Create Slash Commands

This teaches you how to build reusable slash commands for Claude Code, the kind that let you type `/optimize` or `/fix-issue 123` and expand into structured prompts. The skill is thorough about XML structure (objective, process, success_criteria tags), YAML frontmatter basics, and argument handling with $ARGUMENTS or positional variables like $1, $2. What I appreciate is the intelligence rules section that actually tells you when to keep commands simple versus when to add verification and output tags. It covers dynamic context loading with bash commands and file references, plus the distinction between project commands (.claude/commands/) and personal ones in your home directory. If you're setting up team workflows or just tired of retyping the same instructions, this gets you building commands that actually work.

skills.sh installs: 166
GitHub stars: 2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add glittercowboy/taches-cc-resources --skill create-slash-commands --agent claude-code

Installs into .claude/skills of the current project.

Files

Create effective slash commands for Claude Code that enable users to trigger reusable prompts with `/command-name` syntax. Slash commands expand as prompts in the current conversation, allowing teams to standardize workflows and operations. This skill teaches you to structure commands with XML tags, YAML frontmatter, dynamic context loading, and intelligent argument handling.

<quick_start>

1. Create `.claude/commands/` directory (project) or use `~/.claude/commands/` (personal) 2. Create `command-name.md` file 3. Add YAML frontmatter (at minimum: `description`) 4. Write command prompt 5. Test with `/command-name [args]` **File**: `.claude/commands/optimize.md`

---
description: Analyze this code for performance issues and suggest optimizations
---

Analyze the performance of this code and suggest three specific optimizations:

Usage: /optimize

Claude receives the expanded prompt and analyzes the code in context. </quick_start>

<xml_structure> All generated slash commands should use XML tags in the body (after YAML frontmatter) for clarity and consistency.

<required_tags>

SKILL.md on GitHub