agentsclimarketplace

Create claude command

Skill atman-33/atman-marketplace/.claude/skills/create-claude-command

Use when building or improving a Claude Code slash command: $ARGUMENTS handling, file/bash injection, agent invocation, multi-agent orchestration, or command naming.From its SKILL.md

Install
npx -y skills add atman-33/atman-marketplace --skill create-claude-command

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, as published. Nobody here has run it

Claude Code Commands

Quick Reference

ComponentPurposeExample
FilenameCommand namereview.md → /review
$ARGUMENTSFull user input/review auth.js → $ARGUMENTS = "auth.js"
$1, $2Positional args/compare a.js b.js → $1 = "a.js", $2 = "b.js"
@fileInclude file contents@CLAUDE.md
!commandInclude bash output!git status

Command Locations

LocationScope
.claude/commands/Project (version-controlled, team-shared)
~/.claude/commands/Personal (cross-project, not shared)

The Scaffold

Every command is a scaffold — a markdown prompt template the user fills at invocation time:

---
description: Brief description for SlashCommand tool integration
---

# Command Title

[Instructions for what this command does]

User request: $ARGUMENTS

## Steps

1. [First action]
2. [Second action]

## Output Format

[Expected output structure]

The description: frontmatter is required for the SlashCommand tool to reference the command. Always include ## Output Format — without it the agent decides its own output shape, which varies run to run.

Naming Conventions

PatternExampleUse For
{action}/reviewSimple actions
{action}-{target}/security-scanSpecific targets
{domain}-{action}/pm-strategyDomain-prefixed
{tool}-{action}/git-commitTool-specific

Command vs Agent vs Skill

CommandAgentSkill
TriggerUser types /commandClaude decidesClaude loads
PurposeQuick shortcutsComplex workKnowledge
StatefulnessStatelessMaintains contextReference only

Flow: User → Command → Agent → Skill


For full $ARGUMENTS examples, command patterns (agent invocation, multi-agent orchestration, validation checklist), and advanced patterns (conditional logic, flag parsing), see REFERENCE.md.

Keep looking

Skills are one crate of 608,475. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.