This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
npxskills add softaworks/agent-toolkit--skill command-creatorLoading…
This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with /command-name in Claude Code conversations.
Slash commands are markdown files stored in .claude/commands/ (project-level) or ~/.claude/commands/ (global/user-level) that get expanded into prompts when invoked. They're ideal for:
Invoke this skill when users:
This skill includes reference documentation for detailed guidance:
Load these references as needed when creating commands to understand patterns, see examples, or ensure quality.
Every slash command is a markdown file with:
---
description: Brief description shown in /help (required)
argument-hint: <placeholder> (optional, if command takes arguments)
---
# Command Title
[Detailed instructions for the agent to execute autonomously]
Auto-detect the appropriate location:
git rev-parse --is-inside-work-tree 2>/dev/null.claude/commands/~/.claude/commands/~/.claude/commands/.claude/commands/Report the chosen location to the user before proceeding.
Help the user understand different command types. Load references/patterns.md to see available patterns:
Ask the user: "Which pattern is closest to what you want to create?" This helps frame the conversation.
Ask the user for key information:
Ask:
Guidelines:
submit-stack, ensure-ci, create-from-plansubmit_stack, ensure_ci, create_from_planmy-command.md → invoked as /my-command/help output)Ask:
If command takes arguments:
argument-hint: <placeholder> to frontmatter<angle-brackets> for required arguments[square-brackets] for optional argumentsAsk:
Gather details about:
Ask:
Create the command file with agent-optimized instructions. Load references/best-practices.md for:
Key principles:
Determine full file path:
.claude/commands/[command-name].md~/.claude/commands/[command-name].mdEnsure directory exists:
mkdir -p [directory-path]
Write the command file using the Write tool
Confirm with user:
/command-name [arguments]If the user wants to test:
You can test this command by running: /command-name [arguments]For detailed guidance, load the bundled references:
Common patterns to remember:
pytest, pyright, ruff, prettier, make, gt commands.PLAN.md) before proceedingWhen creating a command:
Focus on creating commands that agents can execute autonomously, with clear steps, explicit tool usage, and proper error handling.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).