Github

Community

Mathews-Tom

github

GitHub CLI operations via `gh` for issues, PRs, Actions, releases, and REST/GraphQL API with `--json`/`--jq` parsing. Triggers on: "create an issue", "submit a PR", "check CI status", "why did CI fail", "merge a PR", or pasted GitHub URLs.

Overview

Publisher	Mathews-Tom
Repository	`armory`
Skill name	`github`
Stars	318
Forks	47
Bundled files	12
License	MIT
Links	Skill source Repository Homepage

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.
12 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Mathews-Tom 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.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/Mathews-Tom/armory.git /tmp/armory
mkdir -p .claude/skills
cp -r /tmp/armory/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

All GitHub operations use the gh CLI. Prefer --json with --jq for structured, parseable output. Use --repo owner/repo when not inside a git repository with a configured remote. Use --web to open any resource in the browser.

Prerequisites and Auth

Installation

Platform	Command
macOS	`brew install gh`
Debian/Ubuntu	`sudo apt install gh`
Windows	`winget install GitHub.cli`

Authentication

bash
gh auth login           # interactive OAuth login
gh auth status          # check current auth and active account

Required OAuth Scopes

Scope	Grants Access To
`repo`	Private repos, issues, PRs, commits, status
`read:org`	Org membership, team listing
`workflow`	Trigger and manage GitHub Actions workflows
`gist`	Create and manage gists
`delete_repo`	Delete repositories (not granted by default)
`admin:org`	Manage org settings, teams, members
`project`	Read/write access to ProjectV2 boards

Add missing scopes without re-authenticating from scratch:

bash
gh auth refresh --scopes repo,read:org,workflow

Reference Routing

User intent	Load
Create/list/view/edit/close issues, add comments	`references/issues.md`
Create/list/view/review/merge/edit/close pull requests	`references/pull-requests.md`
List runs, view logs, trigger/rerun/watch workflows, artifacts	`references/ci-actions.md`
Create/fork/clone/view/edit/archive/delete repositories	`references/repos.md`
Create/list/view/edit/upload/delete releases	`references/releases.md`
Search repos, issues, PRs, code, commits	`references/search.md`
Raw REST/GraphQL via `gh api`, pagination, rate limit	`references/api.md`
GraphQL cost model, bulk queries, mutations, rate limits	`references/graphql-queries.md`
Multi-step workflow recipes (PR lifecycle, CI triage, releases)	`references/automation-workflows.md`
Create/list/view/edit/delete gists	`references/gists.md`
List orgs, teams, members	`references/orgs.md`

Workflow Pattern

Identify user intent from the routing table above.
Load the matching references/<file>.md for command syntax and examples.
Execute the gh command with --repo owner/repo and --json/--jq as needed.
On error, consult the Error Handling table below.

Error Handling

Error	Cause	Resolution
HTTP 401 Unauthorized	Token expired or revoked	Run `gh auth login` to re-authenticate
HTTP 403 Forbidden	Insufficient permissions or rate limited	Check `gh auth status` for scopes; check `gh api rate_limit`
HTTP 404 Not Found	Repo does not exist, is private without `repo` scope, or resource deleted	Verify repo name; run `gh auth refresh --scopes repo`
HTTP 422 Unprocessable Entity	Invalid payload — missing required field, validation error	Check request body fields match API schema
HTTP 429 Too Many Requests	REST rate limit exceeded (5000 req/hr authenticated)	Wait for `X-RateLimit-Reset` timestamp; reduce request frequency
GraphQL rate limit exceeded	Used more than 5000 points/hr	Reduce query complexity or wait; see `references/graphql-queries.md`
"no git remotes found"	Running `gh` outside a git repo without `--repo`	Add `--repo owner/repo` to the command
Insufficient OAuth scopes	Token lacks required scope for the operation	Run `gh auth refresh --scopes scope1,scope2`
Duplicate issue/PR title	Not a real error — GitHub allows duplicates, but check before creating	Search with `gh issue list` or `gh pr list` first
Archived repo blocks writes	Repo is archived; all write operations fail	Unarchive with `gh repo edit owner/repo --archived=false` or use a different repo

Enable debug logging to see raw HTTP requests and responses:

bash
GH_DEBUG=api gh pr list --repo owner/repo

Calibration Rules

Prefer --json over parsing text output. Text output formats are unstable across gh versions. Always use --json field1,field2 to get machine-readable output.
Use --jq to minimize output before processing. Filter at the source rather than piping large JSON blobs to external tools. --jq runs server-side and reduces data transferred.
Prefer higher-level commands over raw API. Use gh issue create instead of gh api repos/.../issues -X POST. High-level commands handle auth, pagination, and error formatting automatically.
Use --repo consistently when outside a git directory. Never rely on implicit repo detection in scripts or CI environments. Always pass --repo owner/repo explicitly.
Use GraphQL only for nested or bulk data. For single-resource fetches and mutations with simple payloads, REST is faster to write, easier to debug, and predictable under rate limits.

Limitations

Network required — all gh commands require internet access; no offline mode.
GraphQL point budget — 5000 points/hr for authenticated users. Complex queries with high first/last values consume points faster. See references/graphql-queries.md.
Secrets are write-only — gh secret set works, but there is no gh secret get. Secret values cannot be retrieved after creation.
Org admin operations — managing org settings, teams, and SAML requires the admin:org scope, which is not granted by default.
Artifact retention — workflow artifacts are retained for 90 days by default. Expired artifacts cannot be downloaded.

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 Github AI skill do?

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/Mathews-Tom/armory/tree/main/skills/github. 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 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 Mathews-Tom 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

Resolving Merge Conflicts

mattpocock

CommunityPopular

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

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.

Tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

To Spec

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

GitHub

Prerequisites and Auth

Installation

Authentication

Required OAuth Scopes

Reference Routing

Workflow Pattern

Error Handling

Calibration Rules

Limitations

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now