plugin-creator
Create complete Claude Code plugins with proper structure including skills, commands, agents, and hooks. Generates plugin manifests and directory structures for distribution. Use when: building plugins, creating plugin packages, distributing skills to marketplace. Activates for: "create plugin", "generate plugin", "new plugin", "plugin package", "make plugin"
What this skill does
# Plugin Creator
Generate complete Claude Code plugins with proper structure and configuration.
## When to Use
- Creating shareable plugin packages
- Building complete tool collections
- Organizing related skills/commands/agents
- Distributing functionality to teams
- Contributing to plugin marketplaces
## Plugin Structure
A complete plugin includes:
```sh
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── skills/ # Optional: Skill definitions
│ ├── skill-1.md
│ └── skill-2.md
├── commands/ # Optional: Slash commands
│ ├── command-1.md
│ └── command-2.md
├── agents/ # Optional: Agent definitions
│ ├── agent-1.md
│ └── agent-2.md
├── hooks/ # Optional: Event hooks
│ └── hooks.json
├── README.md # Documentation
└── LICENSE # Optional: License file
```
## Core Workflow
### 1. Gather Requirements
Ask the user:
- **Plugin name**: Kebab-case identifier
- **Purpose**: What problem does this plugin solve?
- **Components**: What will it include (skills/commands/agents/hooks)?
- **Target audience**: Who will use this?
- **Distribution**: Public marketplace or private?
- **Dependencies**: Required tools or other plugins?
### 2. Generate Plugin Structure
#### Create Directory Structure
```bash
mkdir -p plugin-name/.claude-plugin
mkdir -p plugin-name/skills
mkdir -p plugin-name/commands
mkdir -p plugin-name/agents
mkdir -p plugin-name/hooks
```
#### Generate plugin.json
```json
{
"name": "plugin-name",
"version": "1.0.0",
"description": "Clear description of what this plugin does",
"author": {
"name": "Author Name",
"email": "[email protected]",
"github": "github-username"
},
"license": "MIT",
"category": "appropriate-category",
"keywords": ["keyword1", "keyword2", "keyword3"],
"skills": ["skill-1", "skill-2"],
"commands": ["command-1", "command-2"],
"agents": ["agent-1", "agent-2"],
"repository": {
"type": "git",
"url": "https://github.com/username/plugin-name"
},
"homepage": "https://github.com/username/plugin-name",
"requires": {
"tools": ["git", "npm"],
"plugins": []
}
}
```
#### Generate README.md
```markdown
# Plugin Name
> Brief description
## Features
- Feature 1
- Feature 2
- Feature 3
## Installation
\`\`\`bash
/plugin marketplace add username/plugin-name
/plugin install plugin-name
\`\`\`
## Usage
### Skills
- **skill-1**: Description
- **skill-2**: Description
### Commands
- `/command-1`: Description
- `/command-2`: Description
### Agents
- **agent-1**: Description
## Examples
[Usage examples]
## Requirements
- Tool 1
- Tool 2
## License
MIT
```
### 3. Add Components
Use the creator skills to add components:
- **skill-creator**: Add skills
- **command-creator**: Add commands
- **agent-creator**: Add agents
- **hook-creator**: Add hooks
### 4. Validate Plugin
Ensure:
- ✅ plugin.json is valid JSON
- ✅ All referenced components exist
- ✅ Directory structure is correct
- ✅ README is comprehensive
- ✅ License is appropriate
- ✅ Keywords are relevant
## Example Plugins
### TanStack Tools Plugin
```sh
tanstack-tools/
├── .claude-plugin/
│ └── plugin.json
├── skills/
│ ├── tanstack-router-setup.md
│ ├── tanstack-query-hook.md
│ ├── tanstack-form-schema.md
│ ├── tanstack-table-config.md
│ └── tanstack-start-project.md
├── commands/
│ ├── setup-tanstack-start.md
│ └── generate-query-hook.md
├── README.md
└── LICENSE
```
**plugin.json:**
```json
{
"name": "tanstack-tools",
"version": "1.0.0",
"description": "Comprehensive TanStack ecosystem tools for Router, Query, Forms, Table, and Start",
"author": {
"name": "Jace Babin",
"email": "[email protected]",
"github": "jbabin91"
},
"license": "MIT",
"category": "framework",
"keywords": [
"tanstack",
"router",
"query",
"forms",
"table",
"start",
"react"
],
"skills": [
"tanstack-router-setup",
"tanstack-query-hook",
"tanstack-form-schema",
"tanstack-table-config",
"tanstack-start-project"
],
"commands": ["setup-tanstack-start", "generate-query-hook"],
"requires": {
"tools": ["npm", "git"],
"packages": ["@tanstack/router", "@tanstack/react-query"]
}
}
```
### API Tools Plugin
```sh
api-tools/
├── .claude-plugin/
│ └── plugin.json
├── skills/
│ ├── drizzle-setup.md
│ ├── drizzle-schema-generator.md
│ ├── better-auth-setup.md
│ ├── hono-rpc-endpoint.md
│ └── elysia-setup.md
├── commands/
│ ├── init-drizzle.md
│ ├── generate-api-client.md
│ └── setup-auth.md
├── agents/
│ └── api-designer.md
├── README.md
└── LICENSE
```
**plugin.json:**
```json
{
"name": "api-tools",
"version": "1.0.0",
"description": "Backend API development tools for Hono, Elysia, Drizzle, and better-auth",
"author": {
"name": "Jace Babin",
"email": "[email protected]",
"github": "jbabin91"
},
"license": "MIT",
"category": "backend",
"keywords": [
"api",
"backend",
"hono",
"elysia",
"drizzle",
"better-auth",
"openapi"
],
"skills": [
"drizzle-setup",
"drizzle-schema-generator",
"better-auth-setup",
"hono-rpc-endpoint",
"elysia-setup"
],
"commands": ["init-drizzle", "generate-api-client", "setup-auth"],
"agents": ["api-designer"],
"requires": {
"tools": ["npm", "node"],
"packages": ["drizzle-orm", "better-auth"]
}
}
```
### Component Library Plugin
```sh
design-system-tools/
├── .claude-plugin/
│ └── plugin.json
├── skills/
│ ├── component-generator.md
│ ├── component-a11y-validator.md
│ ├── storybook-story.md
│ └── design-tokens-validator.md
├── commands/
│ ├── create-component.md
│ ├── validate-a11y.md
│ └── generate-stories.md
├── agents/
│ ├── component-reviewer.md
│ └── a11y-auditor.md
├── hooks/
│ └── hooks.json
├── README.md
└── LICENSE
```
## Plugin Categories
### Framework-Specific
- tanstack-tools
- react-tools
- next-tools
- vue-tools
### Backend
- api-tools
- database-tools
- auth-tools
### DevOps
- deployment-tools
- ci-cd-tools
- monitoring-tools
### Code Quality
- testing
- linting-tools
- security-tools
### Meta
- skill-tools (this plugin!)
- marketplace-tools
- template-tools
## Plugin Manifest Fields
### Required Fields
```json
{
"name": "plugin-identifier", // Required: kebab-case
"version": "1.0.0", // Required: semantic versioning
"description": "Clear description" // Required: what it does
}
```
### Recommended Fields
```json
{
"author": {
"name": "Author Name",
"email": "[email protected]",
"github": "username"
},
"license": "MIT",
"category": "framework",
"keywords": ["keyword1", "keyword2"],
"repository": {
"type": "git",
"url": "https://github.com/username/plugin"
},
"homepage": "https://github.com/username/plugin"
}
```
### Optional Fields
```json
{
"skills": ["skill-1", "skill-2"], // List of included skills
"commands": ["cmd-1", "cmd-2"], // List of commands
"agents": ["agent-1"], // List of agents
"requires": {
"tools": ["git", "npm"], // Required CLI tools
"plugins": ["other-plugin"], // Plugin dependencies
"packages": ["package-name"] // npm package dependencies
}
}
```
## Distribution
### Public Marketplace
1. Create GitHub repository
2. Add marketplace.json (if creating marketplace)
3. Tag releases with versions
4. Share repository URL
Users install via:
```bash
/plugin marketplace add username/plugin-name
/plugin install plugin-name
```
### Private/Work Distribution
1. Host on private Git server
2. Share repository URL with team
3. Add to team marketplace
Users install via:
```bash
/plugin marketplace add git@internal:plugins/plugin-name
/plugin install plugin-name
```
## Best Practices
1. **Clear Purpose**: Plugin should solve one specific problem domain
2. **Good Documentation**: Comprehensive README with examples
3Related 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.