marketplace-creator
Guide for creating and managing Claude Code marketplaces. Use when creating a new marketplace, updating marketplace configuration, adding plugins to a marketplace, or validating marketplace.json files.
What this skill does
# Marketplace Creator
This skill provides comprehensive guidance for creating, managing, and validating Claude Code marketplace configurations.
## About Marketplaces
Marketplaces are curated collections of plugins that can be distributed and installed together. A marketplace is defined by a `marketplace.json` file that lists available plugins with their sources, versions, and metadata.
### What Marketplaces Provide
1. **Plugin Discovery** - Central catalog of related plugins
2. **Version Management** - Track plugin versions and updates
3. **Easy Distribution** - Users install from a single marketplace URL
4. **Curation** - Organize plugins by theme, purpose, or organization
## Marketplace Development Workflow
Follow these steps when working with marketplaces:
1. Understand marketplace requirements and scope
2. Initialize marketplace configuration
3. Add plugins to the marketplace
4. Validate marketplace structure
5. Test marketplace installation
6. Distribute marketplace
### Step 1: Understanding Marketplace Requirements
Before creating a marketplace, clarify:
- What plugins should be included?
- Who is the target audience (personal, team, public)?
- Will plugins be hosted on GitHub, local paths, or other sources?
- What categorization or organization makes sense?
Ask questions to gather concrete requirements:
- "What plugins should this marketplace include?"
- "Will this be for personal use, team distribution, or public sharing?"
- "Are the plugins already created, or do they need to be built?"
- "How should the plugins be categorized or grouped?"
### Step 2: Initialize Marketplace Configuration
Create a new `marketplace.json` file with the required structure.
**For detailed initialization steps:**
- See [references/marketplace-structure.md](references/marketplace-structure.md) for complete setup instructions and field requirements
- Use the `init_marketplace.py` script for quick setup:
```bash
python3 skills/marketplace-creator/scripts/init_marketplace.py
```
The script will:
- Create marketplace.json with proper structure
- Prompt for owner name and email
- Add example plugin entry (to be customized)
- Include comments explaining each field
**Minimum Required Fields:**
```json
{
"name": "marketplace-name",
"owner": {
"name": "Owner Name",
"email": "[email protected]"
},
"description": "Marketplace description",
"plugins": []
}
```
### Step 3: Add Plugins to the Marketplace
Add plugin entries to the `plugins` array. Each plugin requires:
- `name` - Plugin identifier
- `source` - Where to find the plugin (GitHub, local path, URL)
- `description` - What the plugin does
- `version` - Semantic version (e.g., "1.0.0")
- `author` - Plugin author information
**Helper script for adding plugins:**
```bash
python3 skills/marketplace-creator/scripts/add_plugin_to_marketplace.py
```
**For detailed plugin entry formats and source options:**
- See [references/marketplace-structure.md](references/marketplace-structure.md) for all source format examples
**Common Source Formats:**
1. **GitHub Repository (recommended for public plugins):**
```json
"source": {
"source": "github",
"repo": "owner/repository"
}
```
2. **Relative Path (local installations only):**
```json
"source": "./plugins/my-plugin"
```
3. **Git Repository URL:**
```json
"source": {
"source": "url",
"url": "https://gitlab.com/team/plugin.git"
}
```
4. **Direct Marketplace URL:**
```json
"source": "https://example.com/path/to/marketplace.json"
```
### Step 4: Validate Marketplace Structure
Use the validation script to check marketplace configuration:
```bash
python3 skills/marketplace-creator/scripts/validate_marketplace.py
```
The validator checks:
- JSON syntax validity
- Required fields are present
- Source format correctness (GitHub objects vs strings)
- No placeholder values remain
- Author format consistency
- Semantic versioning compliance
**For complete validation checklist:**
- See validation section in [references/marketplace-structure.md](references/marketplace-structure.md)
### Step 5: Test Marketplace Installation
Test the marketplace locally before distribution:
```bash
# Install from local marketplace.json
claude plugin install /path/to/marketplace.json
# Or install specific plugin from marketplace
claude plugin install /path/to/marketplace.json --plugin plugin-name
```
Verify:
- All plugins install correctly
- Skills/commands/agents are available
- No configuration errors or warnings
### Step 6: Distribute Marketplace
Choose distribution method:
**Option 1: Git Repository**
- Commit marketplace.json to repository
- Users install via: `claude plugin install https://github.com/user/repo/marketplace.json`
**Option 2: Direct URL**
- Host marketplace.json on web server
- Users install via: `claude plugin install https://domain.com/marketplace.json`
**Option 3: Local/Team Distribution**
- Share marketplace.json file or repository
- Users install from local path
## Common Issues and Solutions
### Issue: GitHub URL as String
**Problem:** GitHub repository URLs as strings are not supported in marketplace.json
```json
// ❌ WRONG
"source": "https://github.com/username/plugin-name"
// ✅ CORRECT
"source": {
"source": "github",
"repo": "username/plugin-name"
}
```
### Issue: Relative Paths for Public Distribution
**Problem:** Relative paths only work for local installations
```json
// ⚠️ WARNING - local only
"source": "./plugins/my-plugin"
// ✅ CORRECT - for public distribution
"source": {
"source": "github",
"repo": "username/plugin-name"
}
```
### Issue: Inconsistent Author Format
**Problem:** Author should use consistent object format
```json
// ❌ WRONG - string format
"author": "Username"
// ✅ CORRECT - object format
"author": {
"name": "Username"
}
```
### Issue: Placeholder Values
**Problem:** Template placeholders must be replaced
```json
// ❌ WRONG
"owner": {
"name": "Your Name",
"email": "[email protected]"
}
// ✅ CORRECT
"owner": {
"name": "AnthonyKazyaka",
"email": "[email protected]"
}
```
## Updating Existing Marketplaces
When updating an existing marketplace.json:
1. **Adding a Plugin:**
- Use `add_plugin_to_marketplace.py` script
- Or manually add entry to `plugins` array
- Validate with `validate_marketplace.py`
2. **Updating Plugin Version:**
- Locate plugin entry in `plugins` array
- Update `version` field
- Ensure plugin source reflects new version
3. **Removing a Plugin:**
- Remove plugin entry from `plugins` array
- Validate configuration
4. **Reorganizing Plugins:**
- Consider creating multiple marketplace.json files
- Or use plugin descriptions for categorization
## Best Practices
- **Use semantic versioning** - Follow semver (major.minor.patch)
- **Provide clear descriptions** - Help users understand what each plugin does
- **GitHub sources for public plugins** - More reliable than direct URLs
- **Test before distributing** - Install marketplace locally first
- **Version your marketplace** - Track changes to marketplace itself
- **Document plugin requirements** - Note dependencies or prerequisites
**For detailed structure information:**
- See [references/marketplace-structure.md](references/marketplace-structure.md) for:
- Complete marketplace.json schema
- All source format options
- Field requirements and validation rules
- Example marketplace configurations
**For step-by-step creation guidance:**
- See [references/marketplace-creation-process.md](references/marketplace-creation-process.md) for:
- Detailed workflow for each step
- Decision trees for source format selection
- Testing strategies
- Distribution best practices
## Resources
This skill includes:
- **scripts/validate_marketplace.py** - Automated validation script
- **scripts/init_marketplace.py** - Initialize new marketplace.json
- **scripts/add_plugin_to_marketplace.py** - Add plugin entries iRelated 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.