plugin-development
Create and manage Claude Code plugins including commands, agents, skills, hooks, and MCP servers. This skill should be used when building new plugins, debugging plugin issues, understanding plugin structure, or working with plugin marketplaces.
What this skill does
# Plugin Development
This skill provides guidance for creating, structuring, and debugging Claude Code plugins.
## When to Use
This skill should be used when:
- Creating a new Claude Code plugin from scratch
- Adding components (commands, agents, skills, hooks, MCP servers) to an existing plugin
- Debugging plugin loading or configuration issues
- Understanding plugin directory structure and manifest format
- Preparing plugins for distribution via marketplaces
## Plugin Overview
A Claude Code plugin is a directory containing:
1. **`.claude-plugin/plugin.json`** (required) - Plugin manifest with metadata
2. **Component directories** (optional) - `commands/`, `agents/`, `skills/`, `hooks/`, `.mcp.json`
3. **Scripts and assets** - Supporting files for hooks and utilities
## Creating a Plugin
### Step 1: Create Directory Structure
```
my-plugin/
├── .claude-plugin/
│ └── plugin.json # REQUIRED - manifest
├── commands/ # Slash commands (.md files)
├── agents/ # Subagents (.md files)
├── skills/ # Agent skills (dirs with SKILL.md)
├── hooks/
│ └── hooks.json # Hook configurations
├── .mcp.json # MCP server definitions
└── scripts/ # Utility scripts for hooks
```
### Step 2: Create plugin.json
Minimal manifest:
```json
{
"name": "my-plugin",
"version": "1.0.0",
"description": "What this plugin does"
}
```
Full manifest - see `references/manifest-schema.md`.
### Step 3: Add Components
**Commands** - Create `commands/name.md`:
```markdown
---
description: Brief description for autocomplete
---
# Command Name
Instructions for the command...
```
**Agents** - Create `agents/name.md`:
```markdown
---
description: What this agent specializes in
capabilities: ["task1", "task2"]
---
# Agent Name
Agent instructions...
```
**Skills** - Create `skills/name/SKILL.md`:
```markdown
---
name: skill-name
description: What the skill does
---
# Skill Name
Skill instructions...
```
**Hooks** - Create `hooks/hooks.json` or inline in plugin.json:
```json
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/lint.sh"
}]
}]
}
}
```
**MCP Servers** - Create `.mcp.json` or inline in plugin.json:
```json
{
"mcpServers": {
"server-name": {
"command": "npx",
"args": ["@company/mcp-server"],
"cwd": "${CLAUDE_PLUGIN_ROOT}"
}
}
}
```
## Publishing as a Marketplace
To make your plugin installable via `github:` or `local:` sources, add `.claude-plugin/marketplace.json`:
```json
{
"name": "my-marketplace",
"plugins": [
{
"name": "my-skill",
"description": "What it does",
"source": "./skills/my-skill"
},
{
"name": "full-plugin",
"description": "Everything in this plugin",
"source": "./"
}
]
}
```
**Critical:** All `source` paths must start with `./` (e.g., `"./"` not `"."`).
See `references/marketplace-schema.md` for complete schema.
## Critical Rules
1. **`.claude-plugin/` contains ONLY `plugin.json` and `marketplace.json`** - All component directories go at plugin root
2. **All paths are relative** - Must start with `./`
3. **Use `${CLAUDE_PLUGIN_ROOT}`** - For absolute paths in hooks/MCP configs
4. **Scripts must be executable** - Run `chmod +x script.sh`
## Debugging
Run `claude --debug` to see:
- Which plugins are loading
- Errors in plugin manifests
- Command, agent, and hook registration
- MCP server initialization
### Common Issues
| Issue | Cause | Solution |
|------------------------|----------------------------|---------------------------------------|
| Plugin not loading | Invalid plugin.json | Validate JSON syntax |
| Commands not appearing | Wrong directory structure | Ensure `commands/` at root, not in `.claude-plugin/` |
| Hooks not firing | Script not executable | Run `chmod +x script.sh` |
| MCP server fails | Missing CLAUDE_PLUGIN_ROOT | Use variable for all plugin paths |
| Path errors | Absolute paths used | All paths must be relative with `./` |
| "marketplace not found" | Missing marketplace.json | Add `.claude-plugin/marketplace.json` |
| "source must start with ./" | Source path is `"."` not `"./"` | Change to `"./"` for root plugin |
## Resources
- `references/plugin-structure.md` - Complete directory layout and file locations
- `references/manifest-schema.md` - Full plugin.json schema with all fields
- `references/marketplace-schema.md` - Marketplace.json schema for github/local sources
- `references/components.md` - Detailed specs for commands, agents, skills, hooks, MCP
- `assets/templates/` - Template files for creating new plugins
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.