Skill creator
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.From its SKILL.md
npx -y skills add cskwork/claude-minimal-plugin --skill skill-creatorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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.
What its file declares
Copied from the file, not written here
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.4 KB, 496 tokens by cl100k_base, as published. Nobody here has run it
Skill Creator
Skills are modular packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools.
Core Principles
Concise is Key
The context window is a shared resource. Only add context Claude doesn't already have. Challenge each piece: "Does Claude really need this?"
Anatomy of a Skill
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code
├── references/ - Documentation
└── assets/ - Templates, images
SKILL.md Format
---
name: my-skill-name
description: A clear description of what this skill does and when to use it
---
# My Skill Name
[Instructions for Claude when this skill is active]
## Examples
- Example usage 1
- Example usage 2
## Guidelines
- Guideline 1
- Guideline 2
Skill Creation Process
Step 1: Understand with Examples
Gather concrete examples of how the skill will be used. Ask:
- "What functionality should this skill support?"
- "What would a user say that should trigger this skill?"
Step 2: Plan Reusable Contents
Analyze examples to identify:
- Scripts: Code that gets rewritten repeatedly
- References: Documentation Claude needs to reference
- Assets: Templates, images for output
Step 3: Initialize
Create the skill directory structure with SKILL.md and resource folders.
Step 4: Implement
- Start with reusable resources (scripts, references, assets)
- Write clear SKILL.md with proper frontmatter
- Test scripts by actually running them
Step 5: Iterate
Use the skill on real tasks, notice struggles, improve.
Progressive Disclosure
Keep SKILL.md under 500 lines. Split content:
# PDF Processing
## Quick start
[code example]
## Advanced features
- **Form filling**: See [FORMS.md](FORMS.md)
- **API reference**: See [REFERENCE.md](REFERENCE.md)
What NOT to Include
- README.md
- INSTALLATION_GUIDE.md
- CHANGELOG.md
- User-facing documentation
Skills are for AI agents, not humans.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 2 of the 12 instructions most skill authoring skills give in 496 tokens
Counted across 408 of the 422 authors here whose files we hold, read 2026-09-06
- Keep SKILL.md under 500 lineshere, and in 118 of 408, across 104 files
- Write skill instructions in imperative formin 44 of 408, across 37 files
- Move detailed reference material into references filesin 41 of 408, across 34 files
- Run init_skill.py to initialize new skillsin 40 of 408, across 33 files
- Draft assertions while test runs are in progressin 32 of 408, across 25 files
- Keep description under 1024 charactersin 31 of 408, across 18 files
- Run package_skill.py once the skill is completein 29 of 408, across 23 files
- Spawn with-skill and baseline runs in the same turnin 28 of 408, across 21 files
- Test added scripts by actually running themhere, and in 27 of 408, across 21 files
- Follow the creation steps in orderin 24 of 408, across 17 files
- Generate the eval viewer before evaluating outputs yourselfin 24 of 408, across 17 files
- Write the description in third personin 24 of 408, across 18 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.