slash-commands — Claude Code skill slash-commands, Continuous-Claude-v3, parcadei, community, Claude Code skill, ai agent skill, ide skills, agent automation, AI agent skill, Cursor skill, Windsurf skill, context management

v1.0.0
GitHub

About this Skill

Perfect for Conversational Agents needing efficient context management and MCP execution without context pollution. Slash commands are a feature of Claude Code that enable users to create and use custom commands with a slash syntax.

Features

Built-in commands for common tasks
Isolated context windows for efficient context management
MCP execution without context pollution
Customizable commands with slash syntax
Integration with Claude Code CLI

# Core Topics

parcadei parcadei
[3.6k]
[279]
Updated: 3/21/2026

Quality Score

Top 5%
70
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
> npx killer-skills add parcadei/Continuous-Claude-v3/slash-commands
Supports 19+ Platforms
Cursor
Windsurf
VS Code
Trae
Claude
OpenClaw
+12 more

Agent Capability Analysis

The slash-commands skill by parcadei is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for AI agent skill, Claude Code skill, Cursor skill.

Ideal Agent Persona

Perfect for Conversational Agents needing efficient context management and MCP execution without context pollution.

Core Value

Empowers agents to create and use user-triggered prompts with `/command-name` syntax, providing features like built-in commands and isolated context windows, utilizing protocols like token analysis and settings interfaces.

Capabilities Granted for slash-commands

Creating custom slash commands for specific tasks
Managing conversation history with `/clear` and `/compact` commands
Configuring agent settings with `/config` and analyzing token costs with `/cost`

! Prerequisites & Limits

  • Requires Claude Code compatibility
  • Context windows must be isolated to prevent pollution
SKILL.md
Readonly

Slash Commands Reference

Create and use user-triggered prompts with /command-name syntax.

When to Use

  • "How do I create a slash command?"
  • "What slash commands are available?"
  • "Add bash to my command"
  • "Use file references in commands"
  • "Slash commands vs skills"

Built-in Commands

CommandPurpose
/clearClear conversation history
/compactCompact conversation with focus
/configOpen settings interface
/costShow token usage
/agentsManage sub-agents
/mcpManage MCP servers
/memoryEdit CLAUDE.md files
/modelSelect AI model
/reviewRequest code review
/resumeResume session
/helpGet usage help

Creating Commands

Project Commands

bash
1mkdir -p .claude/commands 2cat > .claude/commands/optimize.md << 'EOF' 3--- 4description: Analyze code for performance issues 5--- 6 7Review this code for: 8- Performance bottlenecks 9- Memory leaks 10- Caching opportunities 11EOF

Personal Commands

bash
1mkdir -p ~/.claude/commands 2cat > ~/.claude/commands/review.md << 'EOF' 3--- 4description: Security-focused code review 5--- 6 7Check for vulnerabilities: 8- Input validation 9- SQL injection 10- XSS risks 11EOF

Command File Format

yaml
1--- 2description: Brief description for /help 3allowed-tools: [Bash, Read, Write] # Optional 4argument-hint: "[file] [type]" # Optional 5--- 6 7Your markdown instructions here. 8Use $1, $2 for arguments or $ARGUMENTS for all.

Bash Execution

Run bash before loading prompt with ! prefix:

yaml
1--- 2allowed-tools: Bash(git:*), Bash(grep:*) 3description: Git commit helper 4--- 5 6Current status: !`git status` 7Staged changes: !`git diff --staged` 8Recent commits: !`git log --oneline -5` 9 10Based on these changes, suggest a commit message.

Rules:

  • Must declare allowed-tools: Bash(...) in frontmatter
  • Use backticks: !`command`
  • Output is included in Claude's context

File References

Include files with @ prefix:

markdown
1Review against @.claude/STYLE_GUIDE.md 2 3Compare: 4- @src/old.js 5- @src/new.js 6 7Refactor files matching @src/**/*.util.ts

Arguments

yaml
1--- 2argument-hint: "[pr-number] [priority]" 3--- 4 5Review PR #$1 with priority: $2 6 7# Or use all arguments: 8Fix issue #$ARGUMENTS

Usage:

bash
1/review-pr 456 high 2# $1 = "456", $2 = "high"

Namespacing

Organize with subdirectories:

.claude/commands/
├── frontend/
│   └── component.md    → /component (project:frontend)
└── backend/
    └── endpoint.md     → /endpoint (project:backend)

MCP Slash Commands

MCP servers expose prompts as commands:

bash
1/mcp__github__list_prs 2/mcp__github__pr_review 456 3/mcp__jira__create_issue "Bug" high

Slash Commands vs Skills

AspectSlash CommandsSkills
InvocationExplicit: /commandAuto-discovered
FilesSingle .md fileDirectory with SKILL.md
Use CaseQuick promptsComplex workflows

Use slash commands for: Frequently typed prompts, simple templates Use skills for: Complex workflows, multiple files, auto-discovery

Example: Complete Git Commit Command

yaml
1--- 2description: Generate semantic commit message 3allowed-tools: Bash(git:*), Read 4argument-hint: "[type]" 5--- 6 7# Semantic Commit Generator 8 9Staged files: !`git diff --name-only --cached` 10 11Diff preview: 12!`git diff --cached | head -100` 13 14Generate a conventional commit message. 15Type: $1 (feat/fix/docs/style/refactor/perf/test/chore) 16 17Format: `<type>(<scope>): <subject>`

Usage: /commit feat

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is slash-commands?

Perfect for Conversational Agents needing efficient context management and MCP execution without context pollution. Slash commands are a feature of Claude Code that enable users to create and use custom commands with a slash syntax.

How do I install slash-commands?

Run the command: npx killer-skills add parcadei/Continuous-Claude-v3/slash-commands. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for slash-commands?

Key use cases include: Creating custom slash commands for specific tasks, Managing conversation history with `/clear` and `/compact` commands, Configuring agent settings with `/config` and analyzing token costs with `/cost`.

Which IDEs are compatible with slash-commands?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for slash-commands?

Requires Claude Code compatibility. Context windows must be isolated to prevent pollution.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add parcadei/Continuous-Claude-v3/slash-commands. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use slash-commands immediately in the current project.

Related Skills

Looking for an alternative to slash-commands or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
Design

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
AI

antd-commit-msg

Logo of ant-design
ant-design

Generate a single-line commit message for ant-design by reading the projects git staged area and recent commit style. Use when the user asks for a commit message, says msg, commit msg, 写提交信息, or wants

97.8k
0
Design