create-agent-skills

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

5 stars

Best use case

create-agent-skills is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Teams using create-agent-skills should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/create-agent-skills/SKILL.md --create-dirs "https://raw.githubusercontent.com/marchatton/agent-skills/main/.agents/skills/98-skill-maintenance/create-agent-skills/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/create-agent-skills/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How create-agent-skills Compares

Feature / Agentcreate-agent-skillsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Create Agent Skills

This skill teaches how to create effective Claude Code Skills following Anthropic's official specification.

## Core Principles

### 1. Skills Are Prompts

All prompting best practices apply. Be clear, be direct. Assume Claude is smart - only add context Claude doesn't have.

### 2. Standard Markdown Format

Use YAML frontmatter + markdown body. **No XML tags** - use standard markdown headings.

```markdown
---
name: my-skill-name
description: What it does and when to use it
---

# My Skill Name

## Quick Start
Immediate actionable guidance...

## Instructions
Step-by-step procedures...

## Examples
Concrete usage examples...
```

### 3. Progressive Disclosure

Keep SKILL.md under 500 lines. Split detailed content into reference files. Load only what's needed.

```
my-skill/
├── SKILL.md              # Entry point (required)
├── reference.md          # Detailed docs (loaded when needed)
├── examples.md           # Usage examples
└── assets/               # Optional templates or static files
```

### 4. Effective Descriptions

The description field enables skill discovery. Include both what the skill does AND when to use it. Write in third person.

**Good:**
```yaml
description: Extracts text and tables from PDF files, fills forms, merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
```

**Bad:**
```yaml
description: Helps with documents
```

## Skill Structure

### Required Frontmatter

| Field | Required | Max Length | Description |
|-------|----------|------------|-------------|
| `name` | Yes | 64 chars | Lowercase letters, numbers, hyphens only |
| `description` | Yes | 1024 chars | What it does AND when to use it |
| `allowed-tools` | No | - | Tools Claude can use without asking |
| `model` | No | - | Specific model to use |

### Naming Conventions

Use **gerund form** (verb + -ing) for skill names:

- `processing-pdfs`
- `analyzing-spreadsheets`
- `generating-commit-messages`
- `reviewing-code`

Avoid: `helper`, `utils`, `tools`, `anthropic-*`, `claude-*`

### Body Structure

Use standard markdown headings:

```markdown
# Skill Name

## Quick Start
Fastest path to value...

## Instructions
Core guidance Claude follows...

## Examples
Input/output pairs showing expected behavior...

## Advanced Features
Additional capabilities (link to reference files)...

## Guidelines
Rules and constraints...
```

## What Would You Like To Do?

1. **Create new skill** - Build from scratch
2. **Audit existing skill** - Check against best practices
3. **Add component** - Add workflow/reference/example
4. **Get guidance** - Understand skill design

## Creating a New Skill

### Step 1: Choose Type

**Simple skill (single file):**
- Under 500 lines
- Self-contained guidance
- No complex workflows

**Progressive disclosure skill (multiple files):**
- SKILL.md as overview
- Reference files for detailed docs
- Scripts for utilities

### Step 2: Create SKILL.md

```markdown
---
name: your-skill-name
description: [What it does]. Use when [trigger conditions].
---

# Your Skill Name

## Quick Start

[Immediate actionable example]

```[language]
[Code example]
```

## Instructions

[Core guidance]

## Examples

**Example 1:**
Input: [description]
Output:
```
[result]
```

## Guidelines

- [Constraint 1]
- [Constraint 2]
```

### Step 3: Add Reference Files (If Needed)

Link from SKILL.md to detailed content:

```markdown
For API reference, see [REFERENCE.md](REFERENCE.md).
For form filling guide, see [FORMS.md](FORMS.md).
```

Keep references **one level deep** from SKILL.md.

### Step 4: Test With Real Usage

1. Test with actual tasks, not test scenarios
2. Observe where Claude struggles
3. Refine based on real behavior
4. Test with Haiku, Sonnet, and Opus

## Auditing Existing Skills

Check against this rubric:

- [ ] Valid YAML frontmatter (name + description)
- [ ] Description includes trigger keywords
- [ ] Uses standard markdown headings (not XML tags)
- [ ] SKILL.md under 500 lines
- [ ] References one level deep
- [ ] Examples are concrete, not abstract
- [ ] Consistent terminology
- [ ] No time-sensitive information
- [ ] Any executable helpers handle errors explicitly

## Common Patterns

### Template Pattern

Provide output templates for consistent results:

```markdown
## Report Template

```markdown
# [Analysis Title]

## Executive Summary
[One paragraph overview]

## Key Findings
- Finding 1
- Finding 2

## Recommendations
1. [Action item]
2. [Action item]
```
```

### Workflow Pattern

For complex multi-step tasks:

```markdown
## Migration Workflow

Copy this checklist:

```
- [ ] Step 1: Backup database
- [ ] Step 2: Run migration script
- [ ] Step 3: Validate output
- [ ] Step 4: Update configuration
```

**Step 1: Backup database**
Back up before running the migration.
...
```

### Conditional Pattern

Guide through decision points:

```markdown
## Choose Your Approach

**Creating new content?** Follow "Creation workflow" below.
**Editing existing?** Follow "Editing workflow" below.
```

## Anti-Patterns to Avoid

- **XML tags in body** - Use markdown headings instead
- **Vague descriptions** - Be specific with trigger keywords
- **Deep nesting** - Keep references one level from SKILL.md
- **Too many options** - Provide a default with escape hatch
- **Windows paths** - Always use forward slashes
- **Punting to Claude** - Scripts should handle errors
- **Time-sensitive info** - Use "old patterns" section instead

## Reference Files

For detailed guidance, see:

- [official-spec.md](references/official-spec.md) - Anthropic's official skill specification
- [best-practices.md](references/best-practices.md) - Skill authoring best practices

## Success Criteria

A well-structured skill:
- Has valid YAML frontmatter with descriptive name and description
- Uses standard markdown headings (not XML tags)
- Keeps SKILL.md under 500 lines
- Links to reference files for detailed content
- Includes concrete examples with input/output pairs
- Has been tested with real usage

Sources:
- [Agent Skills - Claude Code Docs](https://code.claude.com/docs/en/skills)
- [Skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
- [GitHub - anthropics/skills](https://github.com/anthropics/skills)

Related Skills

modular-skills-architect

5
from marchatton/agent-skills

Map and refactor an agent context ecosystem: skills, commands/workflows, hooks, agent files, AGENTS.md templates, and docs. Output system map, module/dependency design, Register updates, and a concrete split/consolidate/rename/delete plan. Use when routing or ownership is messy.

create-prd

5
from marchatton/agent-skills

Draft PRD with scope, stories, acceptance criteria, verification. Use when shaping a new feature or spec.

create-json-prd

5
from marchatton/agent-skills

Generate a Product Requirements Document (PRD) as JSON for Ralph by converting an existing PRD markdown file. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

create-cli

5
from marchatton/agent-skills

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

skill-creator

5
from marchatton/agent-skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

heal-skill

5
from marchatton/agent-skills

This skill should be used when fixing incorrect SKILL.md files with outdated instructions or APIs.

agent-native-audit

5
from marchatton/agent-skills

Comprehensive agent-native architecture audit with scored principles and multi-slice review. Use for system-wide health checks or periodic audits.

write-judge-prompt

5
from marchatton/agent-skills

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

validate-evaluator

5
from marchatton/agent-skills

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

generate-synthetic-data

5
from marchatton/agent-skills

Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.

evaluate-rag

5
from marchatton/agent-skills

Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.

eval-audit

5
from marchatton/agent-skills

Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).