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 validation.
Install
npx skills add willvelida/code-minions --skill creating-agent-skillgit clone --depth 1 https://github.com/willvelida/code-minions.git /tmp/code-minions
mkdir -p ~/.claude/skills
cp -r /tmp/code-minions/packages/creating-agent-skill/skills/creating-agent-skill ~/.claude/skills/creating-agent-skillPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 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 |
Details
- Skill name
creating-agent-skill- Repository
- willvelida/code-minions
- Path
packages/creating-agent-skill/skills/creating-agent-skill/SKILL.md- License
- Apache-2.0
- Repo updated
- 11 June 2026
FAQ
What does the Creating Agent Skill skill do?
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 validation.
How do I install the Creating Agent Skill skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add willvelida/code-minions --skill creating-agent-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Creating Agent Skill popular?
It lives in willvelida/code-minions, which has 23 GitHub stars and 2 forks.
Related skills
Creating Agents
23willvelida/code-minions
Create and review agent definition files (agents.md) that give AI coding agents a clear persona, project knowledge, executable commands, code style examples, and explicit boundaries. Use when a user asks to create an agent, define an agent persona, write an agents.md file, set up a custom Copilot agent, review an existing agent definition, or improve agent quality. Covers the six core areas: commands, testing, project structure, code style, git workflow, and boundaries.
Creating Devcontainers
23willvelida/code-minions
Create and review DevContainer configurations that follow organisational standards. Use when a user asks to set up a dev container, configure a development environment, create a devcontainer.json, add lifecycle hooks, review an existing DevContainer for compliance, or improve container security. Covers base images, features, extensions, lifecycle hooks, and security hardening.
Creating Documentation
23willvelida/code-minions
Create and review README files and repository documentation that follows best practices for clarity, accessibility, and discoverability. Use when a user asks to create a README, write project documentation, improve existing documentation, add a CONTRIBUTING guide, review documentation for accessibility, or document a new repository.
C Level Advisor
40ArogyaReddy/alirezarezvani-claude-skills
10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured recommendations. For founders needing executive-level decision support.
Dispatching Parallel Agents
43lifangda/claude-plugins
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Board
40ArogyaReddy/alirezarezvani-claude-skills
Read, write, and browse the AgentHub message board for agent coordination.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.