Skip to main content
skill CX Codex

skill-name · resciencelab — Claude Code skill template: SKILL.md structure

A starter layout for a skill: SKILL.md sections, script and example folders, a troubleshooting block. Useful when you are writing your first one.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ReScienceLab/opc-skills --skill skill-name -a claude-code
npx skills add ReScienceLab/opc-skills --skill template -a claude-code
Open on GitHub

What skill-name does

This is a template, not a working tool. It ships a SKILL.md file with the required YAML block at the top: name and description, where the description tells the agent when to pull the skill in. Below that sit sections for prerequisites, quick start, usage examples and a command table.

Scripts go in scripts/, full workflow examples in examples/, and the skill entry in skills.json. Commands run from the skill directory, in the shape python3 scripts/script.py. The prerequisites section includes a sample environment variable and API key, so there is already a slot for that if your skill calls an outside service.

You install it for the structure, not the behaviour: with no scripts and no description of your own it does nothing. Copy the template into skills/your-skill-name/ and fill the sections in.

What it helps with

  • lay out a new skill across scripts/ and examples/
  • write a description that tells the agent when to trigger the skill
  • document environment variables and API keys before the first run
  • register the skill in skills.json
  • collect example script calls with flags and parameters

Example prompts for the agent

  • copy the template into skills/your-skill-name/ and fill in the frontmatter
  • add an environment variables section to SKILL.md for my API
  • check that the description in frontmatter says when to use the skill

How to install skill-name

1Skills CLI (Vercel)

npx skills add ReScienceLab/opc-skills --skill skill-name -a claude-code
npx skills add ReScienceLab/opc-skills --skill template -a claude-code

2Manually: put the files in place

~/.claude/skills/template/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/template/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-name

How do I install skill-name in Claude?

Run npx skills add ReScienceLab/opc-skills --skill skill-name -a claude-code. The file lands at ~/.claude/skills/template/SKILL.md.

What does skill-name do?

It is a skill template: the SKILL.md structure, sections for prerequisites, examples, commands and troubleshooting. There is no logic inside, you write that yourself.

How is it different from a finished skill in the same repo?

A finished skill already does something specific, while the template only sets the shape. People take it as a base and fill it with scripts.

Source text

SKILL.md · Apache-2.0
---
name: skill-name
description: Clear description of what this skill does and when to use it. Include trigger keywords and contexts inline, e.g. "Use when user wants to X, Y, or Z."
---

# Skill Name

Brief description of the skill and its purpose.

## Prerequisites

List any setup requirements:
- Environment variables needed
- API keys required
- Dependencies (already listed in frontmatter above)

Example setup:
```bash
export SKILL_API_KEY="your_api_key"
```

## Quick Start

How to use the skill quickly:

```bash
cd <skill_directory>
python3 scripts/command.py --option value
```

## Usage Examples

### Example 1: Basic usage

```bash
python3 scripts/script.py "input"
```

Output:
```
Expected output here
```

### Example 2: Advanced usage

```bash
python3 scripts/script.py "input" --flag --option value
```

## Commands

All commands run from the skill directory.

### Command 1
```bash
python3 scripts/script1.py --help
python3 scripts/script1.py "param1" --option value
```

### Command 2
```bash
python3 scripts/script2.py "param1" "param2"
```

## Scripts

- `script1.py` - Description of what this script does
- `script2.py` - Description of what this script does

## API Info

- **Base URL**: (if applicable)
- **Rate Limits**: (if applicable)
- **Auth**: (how authentication works)
- **Docs**: Link to official documentation

## Troubleshooting

### Issue 1

**Symptom**: Description of the problem

**Solution**:
1. Step 1
2. Step 2

### Issue 2

**Symptom**: Description of the problem

**Solution**:
1. Step 1
2. Step 2

## Examples

See `examples/` directory for full workflow examples.

## References

- [Official Documentation](https://example.com)
- [API Reference](https://example.com/api)
- [Related Skill](https://github.com/ReScienceLab/opc-skills/tree/main/skills/related-skill)

## Notes

- Important note 1
- Important note 2

---

## Frontmatter Guide

The YAML frontmatter at the top of this file is required:

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `name` | string | ✓ | Unique identifier (kebab-case) |
| `description` | string | ✓ | What the skill does and when to use it. Include trigger keywords and "Use when..." contexts inline. |

## Creating Your Skill

1. Copy this template to `skills/your-skill-name/`
2. Update the YAML frontmatter
3. Write your SKILL.md documentation
4. Add Python/shell scripts in `scripts/`
5. Add usage examples in `examples/`
6. Update `skills.json` with your skill entry
7. Test with your agent before submitting PR

© ReScienceLab · Apache-2.0 · ReScienceLab/opc-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

skill-name by other authors comes first.

From the same set10

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor