create-slash-command

Create new slash commands for DevAgent workflows. Use when you need to create a new command file in .agents/commands/ and symlink it to .cursor/commands/ for Cursor IDE integration. This skill handles the complete command creation workflow including file generation, symlink creation, and structure validation.

7 stars

Best use case

create-slash-command is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create new slash commands for DevAgent workflows. Use when you need to create a new command file in .agents/commands/ and symlink it to .cursor/commands/ for Cursor IDE integration. This skill handles the complete command creation workflow including file generation, symlink creation, and structure validation.

Teams using create-slash-command should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/create-slash-command/SKILL.md --create-dirs "https://raw.githubusercontent.com/lambda-curry/devagent/main/.cursor/skills/create-slash-command/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/create-slash-command/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How create-slash-command Compares

Feature / Agentcreate-slash-commandStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create new slash commands for DevAgent workflows. Use when you need to create a new command file in .agents/commands/ and symlink it to .cursor/commands/ for Cursor IDE integration. This skill handles the complete command creation workflow including file generation, symlink creation, and structure validation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Create Slash Command

## Overview

This skill automates the creation of DevAgent slash commands, which are standardized command files that provide interfaces for executing workflows. Commands are created in `.agents/commands/` and symlinked to `.cursor/commands/` for Cursor IDE integration.

**Important**: Commands are **snippets/templates** that get inserted into the chat conversation when invoked in Cursor IDE. The entire command file content is inserted, and users fill in placeholder areas (like "Input Context:") with their specific information. Keep commands simple and self-contained—they should be ready to paste into chat.

## Quick Start

To create a new command:

1. **Create the command file**:
   ```bash
   python3 scripts/create_command.py <command-name> [--workflow <workflow-name>]
   ```

2. **Create the symlink**:
   ```bash
   python3 scripts/create_symlink.py <command-name>
   ```

3. **Update README**: Add the new command to `.agents/commands/README.md`

## Command Creation Workflow

### Step 1: Create Command File

Run `scripts/create_command.py` with the command name:

```bash
python3 scripts/create_command.py my-new-command
```

This creates a command file at `.agents/commands/my-new-command.md` following the standard template. The command will reference a workflow file at `.devagent/core/workflows/my-new-command.md` by default.

**Specify a different workflow**:
```bash
python3 scripts/create_command.py my-command --workflow different-workflow
```

### Step 2: Create Symlink

Run `scripts/create_symlink.py` to create the symlink:

```bash
python3 scripts/create_symlink.py my-new-command
```

This creates a symlink from `.cursor/commands/my-new-command.md` to `.agents/commands/my-new-command.md`, making the command available in Cursor IDE.

### Step 3: Update Documentation

Manually add the new command to `.agents/commands/README.md` in the "Available Commands" section.

## Command Structure

Commands follow a standardized structure that functions as a snippet template. See `references/command-structure.md` for complete details. The template includes:

- Command title (Title Case with "(Command)" suffix)
- Instructions section (can include workflow-specific guidance about required inputs)
- Workflow reference to `.devagent/core/workflows/[workflow-name].md`
- Input Context placeholder (simple, single placeholder area for user input)

Since commands are snippets that get inserted into chat, keep the structure simple:
- Provide workflow-specific guidance in the Instructions section
- Use a single "Input Context:" placeholder for user input
- Avoid complex multi-field forms; explain in instructions what information is needed

The command template is available in `assets/command-template.md` for reference.

## Naming Conventions

- **Format**: Kebab-case (lowercase with hyphens)
- **Examples**: `create-plan.md`, `research.md`, `clarify-feature.md`
- **Avoid**: Generic names like `help.md` or `test.md`

## Validation

Before completing command creation, verify:

- [ ] Command file exists in `.agents/commands/[command-name].md`
- [ ] Command structure matches workflow requirements (use template as starting point, keep snippet-friendly)
- [ ] Workflow file is referenced correctly
- [ ] Instructions clearly guide agent and explain required inputs
- [ ] Input placeholder is simple and easy to fill in (commands are snippets)
- [ ] Symlink exists in `.cursor/commands/[command-name].md`
- [ ] Command is listed in `.agents/commands/README.md`

## Resources

### Scripts

- **`scripts/create_command.py`**: Creates a new command file in `.agents/commands/` following the standard template
- **`scripts/create_symlink.py`**: Creates a symlink from `.cursor/commands/` to `.agents/commands/`

### References

- **`references/command-structure.md`**: Complete reference documentation for command structure, naming conventions, and integration requirements

### Assets

- **`assets/command-template.md`**: Template file for command structure (used by create_command.py)

Related Skills

coderabbit-cli

7
from lambda-curry/devagent

Use CodeRabbit CLI to perform automated code review and iterative improvement in an AI agent workflow. Use when: (1) After generating non-trivial code (new features, refactors, algorithms), (2) Improving code quality, maintainability, or readability before submission, (3) Validating code changes against best practices, (4) Exploring unfamiliar languages, patterns, or domains, or (5) Creating a self-reviewing coding loop. Requires CodeRabbit CLI installed and authenticated. Not for trivial changes (typos, formatting-only) or rapid prototyping without quality constraints.

ai-rules-cli

7
from lambda-curry/devagent

Use ai-rules CLI to manage and synchronize AI coding rules across multiple AI assistants (Cursor, Claude Code, GitHub Copilot, Opencode, etc.). Use when: (1) Setting up ai-rules in a new project, (2) Updating AI coding guidelines and best practices, (3) Generating platform-specific rule files from source, (4) Checking if generated files are in sync with source files, (5) Managing multi-agent rule consistency, or (6) Adding new rules or modifying existing ones. Requires ai-rules CLI installed. The ai-rules/ directory serves as the single source of truth for all AI coding guidelines.

worktree-setup-hook

7
from lambda-curry/devagent

Post-checkout git hook for automatic worktree setup. Use when: (1) Setting up automatic configuration for new git worktrees, (2) Creating post-checkout hooks that detect new worktrees and run setup tasks, (3) Configuring worktrees to automatically copy env files and install dependencies

skill-creator

7
from lambda-curry/devagent

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

GitHub CLI Operations

7
from lambda-curry/devagent

Use GitHub CLI (gh) to interact with GitHub repositories, pull requests, issues, and workflows. Use when: (1) Reading PR details, diffs, or metadata, (2) Listing or filtering PRs and issues, (3) Creating PR comments or linking to issues, (4) Checking CI status or mergeability, (5) Extracting issue references from PR descriptions, or (6) Any GitHub repository operation via command line. Requires GitHub CLI installed and authenticated.

git-workspace

7
from lambda-curry/devagent

Work with git worktrees and workspaces for concurrent development. Use when: (1) Creating new workspaces with \`git worktree add\`, (2) Listing existing worktrees with \`git worktree list\`, (3) Removing worktrees with \`git worktree remove\`, (4) Pruning stale worktree metadata with \`git worktree prune\`, (5) Managing multiple checked-out branches simultaneously, (6) Migrating uncommitted work between workspaces, or (7) Any git workspace/worktree operation. Requires Git 2.5+ for worktree support.

discovering-make-commands

44152
from streamlit/streamlit

Lists available make commands for Streamlit development. Use for build, test, lint, or format tasks.

Developer ToolsClaude

create-pr

31392
from sickn33/antigravity-awesome-skills

Alias for sentry-skills:pr-writer. Use when users explicitly ask for "create-pr" or reference the legacy skill name. Redirects to the canonical PR writing workflow.

Developer ToolsClaude

create-issue-gate

31392
from sickn33/antigravity-awesome-skills

Use when starting a new implementation task and an issue must be created with strict acceptance criteria gating before execution.

Software DevelopmentClaude

create-branch

31392
from sickn33/antigravity-awesome-skills

Create a git branch following Sentry naming conventions. Use when asked to "create a branch", "new branch", "start a branch", "make a branch", "switch to a new branch", or when starting new work on the default branch.

Developer ToolsClaude

Twitter Command Center (Search + Post)

3891
from openclaw/skills

Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts after the user completes OAuth in the browser. Use when the user asks about Twitter/X data, social listening, or posting without sharing account passwords.

Social Media

FP&A Command Center — Financial Planning & Analysis Engine

3891
from openclaw/skills

You are a senior FP&A professional. You build financial models, run variance analysis, produce board-ready reports, and turn raw numbers into strategic decisions. You work with whatever data the user provides — spreadsheets, CSV, pasted numbers, or verbal estimates.

Finance & Analytics