Github logo

Github

OrganizationPopular
Team-Commonly
github

Interact with GitHub (issues, PRs, repos, releases) using the `gh` CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Overview

PublisherTeam-Commonly
Repositorycommonly
Skill namegithub
Stars
1.3K
Forks
187
Bundled files
Instructions only
LicenseApache-2.0
Links
Skill sourceRepositoryHomepage
  • 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 Team-Commonly on GitHub. Read the source before you install it.

Installation

Install the Github 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/Team-Commonly/commonly.git /tmp/commonly
mkdir -p .claude/skills
cp -r /tmp/commonly/backend/commonly-bundled-skills/github .claude/skills/github
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github 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 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 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 — GitHub via the gh CLI

The gh CLI is installed on PATH. The gateway environment provides a GITHUB_PAT env var (a Team-Commonly fine-grained PAT with repo + PR scope) which gh picks up automatically as GH_TOKEN.

The active GitHub identity is Team-Commonly bot identity — anything you push, comment, or open will be attributed to that account.

No shell? Don't use gh. The gh examples below assume a real shell (codex / claude-code runtimes). OpenClaw runtimes (theo/nova/pixel/ops) have no shell and cannot run gh at all. For those agents:

  • Read a PR diff: web.fetch the raw public diff at https://patch-diff.githubusercontent.com/raw/Team-Commonly/commonly/pull/<N>.diff.
  • Post a review verdict: write it into the dev pod chat (read-only review).
  • codex / claude-code runtimes have a shell: use gh directly, as below.

There is deliberately no commonly_pr_* MCP tool. The pair that existed was removed because it spent a shared server-side credential on a caller-chosen repository, so any agent could review any repo that credential reached. gh acts as the machine's own GitHub identity and supports line-level comments, which those tools never did.

Common operations

Issues

bash
# List open issues in a repo
gh issue list --repo Team-Commonly/commonly --state open

# Create an issue
gh issue create --repo Team-Commonly/commonly \
  --title "Title here" \
  --body "Body here"

# Comment on an issue
gh issue comment 123 --repo Team-Commonly/commonly --body "comment"

Pull requests

bash
# List open PRs
gh pr list --repo Team-Commonly/commonly --state open

# View a PR (diff, comments, status)
gh pr view 287 --repo Team-Commonly/commonly --json title,body,additions,deletions

# Get a PR's diff
gh pr diff 287 --repo Team-Commonly/commonly

# Comment on a PR
gh pr comment 287 --repo Team-Commonly/commonly --body "comment text"

# Check CI status
gh pr checks 287 --repo Team-Commonly/commonly

Repos / files

bash
# View a file at a specific ref
gh api repos/Team-Commonly/commonly/contents/README.md --jq '.content' | base64 -d

# Search code
gh search code 'commonly_attach_file' --repo Team-Commonly/commonly --limit 20

Workflows / runs

bash
# List recent workflow runs
gh run list --repo Team-Commonly/commonly --limit 10

# View a specific run's logs
gh run view 12345 --repo Team-Commonly/commonly --log

Heredoc for multi-line PR/issue bodies

bash
gh pr comment 287 --repo Team-Commonly/commonly --body "$(cat <<'EOF'
Multi-line comment.

- Bullet one
- Bullet two
EOF
)"

Useful patterns

  • Always pass --repo <org/name> explicitly; the gateway's working directory may not be inside a clone.
  • Prefer --json <fields> --jq <expr> over scraping plain output — more reliable and structured.
  • Don't push code directly — the dev pattern is "open a PR with gh pr create --base main --head <branch>" and let humans review.

When NOT to use github

  • For long-running coding tasks → delegate to sam-local-codex via DM (per ADR-005 Stage 3).
  • For pasting GitHub URLs into chat → just include the URL; the chat surface renders it.

Frequently asked questions

What does the Github AI skill do?

Interact with GitHub (issues, PRs, repos, releases) using the `gh` CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Why use Github on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Team-Commonly/commonly/tree/main/backend/commonly-bundled-skills/github. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Github?

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?

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

Is the Github AI skill free?

Yes. It is published on GitHub by Team-Commonly 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.

Related AI Skills

View all
mattpocock logo

Prototype

mattpocock
CommunityPopular

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

22.3K
264.4K
3 files
View
mattpocock logo

Research

mattpocock
CommunityPopular

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading…

22.3K
264.4K
1 files
View
mattpocock logo

Resolving Merge Conflicts

mattpocock
CommunityPopular

Use when you need to resolve an in-progress git merge/rebase conflict.

22.3K
264.4K
1 files
View
mattpocock logo

Setup Matt Pocock Skills

mattpocock
CommunityPopular

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

22.3K
264.4K
6 files
View

Set up your own AI workspace now

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