Github Pages Publisher logo

Github Pages Publisher

Community
artwist-polyakov
github-pages-publisher

Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo under a strict year/year-month/page-slug directory layout, then committed and pushed, with a final public artifact URL returned.

Overview

Publisherartwist-polyakov
Repositorypolyakov-claude-skills
Skill namegithub-pages-publisher
Stars
218
Forks
55
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by artwist-polyakov on GitHub. Read the source before you install it.

Installation

Install the Github Pages Publisher 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/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/github-pages-publisher/skills/github-pages-publisher
  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/artwist-polyakov/polyakov-claude-skills.git /tmp/polyakov-claude-skills
mkdir -p .claude/skills
cp -r /tmp/polyakov-claude-skills/plugins/github-pages-publisher/skills/github-pages-publisher .claude/skills/github-pages-publisher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Pages Publisher 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 Pages Publisher 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 Pages Publisher 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 Pages Publisher

Publish already-built static artifacts to a GitHub Pages repository.

This skill is the deployment/output layer for page artifacts created by other skills.

Required repository layout

Every published artifact must go into this path shape inside the target repo:

<year>/<year>-<month>/<page-slug>/

Example:

  • 2026/2026-03/my-landing-page/

Never publish flat at repo root. Never skip the year or year-month nesting.

What this skill expects

Input should already exist as one of these:

  • a folder of built static files
  • a single HTML artifact plus local assets
  • a small static site ready to serve from a subdirectory

This skill should not do major frontend design work. It should package and publish what already exists.

Default publishing rules

  • preserve relative asset paths when possible
  • prefer index.html as entrypoint inside the target page directory
  • keep the output self-contained inside the page folder
  • avoid breaking existing published pages
  • if the same slug is republished, update the existing folder contents deliberately

URL contract

Always return the final public URL of the artifact.

Assume GitHub Pages serves from the repo's configured Pages base URL. The final URL should be:

<pages-base-url>/<year>/<year>-<month>/<page-slug>/

or, if needed explicitly:

.../<page-slug>/index.html

Prefer the clean directory URL when it resolves correctly.

Workflow

  1. Determine the publish date bucket:
    • year = YYYY
    • year-month = YYYY-MM
  2. Create or update target directory:
    • <year>/<year-month>/<page-slug>/
  3. Copy artifact files into that directory
  4. Optimize oversized raster images when practical, unless original-size sharing is intentional
  5. Verify there is an entrypoint (index.html normally)
  6. Run pre-publish validation (see section above)
  7. Commit and push to the Pages repo using the configured fine-grained token workflow
  8. Return the final public URL

Publishing command

bash
python3 scripts/publish_static.py --source <dir-or-html> --slug <name> [--date YYYY-MM-DD] [--image-max-kb 500]

The script copies the artifact into YYYY/YYYY-MM/slug/, optimizes oversized .jpg, .jpeg, .png, and .webp images, commits, pushes, and prints the final public URL.

Image optimization

Image optimization is a recommendation, not a hard requirement. By default, the publishing script tries to keep each raster image under 500KB by stripping metadata, recompressing, and resizing long edges when needed.

Use --image-max-kb <kb> for a different target. Use --keep-large-images or --image-max-kb 0 when the user explicitly needs original-size images (for example, a full-resolution infographic, map, or downloadable media asset).

The original --source artifact is not changed. Optimization happens only after files are copied into the publish repo target directory. If Pillow/uv is unavailable or optimization fails, continue publishing originals and mention the warning.

Manual console run for a prepared artifact:

bash
uv run --with pillow python3 scripts/optimize_images.py <artifact-dir> --max-kb 500

Slug rules

  • use lowercase letters, digits, and hyphens
  • keep it short and descriptive
  • avoid spaces, underscores, Cyrillic, timestamps unless needed for uniqueness
  • if the title is user-facing, the slug can still be normalized separately

Pre-publish validation

Before pushing, the agent must verify:

  • artifact has index.html entrypoint
  • oversized raster images are optimized when practical, unless original-size sharing is intentional
  • no absolute local paths in HTML/CSS
  • no secrets in files
  • all local assets reachable from the target folder
  • page renders correctly (if browser tools are available, check at desktop 1440px and mobile 375px)

Safety rules

  • do not delete unrelated directories in the Pages repo
  • only replace contents of the target page directory being published
  • if overwriting, say so in the result
  • do not expose the token in output, logs, or committed files
  • do not push artifacts that fail local viewport validation

Config

Read config/README.md for required environment variables and URL derivation.

References

Read if needed:

  • references/publish-checklist.md — operational checklist before pushing

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 Pages Publisher AI skill do?

Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo under a strict year/year-month/page-slug directory layout, then committed and pushed, with a final public artifact URL returned.

Why use Github Pages Publisher on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/github-pages-publisher/skills/github-pages-publisher. 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 Pages Publisher?

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 Pages Publisher?

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

Is the Github Pages Publisher AI skill free?

Yes. It is published on GitHub by artwist-polyakov 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 👇