plugin-marketplace
Guide for creating and managing Claude Code plugin marketplaces. Use when setting up a marketplace, validating marketplace.json, or distributing plugins.
What this skill does
# Claude Code Plugin Marketplace
Guide for creating, validating, and managing plugin marketplaces for Claude Code. Includes schema validation, best practices, and automated tools.
## When to Use This Skill
Activate this skill when:
- Creating or editing `.claude-plugin/marketplace.json` files
- Validating marketplace schema compliance
- Setting up plugin repositories with marketplaces
- Troubleshooting marketplace configuration issues
- Converting plugin structures to marketplace format
- Creating plugin entries with advanced features
## Marketplace Schema Overview
### Required Structure
All marketplaces must be located at `.claude-plugin/marketplace.json` in the repository root.
**Required Fields:**
- `name`: Marketplace identifier (kebab-case, lowercase alphanumeric and hyphens only)
- `owner`: Object with maintainer details (`name` required, `email` optional)
- `plugins`: Array of plugin definitions (can be empty)
**Optional Metadata:**
- `metadata.description`: Summary of marketplace purpose
- `metadata.version`: Marketplace version tracking (semantic versioning recommended)
- `metadata.pluginRoot`: Base directory for relative plugin source paths
### Plugin Entry Schema
**IMPORTANT: Schema Relationship**
Plugin entries use the plugin manifest schema with all fields made optional, plus marketplace-specific fields (`source`, `strict`, `category`, `tags`). This means any field valid in a plugin.json file can also be used in a marketplace entry.
- When `strict: false`, the marketplace entry serves as the complete plugin manifest if no plugin.json exists
- When `strict: true` (default), marketplace fields supplement the plugin's own manifest file
Each plugin entry in the `plugins` array requires:
**Mandatory:**
- `name`: Plugin identifier (kebab-case)
- `source`: Location specification (string path or object)
**Standard Metadata:**
- `description`: Brief explanation of plugin functionality
- `version`: Semantic version number
- `author`: Creator information (object with `name`, optional `email`)
- `homepage`: Documentation or project URL
- `repository`: Source control URL
- `license`: SPDX license identifier (e.g., MIT, Apache-2.0)
- `keywords`: Array of discovery and categorization tags
- `category`: Organizational grouping
- `tags`: Additional searchability terms
**Component Configuration:**
- `commands`: Custom paths to command files or directories
- `agents`: Custom paths to agent files
- `hooks`: Custom hooks configuration or path to hooks file
- `mcpServers`: MCP server configurations or path to MCP config
- `skills`: Array of skill directory paths
**Strict Mode Control:**
- `strict`: Boolean (default: `true`)
- `true`: Plugin must include plugin.json; marketplace fields supplement it
- `false`: Marketplace entry serves as complete manifest (no plugin.json needed)
**Dependencies:**
- `dependencies`: Array of plugin names this plugin depends on (format: `"namespace:plugin-name"`)
## Plugin Source Formats
### Relative Path
```json
"source": "./plugins/my-plugin"
```
### Relative Path with pluginRoot
```json
// In marketplace metadata
"metadata": {
"pluginRoot": "./plugins"
}
// In plugin entry
"source": "my-plugin" // Resolves to ./plugins/my-plugin
```
### GitHub Repository
```json
"source": {
"source": "github",
"repo": "owner/plugin-repo",
"path": "optional/subdirectory",
"branch": "main"
}
```
### Git URL
```json
"source": {
"source": "url",
"url": "https://gitlab.com/team/plugin.git",
"branch": "main"
}
```
## Environment Variables
Use `${CLAUDE_PLUGIN_ROOT}` in paths to reference the plugin's installation directory:
```json
{
"skills": [
"${CLAUDE_PLUGIN_ROOT}/skills/my-skill"
],
"commands": [
"${CLAUDE_PLUGIN_ROOT}/commands"
]
}
```
This ensures paths work correctly regardless of installation location.
## Advanced Plugin Entry Features
### Inline Plugin Definitions
Use `strict: false` to define complete plugin manifests inline without requiring plugin.json:
```json
{
"name": "my-plugin",
"source": "./plugins/my-plugin",
"strict": false,
"description": "Complete plugin definition inline",
"version": "1.0.0",
"author": {
"name": "Developer Name"
},
"skills": [
"${CLAUDE_PLUGIN_ROOT}/skills/skill-one",
"${CLAUDE_PLUGIN_ROOT}/skills/skill-two"
]
}
```
### Component Path Override
Customize component locations:
```json
{
"name": "custom-paths",
"source": "./plugins/custom",
"strict": false,
"commands": ["${CLAUDE_PLUGIN_ROOT}/custom-commands"],
"agents": ["${CLAUDE_PLUGIN_ROOT}/custom-agents"],
"hooks": {
"onInstall": "${CLAUDE_PLUGIN_ROOT}/hooks/install.sh"
},
"mcpServers": "${CLAUDE_PLUGIN_ROOT}/mcp-config.json"
}
```
### Metadata Supplementation
With `strict: true`, marketplace entries can add metadata not in plugin.json:
```json
{
"name": "existing-plugin",
"source": "./plugins/existing",
"strict": true,
"category": "development",
"keywords": ["added", "from", "marketplace"],
"homepage": "https://docs.example.com"
}
```
## Validation Workflow
### 1. Schema Validation
Use the provided Nushell script to validate marketplace.json:
```bash
nu ${CLAUDE_PLUGIN_ROOT}/scripts/validate-marketplace.nu .claude-plugin/marketplace.json
```
This validates:
- JSON syntax
- Required fields presence
- Kebab-case naming
- Field type correctness
- Source path accessibility (for relative paths)
### 2. Plugin Entry Validation
Validate individual plugin entries:
```bash
nu ${CLAUDE_PLUGIN_ROOT}/scripts/validate-plugin-entry.nu .claude-plugin/marketplace.json "plugin-name"
```
Checks:
- Required fields (name, source)
- Strict mode consistency
- Dependency references
- Path validity
- Component configuration
### 3. Dependency Graph Validation
Check for circular dependencies and missing dependencies:
```bash
nu ${CLAUDE_PLUGIN_ROOT}/scripts/validate-dependencies.nu .claude-plugin/marketplace.json
```
## Best Practices
### Naming Conventions
- **Marketplace name**: Use your GitHub username or organization (e.g., `vinnie357`)
- **Plugin names**: Use descriptive kebab-case (e.g., `elixir-phoenix`, `rust-tools`, `core-skills`)
- **Categories**: Standardize on common categories: `development`, `language`, `tools`, `frontend`, `backend`, `meta`
### Versioning Strategy
- Use semantic versioning for both marketplace and plugins
- Bump marketplace version when adding/removing plugins
- Bump plugin versions when updating skills or configuration
- Document breaking changes in plugin descriptions
### Dependency Management
- Always declare `dependencies` for plugins that require other plugins
- Keep dependency chains shallow (avoid deep nesting)
- Consider creating a meta-plugin (like `all-skills`) that bundles related plugins
- Use namespace prefixes for dependencies (e.g., `all-skills:core`)
### Strict Mode Decision
**Use `strict: false` when:**
- Creating simple, self-contained plugins
- All configuration is in marketplace.json
- You want centralized management
- Plugin is unlikely to be distributed independently
**Use `strict: true` when:**
- Plugin has complex configuration
- Plugin may be distributed separately
- Plugin has its own versioning lifecycle
- You want to supplement existing plugin.json with marketplace metadata
### Source Path Organization
```json
{
"metadata": {
"pluginRoot": "./plugins"
},
"plugins": [
{
"name": "core",
"source": "core" // Resolves to ./plugins/core
},
{
"name": "external",
"source": {
"source": "github",
"repo": "org/repo"
}
}
]
}
```
## Common Validation Errors
### Error: Invalid kebab-case name
```json
// ❌ Invalid
"name": "myPlugin"
"name": "my_plugin"
"name": "My-Plugin"
// ✅ Valid
"name": "my-plugin"
"name": "core-skills"
```
### Error: Missing required owner field
```json
// ❌ Invalid
{
"name": "marketplace"
}
// ✅ Valid
{
"name": "marketplace",
"owner": {
"name": "Developer Name"
}
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.