plugin-marketplace-creator
Create and configure Claude Code plugin marketplaces hosted on GitHub. Use this skill when users want to set up a new plugin marketplace repository, add plugins to an existing marketplace, configure team distribution settings, or troubleshoot marketplace issues. Triggers include "create a plugin marketplace", "set up a marketplace on GitHub", "add plugins to my marketplace", "configure marketplace for my team", or "distribute Claude Code plugins".
What this skill does
# Plugin Marketplace Creator
Create Claude Code plugin marketplaces—catalogs that distribute plugins to teams and communities via GitHub.
## Quick Start
1. Run `scripts/init_marketplace.py <name> --path <output-dir>` to scaffold
2. Edit `.claude-plugin/marketplace.json` to add plugins
3. Push to GitHub
4. Users install via `/plugin marketplace add owner/repo`
## Marketplace Structure
```
marketplace-repo/
├── .claude-plugin/
│ └── marketplace.json # Required: marketplace definition
├── plugins/ # Optional: local plugins
│ └── my-plugin/
│ └── .claude-plugin/
│ └── plugin.json
└── README.md
```
## Plugin Structure with Skills
Plugins containing skills should have this structure:
```
plugins/my-plugin/
├── .claude-plugin/
│ └── plugin.json # NO "skills" field - skills are auto-discovered
└── skills/
└── my-skill/
└── SKILL.md
```
**Important:** Do NOT add a `skills` field to plugin.json. Skills are automatically discovered from the `skills/` directory.
## Marketplace JSON Schema
### Required Fields
```json
{
"name": "marketplace-name",
"owner": {
"name": "Team Name",
"email": "[email protected]"
},
"plugins": []
}
```
### Optional Metadata
```json
{
"metadata": {
"description": "Brief description",
"version": "1.0.0",
"pluginRoot": "./plugins"
}
}
```
### Reserved Names (cannot use)
`claude-code-marketplace`, `claude-code-plugins`, `claude-plugins-official`, `anthropic-marketplace`, `anthropic-plugins`, `agent-skills`, `life-sciences`
## Plugin Entry Schema
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `name` | string | Yes | Kebab-case identifier |
| `source` | string\|object | Yes | Where to fetch plugin |
| `description` | string | No | Brief description |
| `version` | string | No | Semantic version |
| `author` | object | No | `{name, email}` |
| `category` | string | No | For organization |
| `keywords` | array | No | Search tags |
| `strict` | boolean | No | Require plugin.json (default: true) |
### Source Types
**Local path:**
```json
{"source": "./plugins/my-plugin"}
```
**GitHub:**
```json
{"source": {"source": "github", "repo": "owner/repo"}}
```
**Git URL:**
```json
{"source": {"source": "url", "url": "https://gitlab.com/team/plugin.git"}}
```
## Complete Example
```json
{
"name": "company-tools",
"owner": {
"name": "DevTools Team",
"email": "[email protected]"
},
"metadata": {
"description": "Internal development tools",
"version": "1.0.0"
},
"plugins": [
{
"name": "code-formatter",
"source": "./plugins/formatter",
"description": "Auto-format code on save",
"version": "1.0.0",
"category": "development"
},
{
"name": "deploy-tools",
"source": {"source": "github", "repo": "company/deploy-plugin"},
"description": "Deployment automation",
"category": "devops"
}
]
}
```
## Team Configuration
Add to project's `.claude/settings.json` for automatic installation:
```json
{
"extraKnownMarketplaces": {
"team-tools": {
"source": {"source": "github", "repo": "org/claude-plugins"}
}
},
"enabledPlugins": {
"code-formatter@team-tools": true
}
}
```
## Scripts
- **init_marketplace.py** - Create new marketplace with proper structure
- **validate_marketplace.py** - Validate marketplace.json and plugin sources
- **add_plugin.py** - Add plugin entries to existing marketplace
## Workflow
### Creating a New Marketplace
**Pre-flight checks (REQUIRED before running init script):**
1. **Check git config for user identity:**
```bash
git config --get user.name
git config --get user.email
```
2. **If either is not set, ASK THE USER for their name and email** before proceeding. Use these values with `--owner-name` and `--owner-email` flags.
3. **Check if target directory already has a git repo:**
```bash
ls -la <target-path>/.git 2>/dev/null
```
If `.git` exists, do NOT run `git init` when setting up the repository.
```bash
# 1. Initialize (script auto-detects git config for owner info)
python scripts/init_marketplace.py my-marketplace --path ./output
# Or with explicit owner info if git config is not set:
python scripts/init_marketplace.py my-marketplace --path ./output \
--owner-name "Your Name" --owner-email "[email protected]"
# 2. Validate
python scripts/validate_marketplace.py ./output
# 3. Push to GitHub (skip git init if .git already exists)
cd output
# Only run 'git init' if there's no existing .git directory
git add -A && git commit -m "Initial"
# Create repo on GitHub and push
# 4. Test in Claude Code
# /plugin marketplace add owner/my-marketplace
```
### Adding Plugins
```bash
# Add local plugin
python scripts/add_plugin.py ./marketplace --name my-plugin --source ./plugins/my-plugin
# Add GitHub plugin
python scripts/add_plugin.py ./marketplace --name external --source github:org/repo
```
## Troubleshooting
**Marketplace not loading**: Verify `.claude-plugin/marketplace.json` exists at repo root.
**Plugin install fails**: Check source is accessible. For private repos, ensure authentication.
**Team can't see marketplace**: Verify `extraKnownMarketplaces` in `.claude/settings.json`.
## References
- `references/plugin-schema.md` - Complete plugin.json schema
- `references/examples.md` - Additional marketplace examples
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.