# Creating Agent Skill

> Create and review Agent Skills that follow the open Agent Skills specification and best practices. Use when a user asks to create a new skill, build skill instructions, generate a SKILL.md file, review an existing skill for compliance, or improve skill quality. Covers skill structure, naming conventions, progressive disclosure, writing effective descriptions, creating actions and standards, and v…

- **Type:** Skill
- **Install:** `agentstack add skill-willvelida-code-minions-creating-agent-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [willvelida](https://agentstack.voostack.com/s/willvelida)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [willvelida](https://github.com/willvelida)
- **Source:** https://github.com/willvelida/code-minions/tree/main/packages/creating-agent-skill/skills/creating-agent-skill

## Install

```sh
agentstack add skill-willvelida-code-minions-creating-agent-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Creating Agent Skills

## Overview

This skill provides capabilities for creating and reviewing Agent Skills that comply with the [Agent Skills specification](https://agentskills.io/specification) and follow [authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices).

Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows. A skill is a folder containing a `SKILL.md` file with metadata and instructions, optionally bundled with scripts, references, and assets.

## Capabilities

| Capability | Action | Description |
|------------|--------|-------------|
| Create | `actions/create.md` | Generate a new, specification-compliant Agent Skill |
| Review | `actions/review.md` | Analyse an existing skill for compliance and improvements |

## Standards

This skill bundles the following standards in `standards/`:

| Standard | File | Description |
|----------|------|-------------|
| Specification | `specification.md` | Core Agent Skills format specification |
| Naming | `naming.md` | Naming conventions for skills and files |
| Descriptions | `descriptions.md` | Writing effective skill descriptions |
| Structure | `structure.md` | Directory structure and progressive disclosure |
| Instructions | `instructions.md` | Writing effective skill instructions |
| Clarifying Questions | `clarifying-questions.md` | Questioning framework for gathering skill requirements |
| Checklist | `checklist.md` | Consolidated compliance and quality checklist |

## Principles

### 1. Concise is Key

The context window is a shared resource. Only add context the agent doesn't already have. Challenge each piece of information: "Does the agent really need this explanation?"

### 2. Progressive Disclosure

Structure skills for efficient context use:
- **Metadata** (~100 tokens): `name` and `description` loaded at startup
- **Instructions** (.md`

## References

- [Agent Skills Specification](https://agentskills.io/specification)
- [What are Agent Skills?](https://agentskills.io/what-are-skills)
- [Skill Authoring Best Practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
- [Example Skills](https://github.com/anthropics/skills)
- [Reference Library](https://github.com/agentskills/agentskills/tree/main/skills-ref)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [willvelida](https://github.com/willvelida)
- **Source:** [willvelida/code-minions](https://github.com/willvelida/code-minions)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-willvelida-code-minions-creating-agent-skill
- Seller: https://agentstack.voostack.com/s/willvelida
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.