Agent Context Isolation
The English summary is being prepared. Showing the original description.
Create and use Claude Code slash commands - quick prompts, bash execution, file references
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Create and use user-triggered prompts with /command-name syntax.
| Command | Purpose |
|---|---|
/clear | Clear conversation history |
/compact | Compact conversation with focus |
/config | Open settings interface |
/cost | Show token usage |
/agents | Manage sub-agents |
/mcp | Manage MCP servers |
/memory | Edit CLAUDE.md files |
/model | Select AI model |
/review | Request code review |
/resume | Resume session |
/help | Get usage help |
mkdir -p .claude/commands
cat > .claude/commands/optimize.md << 'EOF'
---
description: Analyze code for performance issues
---
Review this code for:
- Performance bottlenecks
- Memory leaks
- Caching opportunities
EOF
mkdir -p ~/.claude/commands
cat > ~/.claude/commands/review.md << 'EOF'
---
description: Security-focused code review
---
Check for vulnerabilities:
- Input validation
- SQL injection
- XSS risks
EOF
---
description: Brief description for /help
allowed-tools: [Bash, Read, Write] # Optional
argument-hint: "[file] [type]" # Optional
---
Your markdown instructions here.
Use $1, $2 for arguments or $ARGUMENTS for all.
Run bash before loading prompt with ! prefix:
---
allowed-tools: Bash(git:*), Bash(grep:*)
description: Git commit helper
---
Current status: !`git status`
Staged changes: !`git diff --staged`
Recent commits: !`git log --oneline -5`
Based on these changes, suggest a commit message.
Rules:
allowed-tools: Bash(...) in frontmatter!`command`Include files with @ prefix:
Review against @.claude/STYLE_GUIDE.md
Compare:
- @src/old.js
- @src/new.js
Refactor files matching @src/**/*.util.ts
---
argument-hint: "[pr-number] [priority]"
---
Review PR #$1 with priority: $2
# Or use all arguments:
Fix issue #$ARGUMENTS
Usage:
/review-pr 456 high
# $1 = "456", $2 = "high"
Organize with subdirectories:
.claude/commands/
├── frontend/
│ └── component.md → /component (project:frontend)
└── backend/
└── endpoint.md → /endpoint (project:backend)
MCP servers expose prompts as commands:
/mcp__github__list_prs
/mcp__github__pr_review 456
/mcp__jira__create_issue "Bug" high
| Aspect | Slash Commands | Skills |
|---|---|---|
| Invocation | Explicit: /command | Auto-discovered |
| Files | Single .md file | Directory with SKILL.md |
| Use Case | Quick prompts | Complex workflows |
Use slash commands for: Frequently typed prompts, simple templates Use skills for: Complex workflows, multiple files, auto-discovery
---
description: Generate semantic commit message
allowed-tools: Bash(git:*), Read
argument-hint: "[type]"
---
# Semantic Commit Generator
Staged files: !`git diff --name-only --cached`
Diff preview:
!`git diff --cached | head -100`
Generate a conventional commit message.
Type: $1 (feat/fix/docs/style/refactor/perf/test/chore)
Format: `<type>(<scope>): <subject>`
Usage: /commit feat
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Agent Context Isolation
The English summary is being prepared. Showing the original description.
Agent Orchestration Rules
The English summary is being prepared. Showing the original description.
Agentic Workflow Pattern
The English summary is being prepared. Showing the original description.
Guide for integrating Agentica SDK with Claude Code CLI proxy
The English summary is being prepared. Showing the original description.
Reference guide for Agentica multi-agent infrastructure APIs
The English summary is being prepared. Showing the original description.
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
The English summary is being prepared. Showing the original description.