marketplace-builder
Create and configure Claude Code marketplaces and plugins. Use when the user wants to create a marketplace, publish plugins, set up team plugin distribution, or configure marketplace.json or plugin.json files. Triggers: create marketplace, publish plugin, plugin distribution, marketplace.json, plugin.json, team plugins, share plugins
What this skill does
# Marketplace Builder
A comprehensive guide to creating Claude Code marketplaces and plugins for distributing commands, agents, skills, hooks, and MCP servers.
---
## Quick Reference
### Marketplace vs Plugin Distinction
**Critical concept**: These are NOT the same thing.
| Concept | What It Is | Analogy |
|---------|------------|---------|
| **Marketplace** | JSON catalog listing where plugins live | Library catalog |
| **Plugin** | Packaged collection of components | Book |
| **Components** | Commands, agents, skills, hooks, MCP servers | Chapters |
**Relationship**: One marketplace → many plugins → many components per plugin
**Key insight**: Marketplaces don't HOST plugins. They INDEX them. Plugins can live anywhere (GitHub, GitLab, private git, local paths).
---
### JSON Schema Quick Reference
**Minimal marketplace.json**:
```json
{
"name": "marketplace-name",
"owner": {"name": "Owner Name"},
"plugins": [
{
"name": "plugin-name",
"source": "./path-to-plugin",
"description": "What this plugin does",
"version": "1.0.0"
}
]
}
```
**Minimal plugin.json** (inside `.claude-plugin/`):
```json
{
"name": "plugin-name",
"description": "What this plugin does",
"version": "1.0.0"
}
```
**Team settings.json** (inside `.claude/`):
```json
{
"extraKnownMarketplaces": {
"marketplace-name": {
"source": {"source": "github", "repo": "owner/repo"}
}
},
"enabledPlugins": {
"plugin-name@marketplace-name": true
}
}
```
---
### Source Types
| Type | Syntax | Best For |
|------|--------|----------|
| **GitHub** | `{"source": "github", "repo": "owner/repo"}` | Public plugins |
| **Git URL** | `{"source": "git", "url": "https://..."}` | Private/GitLab |
| **Directory** | `{"source": "directory", "path": "./path"}` | Monorepo |
| **Relative** | `"./path"` | Shorthand for directory |
---
### Command Reference
```bash
# Add a marketplace
/plugin marketplace add owner/repo
/plugin marketplace add https://gitlab.com/org/repo.git
/plugin marketplace add ./local-marketplace
# List marketplaces
/plugin marketplace list
# Update marketplace catalog
/plugin marketplace update marketplace-name
# Browse and install plugins
/plugin # Interactive browser
/plugin install plugin-name@marketplace # Direct install
# Manage plugins
/plugin enable plugin@marketplace
/plugin disable plugin@marketplace
/plugin uninstall plugin@marketplace
# Validate structure
claude plugin validate .
```
---
## 6-Phase Workflow
### Phase 1: Requirements Gathering
**Use AskUserQuestion to understand the user's needs:**
1. **What are you distributing?**
- Commands (slash commands)
- Agents (subagents)
- Skills (model-invoked capabilities)
- Hooks (event handlers)
- MCP servers (external tools)
- Mix of the above
2. **How many plugins?**
- Single plugin
- Multiple related plugins
- Large plugin collection
3. **Who is the audience?**
- Personal use (just me)
- Team (colleagues via git)
- Organization (company-wide)
- Public community
4. **What hosting?**
- GitHub (public or private)
- GitLab or other git service
- Self-hosted git
- Local development only
**Document the answers before proceeding.**
---
### Phase 2: Architecture Decision
Based on requirements, recommend one of these patterns:
#### Pattern A: Basic Marketplace (Single Plugin)
**Use when**: One plugin, simple distribution
```
my-marketplace/
├── .claude-plugin/
│ ├── plugin.json
│ └── marketplace.json
├── commands/
└── agents/
```
#### Pattern B: Monorepo (Multiple Plugins, One Repo)
**Use when**: Related plugins, unified versioning, team ownership
```
company-plugins/
├── .claude-plugin/
│ └── marketplace.json
├── plugins/
│ ├── formatter/
│ │ ├── .claude-plugin/plugin.json
│ │ └── commands/
│ ├── linter/
│ │ ├── .claude-plugin/plugin.json
│ │ └── commands/
│ └── tester/
│ ├── .claude-plugin/plugin.json
│ └── agents/
```
#### Pattern C: Multi-Repo (Plugins in Separate Repos)
**Use when**: Independent plugins, different owners, community collection
```
# Marketplace repo
my-marketplace/
└── .claude-plugin/
└── marketplace.json # Points to other repos
# Plugin repos (separate)
tool-a/
├── .claude-plugin/plugin.json
└── commands/
tool-b/
├── .claude-plugin/plugin.json
└── agents/
```
#### Pattern D: Enterprise (Hybrid Private + Public)
**Use when**: Mix of internal and external tools, strict access control
```json
{
"plugins": [
{"name": "internal-tool", "source": {"source": "git", "url": "https://git.corp/..."}},
{"name": "community-tool", "source": {"source": "github", "repo": "public/tool"}}
]
}
```
**Decision tree**:
- Single plugin? → Pattern A
- Multiple plugins, same team? → Pattern B
- Plugins from different sources? → Pattern C
- Enterprise with private + public? → Pattern D
---
### Phase 3: Plugin Creation
For each plugin, create this structure:
```
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Required: plugin manifest
├── commands/ # Optional: slash commands
│ └── my-command.md
├── agents/ # Optional: subagents
│ └── my-agent.md
├── skills/ # Optional: skills
│ └── my-skill/
│ └── SKILL.md
├── hooks/ # Optional: event handlers
│ └── hooks.json
└── .mcp.json # Optional: MCP servers
```
**Write plugin.json**:
```json
{
"name": "plugin-name",
"description": "Clear description of what this plugin provides",
"version": "1.0.0",
"author": {
"name": "Author Name",
"email": "[email protected]"
},
"homepage": "https://docs.example.com",
"repository": "https://github.com/owner/repo",
"license": "MIT"
}
```
**Naming conventions**:
- Plugin name: `kebab-case` (e.g., `code-formatter`)
- Version: Semantic versioning `MAJOR.MINOR.PATCH`
- Commands: `verb-noun.md` (e.g., `format-code.md`)
- Agents: `role-name.md` (e.g., `code-reviewer.md`)
---
### Phase 4: Marketplace Creation
Create `.claude-plugin/marketplace.json`:
**For monorepo (plugins in same repo)**:
```json
{
"name": "company-tools",
"owner": {
"name": "Company Name",
"email": "[email protected]"
},
"metadata": {
"description": "Company development tools",
"version": "1.0.0",
"pluginRoot": "./plugins"
},
"plugins": [
{
"name": "formatter",
"source": "./plugins/formatter",
"description": "Code formatting tools",
"version": "1.0.0"
},
{
"name": "linter",
"source": "./plugins/linter",
"description": "Code linting tools",
"version": "1.0.0"
}
]
}
```
**For multi-repo (plugins in separate repos)**:
```json
{
"name": "community-collection",
"owner": {
"name": "Community",
"email": "[email protected]"
},
"plugins": [
{
"name": "tool-a",
"source": {
"source": "github",
"repo": "community/tool-a"
},
"description": "Tool A description",
"version": "2.1.0"
},
{
"name": "tool-b",
"source": {
"source": "github",
"repo": "community/tool-b"
},
"description": "Tool B description",
"version": "1.3.0"
}
]
}
```
---
### Phase 5: Distribution Setup
#### For Personal Use
No additional setup. Add marketplace locally:
```bash
/plugin marketplace add ./path-to-marketplace
```
#### For Team Distribution
Add to project's `.claude/settings.json`:
```json
{
"extraKnownMarketplaces": {
"team-tools": {
"source": {
"source": "github",
"repo": "company/claude-plugins"
}
}
},
"enabledPlugins": {
"formatter@team-tools": true,
"linter@team-tools": true
}
}
```
**How it works**:
1. Team member clones project
2. Claude Code reads `.claude/settings.json`
3. Prompts to trust configured marketplaces
4. Prompts to install enabled plugins
5. New team members geRelated 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.