Create Command
Create slash commands with brainstorming and best practices
- Type
- Slash Command
- Repository
- athola/claude-night-market
- GitHub stars
- 339
- License
- MIT
- Repo last updated
- Sep 24, 2026
- Source file
- plugins/abstract/commands/create-command.md
What Create Command is
Create Command is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”
A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.
Create Command gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.
How to install Create Command
Claude Code
- Download create-command.md from the repository.
- Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
- Run it by typing / followed by its name.
Claude Cowork
- Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
- In Customize → Skills, click +, then upload the ZIP.
- Run it from any task with / and the skill name.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/abstract/commands/create-command.md, shared under the repository's MIT license. Read the full file on GitHub.
Creates new slash commands through a structured workflow: iron-law → brainstorm → design → scaffold → validate. Uses Socratic questioning to refine rough ideas into well-designed commands before generating any files.
When To Use
Use this command when you need to:
- Creating a new slash command from scratch
- Need guided brainstorming for command design
- Want structured workflow for command development
When NOT To Use
Avoid this command if:
- Creating skills - use /create-skill instead
- Creating hooks - use /create-hook instead
- Modifying existing commands - edit directly
Usage
# Start with brainstorming (recommended)
/create-command "run all tests and show coverage report"
# Skip brainstorming if design is clear
/create-command test-coverage --skip-brainstorm
# Create in specific plugin
/create-command "analyze git history" --plugin sanctumWhat is a Slash Command?
Slash commands are shortcuts that expand into prompts Claude follows. They're stored as .md files in commands/ and referenced in plugin.json.
Simple command example:
---
description: Run tests with coverage
---
Run all tests with pytest and display a coverage report. Focus on files changed in the current branch.Command with arguments:
---
description: Review specific PR
usage: /review-pr <pr-number> [--focus security|performance|all]
---
Review pull request #$ARGUMENTS using the code review skill. Focus on ${focus:-all} aspects.Workflow
Phase 0: Iron Law Interlock (Blocking)
This phase is required and cannot be skipped.
Before any file creation, satisfy the Iron Law interlock:
Step 1: Create Test File FIRST
# Determine test location based on target plugin
tests/unit/test_${command_name}_command.pyStep 2: Write Structural Validation Tests
"""Tests for ${command_name} command structure and validation.
Written BEFORE implementation per Iron Law.
"""
import json
from pathlib import Path
import pytest
class Test${CommandName}Command:
"""Test /${command_name} command structure."""
@pytest.fixture
def command_file_path(self) -> Path:
return Path(__file__).parents[2] / "commands" / "${command_name}.md"
@pytest.fixture
def plugin_json_path(self) -> Path:
return Path(__file__).parents[2] / ".claude-plugin" / "plugin.json"
…Step 3: Run Tests - Capture RED State
pytest tests/unit/test_${command_name}_command.py -vExpected output (RED):
FAILED test_should_exist_when_command_file_path_resolved - FileNotFoundError
FAILED test_should_have_frontmatter_when_parsing_content - FileNotFoundError
FAILED test_should_be_registered_in_plugin_json - AssertionErrorStep 4: Capture Evidence
**Iron Law Checkpoint**: Creating command `${command_name}`.
[E1] Command: pytest tests/unit/test_${command_name}_command.py -v
Output: 3 FAILED (file does not exist)
Status: RED - Interlock satisfied
**Self-Check**:
- [x] Test file created BEFORE implementation
- [x] Failure evidence captured
- [x] Tests drive the implementationStep 5: Create TodoWrite Items
proof:iron-law-red - Test failure captured for ${command_name}Only after completing Phase 0 may you proceed to Phase 1.
Phase 1: Brainstorming (Default)
Before creating any files, refine the command concept through collaborative dialogue.
Invoke the brainstorming skill:
Use superpowers:brainstorming to refine this command idea before scaffolding.The brainstorming phase will:
- Understand the purpose - One question at a time:
- What task does this command automate?
- How often will it be used? (daily, weekly, occasionally)
- What's the expected output? (action, report, interactive)
- Who is the target user?
- Explore the interface:
- What arguments/options are needed?
- Should this be interactive or fire-and-forget?
- Are there variants that should be separate commands?
- What's a good, memorable name?
- Design the implementation:
- Simple prompt expansion vs. skill invocation?
- Does it need an agent for complex tasks?
- What existing skills/commands can it use?
- What tools will Claude need to use?
- Validate the design - Present in sections:
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Create Command?
Create Command is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Create slash commands with brainstorming and best practices
How do I install Create Command in Claude Code?
Download create-command.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.
Can I use Create Command in Claude Cowork?
Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.
Is Create Command safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Doc Verifier QA agent that validates documentation claims using proof-of-work methodology Subagent · athola/claude-night-market
- Documentation Mode Main thread configuration for documentation-focused sessions. Optimized for creating, updating, and consolidating project documentation. Use via: claude --agent documentation-mode Or set in .claude/settings.json: { "agent": "documentation-mode" } Subagent · athola/claude-night-market
- Export Export research findings to a format compatible with memory-palace's knowledge-intake skill. Slash Command · athola/claude-night-market
- Doc Editor Documentation editor agent for polishing and improving content quality Subagent · athola/claude-night-market
- Create Hook Create hooks with brainstorming and security-first design Slash Command · athola/claude-night-market
- Control Desktop Run a computer use task on the desktop via Claude's vision and action API Slash Command · athola/claude-night-market
- Create Issue Create a new GitHub issue with formatted description, labels, and optional reference links Slash Command · athola/claude-night-market
- Context Report Generate context optimization report for skill directories Slash Command · athola/claude-night-market