Automated summary
This skill creates a new Claude Code skill by generating a structured SKILL.md file in the .claude/skills/ directory.
Strengths
- Guides the user through a clear and repeatable process
- Includes concrete examples and best practices
- Automates directory structure and content creation
Limitations
- Requires prior understanding of Claude Code skills concept
- Limited to creating one skill at a time
- Does not handle dependencies between skills
Use this skill whenever you need to define a new reusable workflow for Claude Code in your project.
Do not use it if you need to modify an existing skill or if you are working with an agent other than Claude Code.
Security analysis
SafeThe skill only creates a directory and a markdown file in the project's .claude/skills/ directory, with no external network access, no destructive commands, and no exfiltration risk.
No concerns found
How this analysis is madeExamples
Create a skill called 'commit-message' that helps write conventional commit messages with proper formatting.Define a skill named 'feature-workflow' for guiding the full feature branch lifecycle from planning to deployment.Create a skill that filters verbose output from bash commands to reduce context usage.π― Define Skill
Create a new Claude Code skill to automate workflows and guide development patterns.
Arguments: <skill-name> [description]
π What Are Skills?
Skills are auto-activated workflows stored in .claude/skills/ that:
- Guide Claude through repetitive development patterns
- Reduce context usage with optimized commands
- Ensure consistency across sessions
- Activate automatically based on user intent
ποΈ Skill Structure
Each skill is a directory with a SKILL.md file:
.claude/skills/
βββ my-skill-name/
βββ SKILL.md
π SKILL.md Format
---
name: Human Readable Name
description: When to activate this skill. Activate when [trigger conditions].
allowed-tools: Bash, Read, Write, Edit, Glob, Grep
---
# Skill Name
## When to Use
Activate whenever the user asks to:
- [Trigger condition 1]
- [Trigger condition 2]
- [Trigger condition 3]
## Instructions
[Step-by-step workflow with specific commands and best practices]
### Step 1: [Action]
[Details and code examples]
### Step 2: [Action]
[Details and code examples]
## Best Practices
- [Practice 1]
- [Practice 2]
## Integration with Other Skills
This skill works together with:
- **Other Skill Name**: [How they interact]
β¨ Skill Creation Workflow
When user provides skill details, follow this process:
-
Parse Arguments
- Extract skill name (kebab-case)
- Extract description or ask for clarification
-
Create Directory
mkdir -p .claude/skills/[skill-name] -
Generate SKILL.md
- Add YAML frontmatter with name, description, allowed-tools
- Define "When to Use" triggers
- Write step-by-step instructions
- Include code examples
- Add best practices
- Note integration with other skills
-
Confirm Creation
- Show skill name and location
- Display activation triggers
- Explain when Claude will use it
π¨ Skill Examples
Simple Skill (Quiet Command)
- Purpose: Filter verbose output to reduce context
- Pattern: Wrap command with grep filter
- Tools: Bash only
Complex Skill (Feature Development)
- Purpose: Guide full feature branch workflow
- Pattern: Plan β Branch β Build β Deploy β Iterate
- Tools: Multiple (Bash, Read, Write, Edit)
π‘ Best Practices for Skills
- Clear Activation Triggers: Be specific about when skill activates
- Step-by-Step Instructions: Number steps, provide exact commands
- Code Examples: Show concrete command syntax
- Context Efficiency: Use grep patterns, quiet flags, filtered output
- Integration Notes: Explain how skill works with others
- Tool Restrictions: Only list tools the skill actually needs
π§ Scope
- Project Skills:
.claude/skills/(this project only) - Global Skills: Not supported (skills are project-specific)
π Additional Resources
- Existing skills in
.claude/skills/for reference patterns - Skills activate automatically based on description triggers
- No need to manually invoke skills - Claude recognizes intent
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/create-a-claude-code-skill-mm5t8ahq/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/create-a-claude-code-skill-mm5t8ahq' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-a-claude-code-skill-mm5t8ahq/download' --output '.skill-downloads/create-a-claude-code-skill-mm5t8ahq/SKILL.md.part' && mv '.skill-downloads/create-a-claude-code-skill-mm5t8ahq/SKILL.md.part' '.skill-downloads/create-a-claude-code-skill-mm5t8ahq/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/create-a-claude-code-skill-mm5t8ahq/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.