Deploy logo

Deploy

Organization
FluidForm-ai
deploy

Deploy / publish a single HTML file (deck, page, doc) to FluidDocs hosting using the self-contained scripts/deploy.sh. Handles browser sign-in / re-auth automatically, then opens the live URL in the browser. Trigger on "deploy", "publish", "ship it", "push it live", "put it online", "host this", or any request to make an HTML file publicly viewable.

Overview

PublisherFluidForm-ai
Repositoryfluiddocs-deck-builder
Skill namedeploy
Stars
33
Forks
2
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 FluidForm-ai on GitHub. Read the source before you install it.

Installation

Install the Deploy 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/FluidForm-ai/fluiddocs-deck-builder/tree/main/skills/deploy
  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/FluidForm-ai/fluiddocs-deck-builder.git /tmp/fluiddocs-deck-builder
mkdir -p .claude/skills
cp -r /tmp/fluiddocs-deck-builder/skills/deploy .claude/skills/deploy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deploy 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 Deploy 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 Deploy 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.

Deploy

Publish a single HTML file to FluidDocs hosting. scripts/deploy.sh is self-contained. It handles auth, upload, and project-mapping on its own. Your job is to run it correctly and open the result. Do not re-implement, inspect, or second-guess the script. Just run it.

What the script does (so you don't have to analyze it)

  • Finds HTML files in the current directory only (find . -maxdepth 1). So you must run it from the folder that contains the target file.
  • If exactly one HTML file is present, it auto-selects it. If several, it prompts for a number.
  • Caches an auth token at ~/.config/fluiddocs/auth.json. If the token is missing or expired, it prints a sign-in URL, opens the browser, and polls for up to 5 minutes while the user authorizes.
  • Uploads the file and prints ✓ Deployed → <URL> on success.
  • Records the file→project mapping in ./.fluid-docs.json, so re-deploying the same file updates the existing project instead of creating a duplicate. Keep this file; don't delete it.
  • Flags you use: --name "Friendly Title" (project name), --host URL (alternate server), --logout (clear cached creds for a fresh sign-in). The script also has --public and --slug, but do not use them: visibility and publishing are the user's choice, made in the FluidDocs app, never set from the CLI by you.

Procedure

  1. Pick the target file. If the user names one, use it. Otherwise use the obvious HTML file in context (e.g. the deck you just built). If genuinely ambiguous, ask which file, one short question, then proceed.

  2. Always pass --name "Friendly Title". Without it the project name defaults to the raw filename slug, which is hard to scan in the dashboard. Derive a clean human title (e.g. "Mushee · Seed Pitch").

  3. Run the script from the file's directory. The script lives at ${CLAUDE_PLUGIN_ROOT}/scripts/deploy.sh (plugin install), ~/.claude/skills/deploy/scripts/deploy.sh (manual install), or scripts/deploy.sh at the repo root. From the directory containing the HTML:

    bash
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/deploy.sh" --name "Friendly Title"

    Run it with network access enabled and a generous timeout (up to 600000 ms). The auth poll can take a few minutes while the user signs in. The script opens the user's browser itself when auth is needed; tell the user to complete the sign-in there.

  4. If the run can't do interactive sign-in (sandboxed shell with no network, or the browser can't be driven), hand the command to the user to run in-session with the ! prefix instead, so auth happens in their own browser:

    ! cd <deck-dir> && bash "<path>/scripts/deploy.sh" --name "Friendly Title"
  5. On success, open the live URL in the browser. The script prints but does not open the deployed URL. You do. Capture the URL after ✓ Deployed → and open it:

    bash
    open "<deployed-url>"        # macOS
    # xdg-open "<deployed-url>"  # Linux

    Hand the link back as a private preview only (a plain deploy is private; see Hard rules). Tell the user that to share it, they open it in the FluidDocs app and use Publish / Share or Document Properties to set it to private, unlisted, or public. Do not run --public or --slug yourself; visibility is set by the user in the app.

Re-auth

If the user wants to switch accounts or the token is broken, run bash "${CLAUDE_PLUGIN_ROOT}/scripts/deploy.sh" --logout first, then deploy again to trigger a fresh sign-in.

Hard rules

  • Never deploy without --name.
  • Run from the file's own directory (the script is directory-scoped).
  • Preserve ./.fluid-docs.json. It's what keeps re-deploys updating the same project.
  • A plain deploy is private: the returned link is an owner-only preview that only the signed-in owner can open. Do not call it shareable, and do not offer to make it public. Visibility (private, unlisted, public) and publishing are ALWAYS the user's choice, set by them in the FluidDocs app via Publish / Share or Document Properties. Never run --public or --slug, and never offer to, you do not change visibility. For visibility wording and what FluidDocs offers, see deck-builder/references/about-fluiddocs.md.
  • The user asking to "deploy/publish" is the authorization; don't deploy a file they didn't ask for.

Maintained by FluidDocs. Source: https://github.com/FluidForm-ai/fluiddocs-deck-builder. MIT licensed.

Frequently asked questions

What does the Deploy AI skill do?

Deploy / publish a single HTML file (deck, page, doc) to FluidDocs hosting using the self-contained scripts/deploy.sh. Handles browser sign-in / re-auth automatically, then opens the live URL in the browser. Trigger on "deploy", "publish", "ship it", "push it live", "put it online", "host this", or any request to make an HTML file publicly viewable.

Why use Deploy on TypingMind?

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

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

Which AI models can use Deploy?

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 Deploy?

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

Is the Deploy AI skill free?

Yes. It is published on GitHub by FluidForm-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 👇