Degit logo

Degit

CommunityPopular
Rich-Harris
degit

Download a repository snapshot or template with degit

Overview

PublisherRich-Harris
Repositorydegit
Skill namedegit
Stars
7.9K
Forks
281
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Rich-Harris on GitHub. Read the source before you install it.

Installation

Install the Degit 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.
  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/Rich-Harris/degit.git /tmp/degit
mkdir -p .claude/skills
cp -r /tmp/degit/skills/degit .claude/skills/degit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Degit 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 Degit 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 Degit 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.

Help the user scaffold a project with degit. Use npx degit@latest unless they have installed degit globally.

Start with the smallest command that matches their request:

sh
npx degit@latest user/repo
npx degit@latest user/repo my-project
npx degit@latest user/repo#branch my-project

Sources can be GitHub (user/repo, github:user/repo, or a GitHub URL), GitLab (gitlab:user/repo, a GitLab URL, or gitlab://host/user/repo), Bitbucket (bitbucket:user/repo or URL), Sourcehut (git.sr.ht/user/repo, SSH form, or URL), or Gist (https://gist.github.com/<id>, https://gist.github.com/<user>/<id>, git@gist.github.com:<id>.git, or ssh://git@gist.github.com/<id>). A #ref can name a branch, tag, or commit. A source may include a subdirectory path.

  • The destination defaults to the current directory and must be empty. Do not suggest --force unless the user explicitly wants to overwrite its contents.
  • Use --cache to require a cached copy (no network). Without --cache, degit tries the network first and falls back to the cached copy if the network is unreachable. Use --verbose to diagnose failures. --mode=git still works but is unnecessary; tar snapshots are the default.
  • Use --files <paths> or -F <paths> to clone only specific files or directories; separate multiple paths with commas or repeat the flag.
  • Private repositories are handled automatically, with SSH fallback when needed. SSH/private use requires git on PATH and working repository credentials.
  • For reusable shortcuts, use degit alias <repo> <name>, then degit <name>; use degit ls and degit unalias <name> to manage aliases.
  • If a template needs post-download changes, explain that its top-level degit.json can use clone, search_replace, and remove actions. search_replace uses a named environment variable for its replacement value.

If source, ref, destination, or whether the destination is empty is unknown, ask before giving a potentially destructive command.

Frequently asked questions

What does the Degit AI skill do?

Download a repository snapshot or template with degit

Why use Degit on TypingMind?

Because you install it once and use it with any model. Degit 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 Degit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Rich-Harris/degit/tree/master/skills/degit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Degit?

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 Degit?

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

Is the Degit AI skill free?

Yes. It is published on GitHub by Rich-Harris under the MIT 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 👇