slash-commands
# Claude Code Slash Commands
What this skill does
# Claude Code Slash Commands
Complete reference for all built-in and custom slash commands.
## Built-in Slash Commands
### Session Management
| Command | Description |
|---------|-------------|
| `/clear` | Clear conversation and start fresh (same session) |
| `/compact` | Compress conversation to reduce context usage |
| `/compact [instructions]` | Compact with custom focus instructions |
| `/resume` | Resume a previous session |
| `/continue` | Continue current session |
| `/status` | Current session info |
| `/context` | View context window usage |
### Help & Info
| Command | Description |
|---------|-------------|
| `/help` | Show available commands |
| `/doctor` | Run diagnostics and health checks |
| `/version` | Show Claude Code version |
| `/settings` | View active settings |
### Model & Configuration
| Command | Description |
|---------|-------------|
| `/model` | View or change the current model |
| `/model <name>` | Switch to specific model (sonnet, opus, haiku) |
| `/permissions` | Manage permission rules |
### Conversation Modes
| Command | Description |
|---------|-------------|
| `/plan` | Enter plan mode (read-only analysis) |
| `/fast` | Toggle fast mode (faster output, same model) |
### Memory & Instructions
| Command | Description |
|---------|-------------|
| `/memory` | Edit CLAUDE.md and auto-memory |
| `/init` | Generate project CLAUDE.md |
| `/init-only` | Generate CLAUDE.md and exit |
### Agents & Skills
| Command | Description |
|---------|-------------|
| `/agents` | View, create, edit, delete subagents |
| `/agents list` | List all available agents |
| `/skills` | Browse available skills |
| `/plugin` | Manage plugins (install, enable, disable) |
### Tools & Servers
| Command | Description |
|---------|-------------|
| `/mcp` | Check MCP server status, authenticate |
| `/hooks` | Configure lifecycle hooks |
| `/add-dir <path>` | Add additional working directory |
### Code & Navigation
| Command | Description |
|---------|-------------|
| `/diff` | View git diff interactively |
| `/review` | Review pull request |
| `/fork [name]` | Fork current conversation |
### Display & Preferences
| Command | Description |
|---------|-------------|
| `/theme` | Change color theme |
| `/vim` | Toggle Vim editing mode |
| `/terminal-setup` | Configure keybindings |
### Built-in Skills
| Command | Description |
|---------|-------------|
| `/simplify` | Review code quality and refactor |
| `/batch <instruction>` | Parallel codebase changes |
| `/debug [description]` | Debug session issues |
| `/loop <interval>` | Recurring prompts |
| `/claude-api` | Load Claude API reference docs |
### Security & Sandbox
| Command | Description |
|---------|-------------|
| `/sandbox` | View or configure sandbox settings |
| `/security-review` | Run security analysis on codebase |
### Export & Sharing
| Command | Description |
|---------|-------------|
| `/export` | Export conversation |
| `/copy` | Copy last response to clipboard |
### Monitoring & Insights
| Command | Description |
|---------|-------------|
| `/tasks` | View background tasks |
| `/insights` | Session insights and analytics |
| `/stats` | Usage statistics |
| `/usage` | Token/cost usage for current session |
| `/extra-usage` | Extended usage details |
### Releases & Updates
| Command | Description |
|---------|-------------|
| `/release-notes` | View release notes for current version |
| `/upgrade` | Upgrade Claude Code to latest |
### Hooks & Plugins
| Command | Description |
|---------|-------------|
| `/save-hooks` | Save current hooks configuration |
| `/reload-plugins` | Reload installed plugins |
### Browser & Display
| Command | Description |
|---------|-------------|
| `/chrome` | Open Chrome browser session |
| `/desktop` | Desktop view mode |
| `/mobile` | Mobile view mode |
| `/ide` | IDE integration mode |
### Account & Auth
| Command | Description |
|---------|-------------|
| `/login` | Login to Anthropic |
| `/logout` | Logout from Anthropic |
### Configuration
| Command | Description |
|---------|-------------|
| `/rename` | Rename current conversation |
| `/keybindings` | View or edit keybindings |
| `/statusline` | Configure status line display |
| `/output-style` | Change output formatting style |
| `/privacy-settings` | View or edit privacy settings |
| `/add-dir` | Add working directory to context |
### Remote & Apps
| Command | Description |
|---------|-------------|
| `/remote-env` | Configure remote environment |
| `/remote-control` | Start remote control session |
### GitHub & Slack Apps
| Command | Description |
|---------|-------------|
| `/install-github-app` | Install Claude GitHub App |
| `/install-slack-app` | Install Claude Slack App |
### Bug Reporting
| Command | Description |
|---------|-------------|
| `/bug` | Report a bug (can be disabled via env var) |
### Input Prefixes
| Prefix | Action |
|--------|--------|
| `/` | Invoke command or skill |
| `!` | Bash mode (execute shell command) |
| `@` | File mention (add file to context) |
| `?` | Show shortcuts |
## Keyboard Shortcuts
### Input Controls
| Shortcut | Action |
|----------|--------|
| `Enter` | Send message |
| `Shift+Enter` | Multi-line input |
| `Ctrl+C` | Interrupt current operation |
| `Ctrl+D` | Exit Claude Code |
| `Escape` | Rewind to last checkpoint |
| `Escape` (2x) | Full rewind |
| `Tab` | Auto-complete |
| `Up/Down` | Navigate command history |
| `?` | Show shortcuts |
### Mode & Toggle Controls
| Shortcut | Action |
|----------|--------|
| `Shift+Tab` | Cycle permission modes |
| `Ctrl+O` | Toggle verbose output |
| `Ctrl+B` | Send task to background |
| `Ctrl+T` | Toggle task list |
| `Option+P` | Switch model |
| `Option+T` | Toggle extended thinking |
| `Ctrl+G` | Open input in text editor |
| `Ctrl+V` | Paste image |
### Line Editing
| Shortcut | Action |
|----------|--------|
| `Ctrl+K` | Kill text from cursor to end of line |
| `Ctrl+U` | Kill text from cursor to start of line |
| `Ctrl+Y` | Yank (paste) killed text |
| `Alt+Y` | Cycle through kill ring |
| `Alt+B` | Move back one word |
| `Alt+F` | Move forward one word |
| `Alt+M` | Toggle multiline mode |
### Display & Navigation
| Shortcut | Action |
|----------|--------|
| `Ctrl+L` | Clear screen |
| `Ctrl+R` | Reverse search history |
| `Ctrl+F` | Kill background agents |
### Permission Prompts
| Shortcut | Action |
|----------|--------|
| `y` / `Enter` | Approve (Allow Once) |
| `a` | Allow Always (for this session) |
| `n` | Deny |
| `d` | Deny Always (for this session) |
| `e` | Edit (modify the tool call) |
## Custom Slash Commands
### Creating Custom Commands
Custom commands are skill files in `.claude/skills/` or plugin directories.
#### Skill File Format
```markdown
---
name: my-command
description: What this command does
triggers:
- /my-command
- /mc
args:
- name: target
description: Target to operate on
required: false
---
# My Custom Command
Instructions for Claude when this command is invoked.
## Steps
1. Do this first
2. Then do this
3. Finally do this
## Rules
- Always follow this pattern
- Never do this other thing
```
#### Plugin Command Format
Commands in plugin `commands/` directories:
```markdown
# Command Name
Description of what the command does.
## Usage
\`\`\`
/plugin-prefix:command-name [args]
\`\`\`
## Arguments
- `arg1` — Description
- `--flag` — Description
## Implementation
When this command is invoked:
1. Step one
2. Step two
3. Step three
```
### Command Resolution Order
1. Built-in commands (highest priority)
2. Project skills (`.claude/skills/`)
3. Installed plugin commands
4. User-level skills (`~/.claude/skills/`)
### Invoking Custom Commands
```
# Direct invocation
/my-command
# With arguments
/my-command some-argument
# Plugin-namespaced command
/plugin-name:command-name
# Via Skill tool (programmatic)
Skill(skill="my-command", args="some-argument")
```
## Plan Mode Details
When `/plan` is active:
1. Claude analyzeRelated 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.