claude-plugins
# Claude Code Plugins Quick Reference
What this skill does
# Claude Code Plugins Quick Reference
Full docs:
- [Create plugins](https://code.claude.com/docs/en/plugins.md)
- [Discover & install plugins](https://code.claude.com/docs/en/discover-plugins.md)
- [Plugins reference](https://code.claude.com/docs/en/plugins-reference.md)
- [Plugin marketplaces](https://code.claude.com/docs/en/plugin-marketplaces.md)
## Plugins vs Standalone
| Approach | Skill names | Best for |
|----------|-------------|----------|
| **Standalone** (`.claude/`) | `/hello` | Personal workflows, project-specific, quick experiments |
| **Plugins** (`.claude-plugin/plugin.json`) | `/plugin-name:hello` | Sharing with teams, community distribution, versioned releases |
## Plugin Structure
```
my-plugin/
├── .claude-plugin/
│ └── plugin.json # Required manifest
├── commands/ # Slash commands (Markdown files)
├── skills/ # Agent skills (SKILL.md files)
├── agents/ # Custom agent definitions
├── hooks/
│ └── hooks.json # Event handlers
├── .mcp.json # MCP server configs
└── .lsp.json # LSP server configs
```
**Common mistake**: Don't put `commands/`, `skills/`, etc. inside `.claude-plugin/`. Only `plugin.json` goes there.
## Manifest (plugin.json)
```json
{
"name": "my-plugin",
"description": "What the plugin does",
"version": "1.0.0",
"author": {
"name": "Your Name"
},
"homepage": "https://github.com/you/my-plugin",
"repository": "https://github.com/you/my-plugin",
"license": "MIT"
}
```
The `name` field becomes the skill namespace prefix (e.g., `/my-plugin:hello`).
## Quick Commands
### Marketplace Management
```bash
# Add marketplaces
/plugin marketplace add owner/repo # GitHub
/plugin marketplace add https://gitlab.com/org/repo.git # Other Git
/plugin marketplace add ./local-path # Local directory
/plugin marketplace add https://example.com/marketplace.json # URL
# Add specific branch/tag
/plugin marketplace add owner/repo#v1.0.0
# List, update, remove
/plugin marketplace list
/plugin marketplace update marketplace-name
/plugin marketplace remove marketplace-name
```
Shortcuts: `/plugin market` works, `rm` instead of `remove`
### Plugin Installation
```bash
# Install (defaults to user scope)
/plugin install plugin-name@marketplace-name
# Install with specific scope
claude plugin install plugin-name@marketplace-name --scope project
claude plugin install plugin-name@marketplace-name --scope local
# Enable/disable without uninstalling
/plugin disable plugin-name@marketplace-name
/plugin enable plugin-name@marketplace-name
# Uninstall
/plugin uninstall plugin-name@marketplace-name
```
### Interactive UI
```bash
/plugin # Opens plugin manager with tabs:
# - Discover: browse available plugins
# - Installed: manage your plugins
# - Marketplaces: add/remove marketplaces
# - Errors: view loading errors
```
Navigate tabs with **Tab** / **Shift+Tab**
## Installation Scopes
| Scope | Who sees it | Stored in |
|-------|-------------|-----------|
| **User** | You, all projects | `~/.claude/settings.json` |
| **Project** | All collaborators | `.claude/settings.json` |
| **Local** | You, this repo only | `.claude/settings.local.json` |
| **Managed** | All org users | Admin-controlled |
## Testing During Development
```bash
# Load plugin from local directory
claude --plugin-dir ./my-plugin
# Load multiple plugins
claude --plugin-dir ./plugin-one --plugin-dir ./plugin-two
```
Restart Claude Code after making changes.
## Official Marketplace Plugins
### Code Intelligence (LSP)
| Language | Plugin | Binary required |
|----------|--------|-----------------|
| TypeScript | `typescript-lsp` | `typescript-language-server` |
| Python | `pyright-lsp` | `pyright-langserver` |
| Rust | `rust-analyzer-lsp` | `rust-analyzer` |
| Go | `gopls-lsp` | `gopls` |
| C/C++ | `clangd-lsp` | `clangd` |
Install: `/plugin install typescript-lsp@claude-plugins-official`
### External Integrations (MCP)
`github`, `gitlab`, `atlassian`, `asana`, `linear`, `notion`, `figma`, `vercel`, `firebase`, `supabase`, `slack`, `sentry`
### Development Workflows
`commit-commands`, `pr-review-toolkit`, `agent-sdk-dev`, `plugin-dev`
## Creating a Skill in a Plugin
Create `skills/my-skill/SKILL.md`:
```yaml
---
name: my-skill
description: What the skill does. Use when [context].
---
Instructions for Claude when this skill is invoked...
```
## Creating a Command in a Plugin
Create `commands/hello.md`:
```yaml
---
description: Greet the user
disable-model-invocation: true
---
Greet the user named "$ARGUMENTS" warmly.
```
Use as: `/my-plugin:hello Alex`
## Hooks in Plugins
Create `hooks/hooks.json`:
```json
{
"hooks": {
"PostToolUse": [
{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "jq -r '.tool_input.file_path' | xargs npm run lint:fix"
}]
}
]
}
}
```
## LSP Configuration
Create `.lsp.json` at plugin root:
```json
{
"go": {
"command": "gopls",
"args": ["serve"],
"extensionToLanguage": {
".go": "go"
}
}
}
```
## Auto-Updates
- Official marketplaces: auto-update enabled by default
- Third-party/local: disabled by default
- Toggle per-marketplace in `/plugin` > Marketplaces
- Disable all: `export DISABLE_AUTOUPDATER=true`
- Plugins only: `DISABLE_AUTOUPDATER=true FORCE_AUTOUPDATE_PLUGINS=true`
## Team Setup
Add to `.claude/settings.json` for automatic marketplace prompts:
```json
{
"extraKnownMarketplaces": ["your-org/team-plugins"],
"enabledPlugins": ["plugin-name@your-org-team-plugins"]
}
```
## Troubleshooting
- **`/plugin` not recognized**: Requires Claude Code 1.0.33+. Run `claude --version`
- **Plugin skills not appearing**: `rm -rf ~/.claude/plugins/cache`, restart, reinstall
- **LSP binary not found**: Check `/plugin` Errors tab, install required binary
- **Marketplace not loading**: Verify `.claude-plugin/marketplace.json` exists at path
- **Files not found**: Plugins are cached; paths outside plugin directory won't work
## Convert Standalone to Plugin
1. Create `my-plugin/.claude-plugin/plugin.json`
2. Copy `.claude/commands` to `my-plugin/commands/`
3. Copy `.claude/skills` to `my-plugin/skills/`
4. Move hooks from `settings.json` to `my-plugin/hooks/hooks.json`
5. Test: `claude --plugin-dir ./my-plugin`
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.