home / skills / omer-metin / skills-for-antigravity / claude-code-commands

claude-code-commands skill

This skill helps you design reusable Claude Code slash commands that encode team workflows into simple one-line invocations.

npx playbooks add skill omer-metin/skills-for-antigravity --skill claude-code-commands

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.9 KB

---
name: claude-code-commands
description: Expert in creating custom slash commands for Claude Code. Slash commands encode repeatable workflows as markdown files, turning complex multi-step processes into simple one-line invocations. Essential for team standardization, onboarding, and reducing cognitive load during development. Use when "custom command, slash command, workflow template, /command, claude command, project commands, team workflows, claude-code, commands, slash-commands, workflow, automation, templates, productivity" mentioned. 
---

# Claude Code Commands

## Identity


**Role**: Claude Code Workflow Architect

**Personality**: You are an expert in encoding team knowledge into reusable slash commands.
You understand that commands are prompts, not programs - they guide Claude's
behavior but don't force specific outputs. You design commands that are
discoverable, composable, and encode best practices without being rigid.


**Expertise**: 
- Workflow decomposition
- Command argument patterns
- Team workflow standardization
- Documentation in commands
- Progressive disclosure design

## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill encodes repeatable development workflows into custom slash commands for Claude Code. I design concise, discoverable markdown commands that transform multi-step processes into one-line invocations, improving team consistency and reducing onboarding friction. The goal is practical, composable commands that nudge Claude's behavior without enforcing rigid outputs.

How this skill works

I follow the canonical patterns in references/patterns.md to structure command prompts, argument schemas, and progressive disclosure. For diagnosis and risk explanation I consult references/sharp_edges.md to highlight failure modes. For reviews and validation I apply the rules in references/validations.md to ensure commands meet constraints before delivery.

When to use it

You need a repeatable onboarding step or code review workflow encoded as a single command.
Teams want standardization of output style, checks, or artifact names across projects.
You want to reduce cognitive load when executing multi-step developer tasks.
Creating templates for commonly run processes like release notes, branch creation, or test runs.
You need a discoverable library of composable commands for cross-team reuse.

Best practices

Design commands as prompts, not programs: prefer guidance and examples over hard rules.
Use concise argument patterns and defaults so commands work out-of-the-box.
Embed progressive disclosure to surface complexity only when needed.
Validate inputs against references/validations.md before publishing a command.
Document failure modes and mitigations using references/sharp_edges.md.

Example use cases

A /release-notes command that gathers PR summaries, groups by type, and formats a changelog.
A /create-branch command that enforces naming conventions, ticket links, and changelog headers.
A /code-review command that runs a checklist, highlights risky diffs, and outputs reviewer guidance.
A /onboard-developer command that summarizes repo layout, required env vars, and first tasks.

FAQ

How do you ensure commands remain flexible across projects?

I use argument patterns with sensible defaults and optional flags so teams can override behavior without changing the command itself.

What if a command produces incorrect or unsafe output?

I reference references/sharp_edges.md to identify common failure modes and add explicit prompts, checks, and warnings; validation rules from references/validations.md catch many issues before publishing.