Github Skill logo

Github Skill

Community
zeenie-ai
github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

Overview

Publisherzeenie-ai
RepositoryOpenCompany
Skill namegithub-skill
Stars
912
Forks
137
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 zeenie-ai on GitHub. Read the source before you install it.

Installation

Install the Github 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.
  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/zeenie-ai/OpenCompany.git /tmp/OpenCompany
mkdir -p .claude/skills
cp -r /tmp/OpenCompany/server/skills/github/github-skill .claude/skills/github-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github 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 Github 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 Github 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.

GitHub Skill

Wrapper over the official GitHub CLI. Typed operations for the core flows plus a custom passthrough that covers the entire gh surface.

Tool: github

Operations

OperationPurposeKey fields
repo_cloneClone a repository into the workflow workspaceclone_repo (OWNER/REPO or URL), clone_dir, path
pr_createOpen a pull request; returns its URLtitle, body, base, head, draft, fill, repo, path
pr_listList pull requests (parsed JSON)repo, state, limit
pr_mergeMerge a PRpr (number/URL/branch), merge_method (squash/merge/rebase), delete_branch, repo
issue_createOpen an issue; returns its URLtitle, body, labels, repo
issue_listList issues (parsed JSON)repo, state, limit
customAny other gh commandcommand — exactly what you would type after gh

Response

json
{
  "operation": "pr_list",
  "success": true,
  "url": null,
  "result": [{ "number": 42, "title": "Fix login", "state": "OPEN", "url": "https://github.com/o/r/pull/42", "author": {"login": "octocat"}, "headRefName": "fix-login", "baseRefName": "main", "createdAt": "…" }],
  "stdout": "…raw output…",
  "stderr_tail": null
}

pr_list / issue_list return parsed JSON in result (via gh's --json). pr_create / issue_create put the new item's URL in url. custom commands that emit JSON (api …, … --json fields) come back parsed in result too.

On failure the tool raises an error carrying gh's own message — surface it verbatim; gh's errors are precise (including "not logged in", which tells the user exactly how to authenticate).

Repository targeting

Inside a cloned checkout (after repo_clone, with path pointing at it) gh infers OWNER/REPO from the git remote. Everywhere else, set the repo field explicitly:

json
{ "operation": "pr_list", "repo": "octocat/hello-world", "state": "open" }

Common workflows

Clone, then work inside the checkout

json
{ "operation": "repo_clone", "clone_repo": "octocat/hello-world" }
{ "operation": "pr_create", "path": "hello-world", "fill": true }

path resolves relative to the workflow workspace.

Review flow

json
{ "operation": "pr_list", "repo": "octocat/hello-world", "state": "open" }
{ "operation": "custom", "command": "pr view 42 --repo octocat/hello-world --json title,body,files" }
{ "operation": "pr_merge", "pr": "42", "repo": "octocat/hello-world", "merge_method": "squash", "delete_branch": true }

Issues

json
{ "operation": "issue_create", "repo": "octocat/hello-world", "title": "Crash on login", "body": "Steps…", "labels": "bug" }
{ "operation": "issue_list", "repo": "octocat/hello-world", "state": "open", "limit": 50 }

The full gh surface via custom

json
{ "operation": "custom", "command": "api repos/{owner}/{repo}" }
{ "operation": "custom", "command": "api user" }
{ "operation": "custom", "command": "run list --repo octocat/hello-world --json databaseId,status,conclusion" }
{ "operation": "custom", "command": "release create v1.0.0 --notes 'First release'" }
{ "operation": "custom", "command": "repo create my-new-repo --private" }
{ "operation": "custom", "command": "gist create notes.md" }

Prefer --json <fields> (list/view commands) or gh api when you need machine-readable output. gh api supports {owner}/{repo} placeholders inside a checkout.

Quoting and escaping

command is parsed with shlex.split — quote arguments containing spaces with single quotes: custom: "release create v1.0.0 --notes 'First release'".

Authentication

The gh CLI owns its auth — OpenCompany never stores a token. Three equivalent ways to connect (any one is enough):

  1. Credentials Modal → GitHub → Login with GitHub — gh (auto-installed) starts its browser device flow: the modal shows a one-time code and opens github.com/login/device; enter the code and approve.
  2. gh auth login in a terminal on this machine.
  3. gh auth login --with-token in a terminal, piping a Personal Access Token (scopes: repo, read:org, gist).

If a command fails with an authentication error, tell the user to connect via one of these; don't ask them for a token.

Best practices

  1. Set repo explicitly unless you're operating inside a cloned checkout.
  2. Use fill: true on pr_create when commits already carry good messages.
  3. Return created URLs to the user (PRs, issues, releases).
  4. Destructive administration (repo delete, etc.) goes through custom and gh will require its own --yes-style confirmation flags — pass them only when the user explicitly asked.
  5. Surface gh error messages verbatim — don't paraphrase.

Frequently asked questions

What does the Github Skill AI skill do?

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

Why use Github Skill on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/github/github-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Github 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 Github Skill?

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

Is the Github Skill AI skill free?

Yes. It is published on GitHub by zeenie-ai 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 👇