Gh Action logo

Gh Action

OrganizationPopular
live-codes
gh-action

Use the "Preview in LiveCodes" GitHub Action to generate preview playground links for pull request code changes. Automates playground creation and PR comments.

Overview

Publisherlive-codes
Repositorylivecodes
Skill namegh-action
Stars
1.5K
Forks
271
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 live-codes on GitHub. Read the source before you install it.

Installation

Install the Gh Action 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/live-codes/livecodes/tree/develop/.agents/skills/livecodes/gh-action
  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/live-codes/livecodes.git /tmp/livecodes
mkdir -p .claude/skills
cp -r /tmp/livecodes/.agents/skills/livecodes/gh-action .claude/skills/gh-action
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gh Action 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 Gh Action 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 Gh Action 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.

LiveCodes — GitHub Action: Preview in LiveCodes

The Preview in LiveCodes GitHub Action generates preview links to LiveCodes playgrounds for code changes in pull requests and posts them as PR comments.

Use case: Library authors can preview changes in the playground before merging PRs.

How It Works

  1. PR is created or updated
  2. Action optionally installs dependencies and builds the project
  3. Action scans .livecodes/ folder for playground configurations
  4. Generates playground URLs with your new code
  5. Posts comment with preview links to the PR

Setup

Two Required Workflow Files

The action requires two workflow files that must be merged to the default branch first.

1. Trigger workflow .github/workflows/livecodes-preview.yml:

yaml
name: livecodes

on: [pull_request]

jobs:
  build_and_prepare:
    runs-on: ubuntu-latest
    name: Generate Playgrounds
    steps:
      - name: Checkout
        uses: actions/checkout@v3

      - name: Build and generate
        uses: live-codes/preview-in-livecodes@v1
        with:
          # Optional: install-command: "npm install"
          # Optional: build-command: "npm run build"
          # Optional: base-url: "https://{{LC::REF}}.my-project.pages.dev"

2. Comment workflow .github/workflows/livecodes-post-comment.yml:

yaml
name: comment

on:
  workflow_run:
    workflows: ['livecodes']
    types:
      - completed

jobs:
  upload:
    runs-on: ubuntu-latest
    permissions:
      pull-requests: write
    if: >
      github.event.workflow_run.event == 'pull_request' &&
      github.event.workflow_run.conclusion == 'success'
    steps:
      - uses: live-codes/pr-comment-from-artifact@v1
        with:
          GITHUB_TOKEN: ${{ github.token }}

Two separate workflows are needed because each runs in a different security context. See GitHub security article for details.

Action Inputs

InputRequiredDescription
install-commandNoInstall command (e.g., npm install)
build-commandNoBuild command (e.g., npm run build)
base-urlNoBase URL for deployed assets. Supports dynamic values.
artifactNoArtifact name (default: pr)
GITHUB_TOKENNoGitHub token (default: ${{ github.token }})

Action Outputs

OutputDescription
messageMarkdown message with preview links for PR comment

Configure Playgrounds

Create JSON files in .livecodes/ folder. Each file becomes a playground link.

Example Configure Project JSON

.livecodes/hello-world.json:

json
{
  "title": "JavaScript Starter",
  "markup": {
    "language": "html",
    "content": "<h1>Hello, World!</h1>"
  },
  "script": {
    "language": "javascript",
    "content": "import { demo } from 'my-lib';\n\ndemo();"
  },
  "imports": {
    "my-lib": "{{LC::TO_DATA_URL(./index.js)}}"
  }
}

The title property becomes the playground name in the message. If omitted, filename is used.

Dynamic Values

Use these placeholders in project JSON and base-url:

PlaceholderDescription
{{LC::REF}}Branch or tag name of PR head
{{LC::SHA}}Full commit SHA
{{LC::SHORT_SHA}}Short SHA (first 7 characters)
{{LC::PR}}Pull request number
{{LC::REPO}}Repository name

File Placeholders (project JSON only)

PlaceholderDescription
{{LC::TO_URL(./file.js)}}URL of file with base-url prepended
{{LC::TO_DATA_URL(./file.js)}}File converted to data URL (for small files)

Using Newly Added Code in Playgrounds

Three strategies to make PR code available to playgrounds:

1. Deploy to Preview URL (Recommended)

Use Cloudflare Pages or Netlify for automatic preview deployments.

yaml
# workflow
base-url: 'https://{{LC::REF}}.my-project.pages.dev'

In project JSON:

json
{
  "imports": {
    "my-lib": "{{LC::TO_URL(./dist/index.js)}}"
  }
}

2. Use CDN Mirroring GitHub

Link to files via jsDelivr or similar:

yaml
# workflow
base-url: 'https://cdn.jsdelivr.net/gh/{{LC::REPO}}@{{LC::SHA}}/'

3. Data URLs (Small Files Only)

Encode files directly. Stored at dpaste.com (limit: 1M chars, expires after 365 days).

json
{
  "imports": {
    "my-lib": "{{LC::TO_DATA_URL(./index.js)}}"
  }
}

Common Mistakes

HIGH Workflow files not on default branch

The workflow files must be merged to the default branch (e.g., main) before the action can be triggered by PRs.

Wrong:

yaml
# Creating PR with workflow files
# Action won't run until merged to default branch

Correct:

bash
# First merge workflow files to default branch
git checkout main
git merge feature/add-gh-action
git push

# Now PRs can trigger the action

Source: GitHub Actions documentation on workflow_run event

MEDIUM Missing permissions for PR comments

The comment workflow needs pull-requests: write permission.

yaml
jobs:
  upload:
    permissions:
      pull-requests: write # Required!

MEDIUM Using data URLs for large files

Data URLs are limited to ~1M characters at dpaste.com. Large builds will fail.

Wrong:

json
{
  "imports": {
    "my-lib": "{{LC::TO_DATA_URL(./dist/bundle.js)}}" // Too large!
  }
}

Correct:

yaml
# Use base-url and TO_URL for large files
base-url: 'https://{{LC::REF}}.my-project.pages.dev'

Example PR Comment Output

markdown
## Preview in LiveCodes

**Latest commit:** abc1234  
**Last updated:** Jan 15, 2024 3pm (UTC)

|   Playground   | Link                                                               |
| :------------: | ------------------------------------------------------------------ |
| **JavaScript** | [https://livecodes.io?x=code/...](https://livecodes.io?x=code/...) |
|   **React**    | [https://livecodes.io?x=code/...](https://livecodes.io?x=code/...) |

See [documentations](https://github.com/live-codes/preview-in-livecodes) for usage instructions.

Related Skills

  • import-export - Understanding project configuration objects
  • self-hosting - Using custom appUrl for self-hosted playgrounds

Frequently asked questions

What does the Gh Action AI skill do?

Use the "Preview in LiveCodes" GitHub Action to generate preview playground links for pull request code changes. Automates playground creation and PR comments.

Why use Gh Action on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/live-codes/livecodes/tree/develop/.agents/skills/livecodes/gh-action. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gh Action?

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 Gh Action?

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

Is the Gh Action AI skill free?

Yes. It is published on GitHub by live-codes 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 👇