to skills and agents in progressive disclosure formats (AGENTS.md, GEMINI.md, etc.). Defaults to false (lazy loading).", "default": false, "examples": [true, false] }, "scripts": { "type": "object", "description": "Lifecycle scripts that run during package operations. Only applies to multi-package manifests (prpm.json with packages array).", "properties": { "prepublishOnly": { "type": "string", "description": "Script to run before publishing (recommended - only runs on 'prpm publish')", "examples": ["npm run build", "cd packages/hooks && npm run build", "npm test && npm run build"] }, "prepublish": { "type": "string", "description": "Script to run before publishing and on npm install (not recommended - use prepublishOnly instead)", "examples": ["npm run build"] } }, "additionalProperties": false }, "tags": { "type": "array", "description": "Package tags for categorization", "items": { "type": "string" }, "maxItems": 10, "uniqueItems": true, "examples": [ ["productivity", "coding"], ["testing", "quality"] ] }, "keywords": { "type": "array", "description": "Search keywords", "items": { "type": "string" }, "maxItems": 20, "uniqueItems": true, "examples": [["ai", "prompts", "development"]] }, "category": { "type": "string", "description": "Package category", "examples": ["development", "productivity", "testing"] }, "files": { "description": "Files to include in package. Can be simple paths or enhanced file objects with metadata.", "oneOf": [ { "type": "array", "description": "Simple format: array of file paths", "items": { "type": "string" }, "minItems": 1, "examples": [ ["skill.md", "README.md"], [".cursor/rules/react.mdc", "LICENSE"] ] }, { "type": "array", "description": "Enhanced format: array of file objects with metadata", "items": { "type": "object", "required": ["path", "format"], "properties": { "path": { "type": "string", "description": "Relative path to file", "examples": [ ".claude/skills/tdd.md", ".cursor/rules/react.mdc", ".continue/rules/python.json" ] }, "format": { "type": "string", "description": "File format - the AI tool/platform this file is for", "enum": [ "cursor", "claude", "claude-plugin", "continue", "windsurf", "copilot", "kiro", "agents.md", "generic", "mcp" ] }, "subtype": { "type": "string", "description": "File subtype - the functional category", "enum": [ "rule", "agent", "skill", "slash-command", "prompt", "workflow", "tool", "template", "collection", "chatmode", "hook", "plugin", "server" ] }, "name": { "type": "string", "description": "Display name for this file", "examples": ["React Rules", "Test-Driven Development"] }, "description": { "type": "string", "description": "Description of what this file does" }, "tags": { "type": "array", "description": "File-specific tags", "items": { "type": "string" }, "uniqueItems": true, "examples": [ ["react", "typescript"], ["testing", "tdd"] ] }, "eager": { "type": "boolean", "description": "File-level eager setting. Overrides package-level eager for this specific file.", "default": false } }, "additionalProperties": false }, "minItems": 1 } ] }, "main": { "type": "string", "description": "Main entry file (for single-file packages)", "examples": ["index.md", "skill.md"] }, "dependencies": { "type": "object", "description": "Package dependencies", "patternProperties": { "^(@[a-z0-9-]+\\/)?[a-z0-9-]+$": { "type": "string", "pattern": "^(\\^|~)?\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9.-]+)?(\\+[a-zA-Z0-9.-]+)?$" } }, "additionalProperties": false, "examples": [ { "@pr-pm/utils": "^1.0.0", "common-rules": "~2.1.0" } ] }, "peerDependencies": { "type": "object", "description": "Peer dependencies (packages that should be installed alongside)", "patternProperties": { "^(@[a-z0-9-]+\\/)?[a-z0-9-]+$": { "type": "string" } }, "additionalProperties": false }, "engines": { "type": "object", "description": "Required engine versions", "properties": { "prpm": { "type": "string", "description": "Required PRPM version" }, "node": { "type": "string", "description": "Required Node.js version" } }, "additionalProperties": false, "examples": [ { "prpm": ">=1.0.0", "node": ">=18.0.0" } ] }, "packages": { "type": "array", "description": "Array of packages to publish from a single manifest (multi-package publishing). Packages inherit top-level fields unless overridden.", "items": { "$ref": "#" }, "minItems": 1 }, "collections": { "type": "array", "description": "Array of collections to publish. Collections bundle multiple packages together for easier installation.", "items": { "type": "object", "required": ["id", "name", "description", "packages"], "properties": { "id": { "type": "string", "description": "Unique collection identifier (kebab-case)", "pattern": "^[a-z0-9-]+$", "minLength": 3, "maxLength": 100, "examples": ["nextjs-complete", "fullstack-setup", "react-essentials"] }, "name": { "type": "string", "description": "Display name of the collection", "minLength": 3, "maxLength": 100, "examples": ["Next.js Complete", "Full Stack Setup"] }, "description": { "type": "string", "description": "What this collection provides", "minLength": 10, "maxLength": 500 }, "version": { "type": "string", "description": "Semantic version of the collection", "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9.-]+)?(\\+[a-zA-Z0-9.-]+)?$", "examples": ["1.0.0", "2.1.0"] }, "category": { "type": "string", "description": "Collection category", "enum": [ "development", "testing", "deployment", "data-science", "devops", "design", "documentation", "security", "performance", "general" ], "examples": ["development", "testing"] }, "tags": { "type": "array", "description": "Tags for discoverability (kebab-case)", "items": { "type": "string", "pattern": "^[a-z0-9-]+$" }, "minItems": 1, "maxItems": 10, "examples": [ ["react", "typescript", "nextjs"], ["python", "data-science", "ml"] ] }, "icon": { "type": "string", "description": "Emoji or icon for the collection", "maxLength": 10, "examples": ["⚛️", "🚀", "📦"] }, "packages": { "type": "array", "description": "Array of packages included in this collection", "items": { "type": "object", "required": ["packageId"], "properties": { "packageId": { "type": "string", "description": "Package identifier to include", "minLength": 1, "examples": ["typescript-strict", "react-best-practices"] }, "version": { "type": "string", "description": "Version range (semver) or 'latest'", "examples": ["^1.0.0", "~2.1.0", "1.0.0", "latest"] }, "required": { "type": "boolean", "description": "Whether this package is required (true) or optional (false)", "default": true }, "reason": { "type": "string", "description": "Explanation of why this package is included", "maxLength": 200, "examples": ["Enforces strict TypeScript type safety", "React component best practices"] } } }, "minItems": 1 } } }, "minItems": 1 } }, "additionalProperties": false, "examples": [ { "name": "@username/simple-package", "version": "1.0.0", "description": "A simple package with basic files", "format": "claude", "subtype": "skill", "author": "Your Name", "license": "MIT", "files": ["skill.md", "README.md"] }, { "name": "@company/coding-standards", "version": "1.0.0", "description": "Team coding standards that must be active in every session", "format": "claude", "subtype": "skill", "author": "Company Team", "organization": "my-company", "license": "MIT", "eager": true, "files": [".claude/skills/coding-standards/SKILL.md"] }, { "name": "@company/team-package", "version": "1.0.0", "description": "A package published under organization account", "format": "cursor", "author": "Team Name", "organization": "my-company", "license": "MIT", "files": [".cursor/rules/guidelines.mdc", "README.md"] }, { "name": "@username/cursor-rules", "version": "1.0.0", "description": "Multiple Cursor rules for different languages", "format": "cursor", "author": { "name": "Your Name", "email": "you@example.com" }, "license": "MIT", "repository": "https://github.com/username/cursor-rules", "tags": ["cursor", "rules", "multi-language"], "files": [ { "path": ".cursor/rules/typescript.mdc", "format": "cursor", "name": "TypeScript Rules", "tags": ["typescript", "frontend"] }, { "path": ".cursor/rules/python.mdc", "format": "cursor", "name": "Python Rules", "tags": ["python", "backend"] } ] }, { "name": "@community/testing-suite", "version": "2.0.0", "description": "Complete testing suite with skills and agents", "format": "generic", "subtype": "collection", "author": "Community", "license": "MIT", "tags": ["testing", "quality"], "files": [ { "path": ".claude/skills/tdd.md", "format": "claude", "subtype": "skill", "name": "Test-Driven Development" }, { "path": ".claude/agents/test-generator.md", "format": "claude", "subtype": "agent", "name": "Test Generator" } ] }, { "name": "@username/copilot-instructions", "version": "1.0.0", "description": "GitHub Copilot instructions for API development", "format": "copilot", "author": "Your Name", "license": "MIT", "tags": ["copilot", "api", "backend"], "files": ["api-guidelines.md"] }, { "name": "@username/kiro-steering", "version": "1.0.0", "description": "Kiro steering file for testing standards", "format": "kiro", "author": "Your Name", "license": "MIT", "tags": ["kiro", "testing", "quality"], "files": ["testing.md"] }, { "name": "@username/windsurf-rules", "version": "1.0.0", "description": "Windsurf coding rules for React projects", "format": "windsurf", "author": "Your Name", "license": "MIT", "tags": ["windsurf", "react", "frontend"], "files": [".windsurfrules"] }, { "name": "@company/private-package", "version": "1.0.0", "description": "A private package only accessible to organization members", "format": "claude", "subtype": "skill", "author": "Company Team", "organization": "my-company", "private": true, "license": "Proprietary", "files": ["internal-skill.md", "README.md"] }, { "name": "@username/multi-package-example", "version": "1.0.0", "description": "Multi-package manifest example", "author": "Your Name", "license": "MIT", "repository": "https://github.com/username/multi-package", "packages": [ { "name": "@username/package-one", "version": "1.0.0", "description": "First package in the multi-package manifest", "format": "claude", "subtype": "skill", "files": ["package-one/SKILL.md"] }, { "name": "@username/package-two", "version": "1.0.0", "description": "Second package with different settings", "format": "cursor", "private": true, "files": ["package-two/.cursor/rules/main.mdc"] } ] }, { "name": "@username/multi-package-with-collection", "version": "1.0.0", "description": "Repository with both packages and a collection", "author": "Your Name", "license": "MIT", "packages": [ { "name": "typescript-rules", "version": "1.0.0", "description": "TypeScript coding standards", "format": "cursor", "subtype": "rule", "tags": ["typescript", "cursor"], "files": [".cursor/rules/typescript.mdc"] }, { "name": "react-patterns", "version": "1.0.0", "description": "React best practices", "format": "claude", "subtype": "skill", "tags": ["react", "best-practices"], "files": [".claude/skills/react-patterns/SKILL.md"] } ], "collections": [ { "id": "fullstack-setup", "name": "Full Stack Setup", "description": "Complete full-stack development setup with TypeScript and React", "version": "1.0.0", "category": "development", "tags": ["typescript", "react", "fullstack"], "icon": "🚀", "packages": [ { "packageId": "typescript-rules", "version": "^1.0.0", "required": true, "reason": "TypeScript coding standards for the project" }, { "packageId": "react-patterns", "version": "^1.0.0", "required": true, "reason": "React component best practices" } ] } ] } ] } -
SKILL.md 34.5 KB
--- name: prpm-json-best-practices description: Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints --- # PRPM JSON Best Practices You are an expert at creating and maintaining `prpm.json` package manifests for PRPM (Prompt Package Manager). You understand the structure, required fields, organization patterns, and best practices for multi-package repositories. ## When to Apply This Skill **Use when:** - Creating a new `prpm.json` manifest for publishing packages - Maintaining existing `prpm.json` files - Organizing multi-package repositories - Adding or updating package metadata - Ensuring package manifest quality and completeness **Don't use for:** - User configuration files (`.prpmrc`) - those are for users - Lockfiles (`prpm.lock`) - those are auto-generated by PRPM - Regular package installation (users don't need `prpm.json`) - Dependencies already tracked in lockfiles ## Core Purpose `prpm.json` is **only needed if you're publishing packages**. Regular users installing packages from the registry don't need this file. Use `prpm.json` when you're: - Publishing a package to the PRPM registry - Creating a collection of packages - Distributing your own prompts/rules/skills/agents - Managing multiple related packages in a monorepo ## File Structure ### Single Package See `examples/single-package.json` for complete structure. **Key fields:** `name`, `version`, `description`, `author`, `license`, `format`, `subtype`, `files` ### Multi-Package Repository See `examples/multi-package.json` for complete structure. **Use when:** Publishing multiple related packages from one repo **Key difference:** Top-level `packages` array with individual package definitions ### Collections Repository See `examples/collections-repository.json` for complete structure. **Use when:** Bundling existing published packages into curated collections **Key points:** - `collections` array references packages by `packageId` (not files) - Each collection has `id`, `name`, `description`, `packages` - Packages can be `required: true` (default) or `false` (optional) - Use version ranges (`^1.0.0`) or `latest` - Add `reason` to explain why package is included ### Packages + Collections (Combined) See `examples/packages-with-collections.json` for complete structure. **Use when:** Publishing packages AND creating collections that bundle them **Key points:** - Define packages in `packages` array with files - Define collections in `collections` array referencing those packages - Collections can reference both local packages and external ones - Publish both individual packages and collection bundles from same repo ## Required Fields ### Top-Level (Single Package) | Field | Type | Required | Description | | ------------- | -------- | -------- | ------------------------------------------------------------------------------- | | `name` | string | **Yes** | Package name (kebab-case, unique in registry) | | `version` | string | **Yes** | Semver version (e.g., `1.0.0`) | | `description` | string | **Yes** | Clear description of what the package does | | `author` | string | **Yes** | Author name and optional email | | `license` | string | **Yes** | SPDX license identifier (e.g., `MIT`, `Apache-2.0`) | | `format` | string | **Yes** | Target format: `claude`, `cursor`, `continue`, `windsurf`, etc. | | `subtype` | string | **Yes** | Package type: `agent`, `skill`, `rule`, `slash-command`, `prompt`, `collection` | | `files` | string[] | **Yes** | Array of files to include in package | ### Optional Top-Level Fields | Field | Type | Description | | --------------- | -------- | ------------------------------------------------------------- | | `repository` | string | Git repository URL | | `organization` | string | Organization name (for scoped packages) | | `homepage` | string | Package homepage URL | | `documentation` | string | Documentation URL | | `license_text` | string | Full text of the license file for proper attribution | | `license_url` | string | URL to the license file in the repository | | `tags` | string[] | Searchable tags (kebab-case) | | `keywords` | string[] | Additional keywords for search | | `category` | string | Package category | | `private` | boolean | If `true`, won't be published to public registry | | `dependencies` | object | Package dependencies (name: semver) | | `scripts` | object | Lifecycle scripts (multi-package only) | | `eager` | boolean | If `true`, skill/agent loads at session start (not on-demand) | ### Multi-Package Fields When using `packages` array: | Field | Type | Required | Description | | ------------- | -------- | ----------- | ------------------------------------------ | | `name` | string | **Yes** | Unique package name | | `version` | string | **Yes** | Package version | | `description` | string | **Yes** | Package description | | `format` | string | **Yes** | Package format | | `subtype` | string | **Yes** | Package subtype | | `tags` | string[] | Recommended | Searchable tags | | `files` | string[] | **Yes** | Files to include | | `private` | boolean | No | Mark as private | | `eager` | boolean | No | Load at session start (skills/agents only) | ### Collection Fields When using `collections` array: **Top-level (repository with collections):** - `name`, `version`, `description`, `author`, `license` - **Required** - `repository`, `organization` - Recommended - Note: No `format`, `subtype`, or `files` required at top level **Each collection object:** | Field | Type | Required | Description | | ------------- | -------- | ----------- | ------------------------------------------------------ | | `id` | string | **Yes** | Unique collection identifier (kebab-case, 3-100 chars) | | `name` | string | **Yes** | Display name (3-100 chars) | | `description` | string | **Yes** | What the collection provides (10-500 chars) | | `packages` | array | **Yes** | Array of packages to include (minimum 1) | | `version` | string | Recommended | Semantic version of collection | | `category` | string | Recommended | Collection category (development, testing, etc.) | | `tags` | string[] | Recommended | Searchable tags (kebab-case, 1-10 items) | | `icon` | string | Optional | Emoji or icon (max 10 chars) | **Each package within collection:** | Field | Type | Required | Description | | ----------- | ------- | -------- | --------------------------------------------- | | `packageId` | string | **Yes** | Package to include | | `version` | string | Optional | Version range (^1.0.0, ~2.1.0, 1.0.0, latest) | | `required` | boolean | Optional | Whether package is required (default: true) | | `reason` | string | Optional | Why package is included (max 200 chars) | ## Format and Subtype Values ### Format (Target AI Tool) | Format | Description | | ----------- | ----------------------------- | | `claude` | Claude Code (agents, skills) | | `cursor` | Cursor IDE (rules, MDC files) | | `continue` | Continue.dev extension | | `windsurf` | Windsurf IDE | | `copilot` | GitHub Copilot | | `kiro` | Kiro IDE | | `agents.md` | Agents.md format | | `generic` | Generic/universal format | | `mcp` | Model Context Protocol | ### Subtype (Package Type) | Subtype | Description | Typical Formats | | --------------- | ------------------------ | --------------------- | | `agent` | Autonomous agents | `claude`, `agents.md` | | `skill` | Specialized capabilities | `claude` | | `rule` | IDE rules and guidelines | `cursor`, `windsurf` | | `slash-command` | Slash commands | `cursor`, `continue` | | `prompt` | Prompt templates | `generic` | | `collection` | Package collections | Any | | `chatmode` | Chat modes | `kiro` | | `tool` | MCP tools | `mcp` | ## Eager vs Lazy Activation Skills and agents can be configured to load eagerly (at session start) or lazily (on-demand when relevant). ### When to Use Eager **Use `eager: true` when:** - The skill should ALWAYS be active (coding standards, style guides) - Critical behavior that must never be skipped - Small, foundational skills with minimal token cost **Keep lazy (default) when:** - Specialized skills for specific contexts - Large skills with significant token overhead - Skills that only apply to certain file types ### Setting Eager in prpm.json **Package-level:** ```json { "name": "code-style-enforcer", "version": "1.0.0", "format": "claude", "subtype": "skill", "eager": true, "files": [".claude/skills/code-style/SKILL.md"] } ``` **File-level (enhanced files format):** ```json { "files": [ { "path": ".claude/skills/critical-skill/SKILL.md", "format": "claude", "subtype": "skill", "eager": true }, { "path": ".claude/skills/optional-skill/SKILL.md", "format": "claude", "subtype": "skill", "eager": false } ] } ``` ### Precedence When installing, the final eager setting is determined by: 1. CLI flag (`--eager`/`--lazy`) - highest priority 2. File-level `eager` setting (enhanced files) 3. Package-level `eager` setting 4. Default: lazy (false) ### Applicable Subtypes | Subtype | Supports Eager | | --------------- | -------------- | | `skill` | Yes | | `agent` | Yes | | `rule` | No | | `slash-command` | No | | `hook` | No | Eager loading only affects progressive disclosure formats (agents.md, gemini.md, claude.md, aider). ## Tags Best Practices ### Tag Structure - Use **kebab-case** for all tags - Be **specific** and **searchable** - Include 3-8 tags per package - Combine technology, domain, and purpose tags ### Tag Categories **Technology Tags:** - Languages: `typescript`, `python`, `javascript`, `rust` - Frameworks: `react`, `nextjs`, `fastify`, `django` - Tools: `aws`, `docker`, `kubernetes`, `postgresql` **Domain Tags:** - `deployment`, `testing`, `ci-cd`, `database` - `infrastructure`, `cloud`, `monitoring` - `documentation`, `code-review`, `security` **Purpose Tags:** - `troubleshooting`, `debugging`, `best-practices` - `automation`, `quality-assurance`, `performance` - `architecture`, `design-patterns` **Meta Tags:** - `meta` - For packages about creating packages - `prpm-internal` - For internal/private packages - `prpm-development` - For PRPM development itself ### Tag Examples **Good Tags:** ```json { "tags": ["typescript", "type-safety", "code-quality", "best-practices", "static-analysis"] } ``` **Poor Tags:** ```json { "tags": [ "code", // Too generic "stuff", // Meaningless "TypeScript", // Wrong case "type_safety" // Wrong format (use kebab-case) ] } ``` ## Organization Best Practices ### Multi-Package Organization **Order packages by:** 1. **Privacy** - Private packages first 2. **Format** - Group by format (claude, cursor, etc.) 3. **Subtype** - Group by subtype (agent, skill, rule) **Example organization:** ```json { "packages": [ // Private > Claude > Agents { "name": "internal-agent", "private": true, "format": "claude", "subtype": "agent" }, // Private > Claude > Skills { "name": "internal-skill", "private": true, "format": "claude", "subtype": "skill" }, // Private > Cursor > Rules { "name": "internal-rule", "private": true, "format": "cursor", "subtype": "rule" }, // Public > Claude > Skills { "name": "public-skill", "format": "claude", "subtype": "skill" }, // Public > Cursor > Rules { "name": "public-rule", "format": "cursor", "subtype": "rule" } ] } ``` ### Naming Conventions **Package Names:** - Use **kebab-case**: `my-awesome-skill` - Be **descriptive**: `typescript-type-safety` not `ts-types` - Avoid duplicates across formats: use suffixes if needed - `format-conversion-agent` (Claude agent) - `format-conversion` (Cursor rule) **File Paths:** - Use **full paths from project root** (where prpm.json lives) - Agents: `.claude/agents/name.md` - Skills: `.claude/skills/name/SKILL.md` - Rules: `.cursor/rules/name.mdc` - Commands: `.claude/commands/category/name.md` ## Version Management ### Semver Guidelines Follow semantic versioning: - **Major (1.0.0 → 2.0.0)**: Breaking changes - **Minor (1.0.0 → 1.1.0)**: New features, backward compatible - **Patch (1.0.0 → 1.0.1)**: Bug fixes, backward compatible ### Version Bumping When to bump versions: - **Patch**: Bug fixes, typo corrections, minor improvements - **Minor**: New sections, additional examples, new features - **Major**: Complete rewrites, breaking changes, renamed fields ### Keep Versions in Sync For multi-package repos, keep related packages in sync: ```json { "packages": [ { "name": "pkg-one", "version": "1.2.0" }, { "name": "pkg-two", "version": "1.2.0" }, { "name": "pkg-three", "version": "1.2.0" } ] } ``` ## File Management ### Files Array **CRITICAL: File paths must be full paths from project root (where prpm.json lives).** **Required:** - List all files to include in the package - Use **full paths from project root** - not relative to destination directories - Paths should start with `.claude/`, `.cursor/`, etc. - Include documentation files **Why Full Paths?** File paths in `prpm.json` are used for: 1. **Tarball creation** - Reads files directly from these paths 2. **Snippet extraction** - Shows file preview before install 3. **Installation** - CLI derives destination from format/subtype **Examples:** Claude agent (single file): ```json { "format": "claude", "subtype": "agent", "files": [".claude/agents/my-agent.md"] } ``` Claude skill (multiple files): ```json { "format": "claude", "subtype": "skill", "files": [ ".claude/skills/my-skill/SKILL.md", ".claude/skills/my-skill/EXAMPLES.md", ".claude/skills/my-skill/README.md" ] } ``` Cursor rule: ```json { "format": "cursor", "subtype": "rule", "files": [".cursor/rules/my-rule.mdc"] } ``` Slash command: ```json { "format": "claude", "subtype": "slash-command", "files": [".claude/commands/category/my-command.md"] } ``` ### Enhanced File Format **Advanced:** Files can be objects with metadata instead of simple strings. Useful for packages with multiple files targeting different formats or needing per-file metadata. **Enhanced file object structure:** ```json { "files": [ { "path": ".cursor/rules/typescript.mdc", "format": "cursor", "subtype": "rule", "name": "TypeScript Rules", "description": "TypeScript coding standards and best practices", "tags": ["typescript", "frontend"] }, { "path": ".cursor/rules/python.mdc", "format": "cursor", "subtype": "rule", "name": "Python Rules", "description": "Python best practices for backend development", "tags": ["python", "backend"] } ] } ``` **When to use enhanced format:** - Multi-file packages with different formats/subtypes per file - Need per-file descriptions or tags - Want to provide display names for individual files - Building collection packages with mixed content types **Enhanced file fields:** | Field | Required | Description | | ------------- | -------- | ----------------------------------------------- | | `path` | **Yes** | Relative path to file from project root | | `format` | **Yes** | File's target format (`cursor`, `claude`, etc.) | | `subtype` | No | File's subtype (`rule`, `skill`, `agent`, etc.) | | `name` | No | Display name for this file | | `description` | No | Description of what this file does | | `tags` | No | File-specific tags (array of strings) | **Note:** Cannot mix simple strings and objects in the same `files` array. Use all strings OR all objects, not both. **Common Mistake:** ```json { // ❌ WRONG - Relative paths without directory prefix "files": ["agents/my-agent.md"] // Will fail to find file // ✅ CORRECT - Full path from project root "files": [".claude/agents/my-agent.md"] } ``` ### File Verification Always verify files exist: ```bash # Check all files in prpm.json exist for file in $(cat prpm.json | jq -r '.packages[].files[]'); do if [ ! -f "$file" ]; then echo "Missing: $file" fi done ``` ## Duplicate Detection ### Check for Duplicate Names Run this check before committing: ```bash # Check for duplicate package names cat prpm.json | jq -r '.packages[].name' | sort | uniq -d ``` If output is empty, no duplicates exist. If names appear, you have duplicates to resolve. ### Resolving Duplicates **Bad:** ```json { "packages": [ { "name": "typescript-safety", "format": "claude" }, { "name": "typescript-safety", "format": "cursor" } ] } ``` **Good:** ```json { "packages": [ { "name": "typescript-safety", "format": "claude", "subtype": "skill" }, { "name": "typescript-safety-rule", "format": "cursor", "subtype": "rule" } ] } ``` ## Conversion Hints (Advanced) **Purpose:** Help improve quality when converting packages to other formats. The `conversion` field provides format-specific hints for cross-format transformations. **Note:** This is an advanced feature primarily used by format conversion tools. Most packages don't need this. **Structure:** ```json { "name": "my-package", "version": "1.0.0", "format": "claude", "conversion": { "cursor": { "alwaysApply": false, "priority": "high", "globs": ["**/*.ts", "**/*.tsx"] }, "kiro": { "inclusion": "fileMatch", "fileMatchPattern": "**/*.ts", "domain": "typescript", "tools": ["fs_read", "fs_write"], "mcpServers": { "database": { "command": "mcp-server-postgres", "args": [], "env": { "DATABASE_URL": "${DATABASE_URL}" } } } }, "copilot": { "applyTo": ["src/**", "lib/**"], "excludeAgent": "code-review" } } } ``` **Supported conversion hints:** ### Cursor Hints ```json { "conversion": { "cursor": { "alwaysApply": boolean, // Whether rule should always apply "priority": "high|medium|low", // Rule priority level "globs": ["**/*.ts"] // File patterns to auto-attach } } } ``` ### Claude Hints ```json { "conversion": { "claude": { "model": "sonnet|opus|haiku|inherit", // Preferred model "tools": ["Read", "Write"], // Allowed tools "subagentType": "format-conversion" // Subagent type if agent } } } ``` ### Kiro Hints ```json { "conversion": { "kiro": { "inclusion": "always|fileMatch|manual", // When to include "fileMatchPattern": "**/*.ts", // Pattern for fileMatch mode "domain": "typescript", // Domain category "tools": ["fs_read", "fs_write"], // Available tools "mcpServers": { // MCP server configs "database": { "command": "mcp-server-postgres", "args": [], "env": { "DATABASE_URL": "${DATABASE_URL}" } } } } } } ``` ### Copilot Hints ```json { "conversion": { "copilot": { "applyTo": "src/**", // Path patterns "excludeAgent": "code-review|coding-agent" // Agent to exclude } } } ``` ### Continue Hints ```json { "conversion": { "continue": { "alwaysApply": boolean, // Always apply rule "globs": ["**/*.ts"], // File patterns "regex": ["import.*from"] // Regex patterns } } } ``` ### Windsurf Hints ```json { "conversion": { "windsurf": { "characterLimit": 12000 // Warn if exceeding limit } } } ``` ### Agents.md Hints ```json { "conversion": { "agentsMd": { "project": "my-project", // Project name "scope": "backend" // Scope/domain } } } ``` **When to use conversion hints:** - Publishing cross-format packages that need specific settings per format - Format conversion tools need guidance on how to transform content - Package behavior should change based on target format - Want to preserve format-specific metadata during conversions ## Common Patterns ### Private Internal Packages ```json { "name": "internal-tool", "version": "1.0.0", "description": "Internal development tool", "private": true, "format": "claude", "subtype": "skill", "tags": ["prpm-internal", "development"], "files": [".claude/skills/internal-tool/SKILL.md"] } ``` ### Meta Packages (Creating Other Packages) ```json { "name": "creating-skills", "version": "1.0.0", "description": "Guide for creating effective Claude Code skills", "format": "claude", "subtype": "skill", "tags": ["meta", "claude-code", "skills", "documentation", "best-practices"], "files": [".claude/skills/creating-skills/SKILL.md"] } ``` ### Cross-Format Packages When you have the same content for multiple formats: ```json { "packages": [ { "name": "format-conversion-agent", "format": "claude", "subtype": "agent", "description": "Agent for converting between AI prompt formats", "files": [".claude/agents/format-conversion.md"] }, { "name": "format-conversion", "format": "cursor", "subtype": "rule", "description": "Rule for converting between AI prompt formats", "files": [".cursor/rules/format-conversion.mdc"] } ] } ``` ### Collections in prpm.json Collections CAN be defined in prpm.json alongside packages using the `collections` array. Collections bundle multiple packages together for easier installation. **Example with both packages and collections:** ```json { "name": "my-prompts-repo", "author": "Your Name", "license": "MIT", "packages": [ { "name": "typescript-rules", "version": "1.0.0", "description": "TypeScript best practices", "format": "cursor", "subtype": "rule", "tags": ["typescript"], "files": [".cursor/rules/typescript.mdc"] } ], "collections": [ { "id": "my-dev-setup", "name": "My Development Setup", "description": "Complete development setup with TypeScript and React", "version": "1.0.0", "category": "development", "tags": ["typescript", "react"], "packages": [ { "packageId": "typescript-strict", "version": "^1.0.0", "required": true, "reason": "Enforces strict TypeScript type safety" }, { "packageId": "react-best-practices", "version": "^2.0.0", "required": true } ] } ] } ``` For more details on creating collections, see the PRPM documentation at https://docs.prpm.dev or run `prpm help collections`. **Summary:** `prpm.json` can contain both packages (skills, agents, rules, slash-commands, etc.) and collections. ## Lifecycle Scripts **IMPORTANT:** The `scripts` field only applies to **multi-package manifests** (prpm.json with a `packages` array). It does NOT work in single-package manifests. Use the `scripts` field to run commands automatically during package operations, particularly for building TypeScript hooks before publishing. ### When to Use Scripts **Primary use case: Building TypeScript Hooks** If your packages include Claude Code hooks written in TypeScript, you MUST build them to JavaScript before publishing: ```json { "name": "my-packages", "license": "MIT", "scripts": { "prepublishOnly": "cd packages/hooks && npm run build" }, "packages": [ { "name": "my-hook", "version": "1.0.0", "format": "claude", "subtype": "hook", "files": [ ".claude/hooks/my-hook/hook.ts", ".claude/hooks/my-hook/hook.json", ".claude/hooks/my-hook/dist/hook.js" ] } ] } ``` ### Available Script Types | Script | When it Runs | Use Case | | ---------------- | --------------------------------- | ---------------------------------------------- | | `prepublishOnly` | Before `prpm publish` only | **Recommended** - Build hooks, compile assets | | `prepublish` | Before publish AND on npm install | **Not recommended** - causes unexpected builds | **Always use `prepublishOnly` instead of `prepublish`** to avoid running builds when users install your packages. ### prepublishOnly Examples **Single hook:** ```json { "scripts": { "prepublishOnly": "cd .claude/hooks/my-hook && npm run build" } } ``` **Multiple hooks:** ```json { "scripts": { "prepublishOnly": "cd .claude/hooks/hook-one && npm run build && cd ../hook-two && npm run build" } } ``` **With tests:** ```json { "scripts": { "prepublishOnly": "npm test && cd packages/hooks && npm run build" } } ``` ### What Happens During Publishing When you run `prpm publish`: 1. PRPM checks for `scripts.prepublishOnly` in your prpm.json 2. If found, runs the script from the directory containing prpm.json 3. If script succeeds (exit code 0), publishing continues 4. If script fails (non-zero exit code), publishing is aborted **Script execution details:** - Working directory: Same directory as prpm.json - Timeout: 5 minutes (300,000ms) default - Environment: Inherits your shell's environment variables - Output: Shown in real-time ### Best Practices for Scripts **DO:** - ✅ Use `prepublishOnly` for building hooks - ✅ Chain commands with `&&` for dependencies: `npm test && npm run build` - ✅ Keep scripts fast (under 1 minute if possible) - ✅ Test scripts locally before publishing **DON'T:** - ❌ Use `prepublish` (runs on install too) - ❌ Forget to build hooks before publishing - ❌ Use scripts in single-package manifests (not supported) - ❌ Put long-running operations in scripts ### Common Patterns **Hooks in packages/ directory:** ```json { "scripts": { "prepublishOnly": "cd packages/hooks && npm run build" } } ``` **Hooks in .claude/ directory:** ```json { "scripts": { "prepublishOnly": "cd .claude/hooks/my-hook && npm run build" } } ``` **Build multiple components:** ```json { "scripts": { "prepublishOnly": "npm run build:hooks && npm run build:assets" } } ``` ### Debugging Script Failures If your prepublishOnly script fails: 1. **Check the output** - Error messages show what went wrong 2. **Run manually** - Test the exact command in your terminal 3. **Verify working directory** - Scripts run from prpm.json location 4. **Check dependencies** - Ensure npm packages are installed **Example debugging:** ```bash # Test your prepublishOnly script manually cd /path/to/prpm.json/directory cd packages/hooks && npm run build # If it works manually but fails in PRPM, check: # - Working directory assumptions # - Environment variables # - Installed dependencies ``` ### Why This Matters **Without prepublishOnly:** - You might forget to build hooks before publishing - Published packages contain stale/outdated JavaScript - Users install broken hooks - Manual builds are error-prone **With prepublishOnly:** - Hooks automatically build before every publish - JavaScript always matches TypeScript source - Prevents publishing broken code - Consistent, reliable publishing workflow ## Validation Checklist Before publishing, verify: **Required Fields:** - [ ] All packages have `name`, `version`, `description` - [ ] All packages have `format` and `subtype` - [ ] All packages have `files` array - [ ] Top-level has `author` and `license` **File Verification:** - [ ] All files in `files` arrays exist - [ ] File paths are relative to repo root - [ ] No missing or broken file references **No Duplicates:** - [ ] No duplicate package names - [ ] Package names are unique across entire manifest **Tags:** - [ ] Tags use kebab-case - [ ] 3-8 relevant tags per package - [ ] Tags include technology, domain, and purpose **Organization:** - [ ] Private packages listed first - [ ] Packages grouped by format and subtype - [ ] Consistent versioning across related packages ## Lockfile Management ### Understanding prpm.lock The `prpm.lock` file is **auto-generated** and tracks installed packages. It serves as the source of truth for what's installed in your project. **IMPORTANT:** Do NOT add packages to `prpm.json` if they already exist in `prpm.lock`: - `prpm.lock` tracks **installed dependencies** (packages you use) - `prpm.json` defines **published packages** (packages you create and share) ### When to Use prpm.json vs prpm.lock **Use `prpm.json` when:** - You're creating a package to publish to the registry - You want to define metadata for YOUR packages - You're setting up a multi-package repository **Use `prpm.lock` (auto-generated) when:** - You install packages with `prpm install` - You want to track which packages are installed - You want reproducible installations across environments ### Common Mistake: Duplicating Dependencies **❌ WRONG - Don't add installed packages to prpm.json:** ```json // prpm.json { "name": "my-project", "packages": [ { "name": "typescript-safety", // ❌ This is an INSTALLED package "version": "1.0.0", "format": "cursor", "subtype": "rule", "files": [".cursor/rules/typescript-safety.mdc"] } ] } ``` ```json // prpm.lock (auto-generated) { "packages": { "@prpm/typescript-safety": { // ✅ Already tracked here "version": "1.0.0", "format": "cursor", "subtype": "rule" } } } ``` **✅ CORRECT - prpm.json only for YOUR packages:** ```json // prpm.json - Only YOUR packages you're publishing { "name": "my-project", "packages": [ { "name": "my-custom-rule", // ✅ This is YOUR package "version": "1.0.0", "format": "cursor", "subtype": "rule", "files": [".cursor/rules/my-custom-rule.mdc"] } ] } ``` ```json // prpm.lock - Installed dependencies (auto-generated) { "packages": { "@prpm/typescript-safety": { // ✅ Installed from registry "version": "1.0.0", "format": "cursor", "subtype": "rule" } } } ``` ### Key Principles 1. **Lockfile is Auto-Generated** - Never manually edit `prpm.lock` 2. **Separation of Concerns**: - `prpm.json` = What you PUBLISH - `prpm.lock` = What you INSTALL 3. **Check Lockfile First** - Before adding to `prpm.json`, check if it's already in `prpm.lock` 4. **Trust the Lockfile** - It's the authoritative record of installed packages ### Workflow Example ```bash # Install a package (updates prpm.lock automatically) prpm install @prpm/typescript-safety # This creates/updates prpm.lock - DO NOT add to prpm.json! # Only create prpm.json entries for packages YOU create: # 1. Create your custom rule/skill/agent # 2. Add entry to prpm.json # 3. Publish with: prpm publish ``` ## Publishing Workflow ### 1. Validate Manifest ```bash # Validate JSON syntax cat prpm.json | jq . > /dev/null # Check for duplicates cat prpm.json | jq -r '.packages[].name' | sort | uniq -d # Verify files exist # (see File Verification section) ``` ### 2. Bump Versions Update version numbers for changed packages. ### 3. Test Locally ```bash # Test package installation prpm install . --dry-run ``` ### 4. Publish ```bash # Publish all packages prpm publish # Or publish specific package prpm publish --package my-skill ``` ## Common Mistakes to Avoid ### ❌ Missing Required Fields ```json { "name": "my-skill" // Missing: version, description, format, subtype, files } ``` ### ❌ Wrong Tag Format ```json { "tags": ["TypeScript", "Code_Quality", "bestPractices"] // Should be: ["typescript", "code-quality", "best-practices"] } ``` ### ❌ Duplicate Names ```json { "packages": [ { "name": "my-skill", "format": "claude" }, { "name": "my-skill", "format": "cursor" } // Second should be: "my-skill-rule" or similar ] } ``` ### ❌ Missing Files ```json { "files": [".claude/skills/my-skill/SKILL.md"] // But .claude/skills/my-skill/SKILL.md doesn't exist in the repo } ``` ### ❌ Absolute Paths ```json { "files": ["/Users/me/project/.claude/skills/my-skill/SKILL.md"] // Should be: ".claude/skills/my-skill/SKILL.md" (relative to project root) } ``` ### ❌ Missing Directory Prefix ```json { "files": ["agents/my-agent.md"] // Should be: ".claude/agents/my-agent.md" (include .claude/ prefix) } ``` ## Remember - `prpm.json` is **only for publishing YOUR packages/collections**, not for installed dependencies - **Never add packages from `prpm.lock` to `prpm.json`** - they serve different purposes - `prpm.lock` tracks what you INSTALL, `prpm.json` defines what you PUBLISH - Use `collections` array to bundle existing packages (references by packageId) - Use `packages` array to define packages with files - Can combine both `packages` and `collections` in same repo - Always validate before committing - Keep versions in sync for related packages - Use consistent, searchable tags - Verify all file paths exist - Check for duplicate names - Follow semver for version management **Goal:** Create maintainable, well-organized package manifests and curated collections that are easy to publish and discover in the PRPM registry.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.