Create Skill logo

Create Skill

Organization
openvetta
create-skill

Create or update Vetta-compatible Agent Skills. Use when the user asks to create a skill, add a SKILL.md workflow, register a skill in skills-manifest.json, package a skill in a Vetta plugin, or add a built-in Vetta skill preset.

Overview

Publisheropenvetta
Repositoryopen-vetta
Skill namecreate-skill
Stars
299
Forks
51
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by openvetta on GitHub. Read the source before you install it.

Installation

Install the Create Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/openvetta/open-vetta/tree/main/packages/skill-presets/create-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/openvetta/open-vetta.git /tmp/open-vetta
mkdir -p .claude/skills
cp -r /tmp/open-vetta/packages/skill-presets/create-skill .claude/skills/create-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Create Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Create Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Create a Vetta Skill

Create focused Agent Skills that Vetta can execute and display. Treat the Skill files and their registration metadata as one change.

Choose the target

Infer the target from the request. If it is ambiguous, ask the user to choose before writing files.

TargetSkill directoryRequired registration
Global Vetta product skill~/.vetta/skills/<skill-name>/Update ~/.vetta/skills-manifest.json.
Project skill<project-root>/.vetta/skills/<skill-name>/No global manifest entry; project discovery is directory-based.
Plugin skill<plugin-root>/agent/skills/<skill-name>/Update plugin.json under agent.skillPaths.
Built-in Desktop skill<vetta-mono>/packages/skill-presets/<skill-name>/Update <vetta-mono>/packages/skill-presets/skills-manifest.json.

Do not place a global product Skill only in ~/.vetta/agent/skills; that directory is Agent-compatible but does not provide the Vetta product registration metadata required by the Skills UI.

Understand the directory protection

Skill and scene roots — ~/.vetta/skills, ~/.vetta/agent/skills, ~/.vetta/scene, <project-root>/.vetta/skills, and the .agents/skills equivalents — are read-only so that generated artifacts never land in them. Creating a new <root>/<skill-name>/ directory is exempt: once this session authors that directory, every file inside it stays writable for the rest of the session.

An already-installed Skill stays read-only. write and edit reject its files, and a shell command that touches them returns a warning to move the output out. To change one, edit the source it was installed from — the plugin, the repository preset, or the project directory — or ask the user to uninstall it first. Never work around the rejection with shell redirection.

Create the Skill

  1. Convert the requested name to lowercase kebab-case. It must be 1-64 characters containing only lowercase letters, digits, and hyphens. The directory name must match the frontmatter name.
  2. Inspect nearby Skills and relevant project documentation before writing. Reuse established terminology and tool names without copying unrelated instructions.
  3. Create <skill-directory>/SKILL.md with YAML frontmatter containing name and description.
  4. Write the body as imperative workflow instructions. State when to inspect context, when to ask a question, what files to create or edit, and how to verify completion.
  5. Add scripts/, references/, or assets/ only when genuinely required. Keep detailed reference material outside SKILL.md and link to it with relative paths.
  6. Do not overwrite an existing Skill or unrelated configuration without reading it first. Ask before replacing intentional behavior. Inside a protected root, an existing Skill directory cannot be overwritten at all — see the directory protection above.

Use this minimal structure:

markdown
---
name: example-skill
description: Describe what the Skill does and the user requests that should trigger it.
---

# Example Skill

Concise workflow instructions.

Register a global Vetta Skill

Read the full ~/.vetta/skills-manifest.json before editing it. The file is a root-level JSON object keyed by Skill name. Preserve every existing entry and add or update only the target Skill.

Use an entry shaped like this:

json
{
  "example-skill": {
    "name": "example-skill",
    "version": "1.0.0",
    "installedAt": "<current ISO-8601 timestamp>",
    "source": "custom",
    "enabled": true,
    "type": "skill",
    "alias": "Optional display name",
    "description": "Description aligned with SKILL.md frontmatter"
  }
}

If the manifest does not exist, create it as {} before adding the entry. Keep it valid JSON and avoid replacing unrelated Skills. Use the actual current timestamp rather than a placeholder.

Register a built-in Desktop Skill

Read the full packages/skill-presets/skills-manifest.json. Preserve existing entries and add the new Skill with source: "builtin", enabled: true, type: "skill", a version, and display metadata. The manifest key, entry name, directory name, and SKILL.md frontmatter name must all match.

The Desktop build only packages enabled directories registered in this manifest. An unregistered preset is an error.

Update plugin configuration

Only plugin-packaged Skills use plugin.json registration.

  1. Read the full plugin.json before editing it.
  2. Preserve every existing agent field and every existing skillPaths entry.
  3. Add a plugin-relative path. Prefer a shared parent such as "agent/skills" when it intentionally contains all plugin Skills; otherwise add the specific Skill directory.
  4. Do not add duplicate paths.

Example:

json
{
  "agent": {
    "skillPaths": ["agent/skills"]
  }
}

Quality rules

  • Keep the frontmatter valid YAML at the start of the file.
  • Make description specific enough for reliable triggering; include both the capability and common request language.
  • Keep SKILL.md under 500 lines. Move large examples and domain references into references/.
  • Use relative links for files inside the Skill directory.
  • Do not hardcode secrets, machine-specific absolute paths, or destructive commands.
  • Prefer the minimum files and instructions needed for the requested workflow.

Verify

  1. Confirm the final directory matches the selected target.
  2. Confirm SKILL.md exists and its frontmatter name matches the directory.
  3. Confirm the description clearly states when the Skill should run.
  4. For global or built-in Skills, parse the complete skills-manifest.json and confirm the target entry is present without losing existing entries.
  5. For plugin Skills, confirm plugin.json contains the correct relative agent.skillPaths entry and remains valid JSON.
  6. Report created or modified files and any validation that was not run.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Create Skill AI skill do?

Create or update Vetta-compatible Agent Skills. Use when the user asks to create a skill, add a SKILL.md workflow, register a skill in skills-manifest.json, package a skill in a Vetta plugin, or add a built-in Vetta skill preset.

Why use Create Skill on TypingMind?

Because you install it once and use it with any model. Create Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Create Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openvetta/open-vetta/tree/main/packages/skill-presets/create-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Create Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Create Skill?

As many as you like. As long as a model supports skills, you can use Create Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Create Skill AI skill free?

Yes. It is published on GitHub by openvetta under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇