Longform Publish Folder logo

Longform Publish Folder

Community
kevinbadi
longform-publish-folder

Publish long-form videos to YouTube from a local folder. Drop your edited videos into the watch folder and this skill uploads them with AI-generated titles, descriptions, and tags. Trigger when asked to publish YouTube videos, upload long-form content, or automate YouTube publishing.

Overview

Publisherkevinbadi
Repositoryai-os-skills
Skill namelongform-publish-folder
Stars
73
Forks
29
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by kevinbadi on GitHub. Read the source before you install it.

Installation

Install the Longform Publish Folder 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/kevinbadi/ai-os-skills/tree/main/longform-publish-folder
  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/kevinbadi/ai-os-skills.git /tmp/ai-os-skills
mkdir -p .claude/skills
cp -r /tmp/ai-os-skills/longform-publish-folder .claude/skills/longform-publish-folder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Longform Publish Folder 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 Longform Publish Folder 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 Longform Publish Folder 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.

Longform Publish — Folder Method

Publish your long-form videos to YouTube from a local folder.

Drop your edited videos into ~/Long form videos/. This skill picks them up, uploads to YouTube via Late API, and generates optimized titles, descriptions, and tags via Gemini.

For creators who edit their own YouTube content and want automated publishing.


Watch Folder

Default: ~/Desktop/Long form videos/

The skill scans this folder for video files (.mp4, .mov, .webm) that haven't been published yet. Published videos get a .published.json sidecar file so they're not re-posted.

Folder Structure

~/Long form videos/
  ├── how-to-build-ai-agents.mp4       ← ready to publish
  ├── weekly-vlog-march.mov            ← ready to publish
  ├── old-video.mp4                    ← already published
  ├── old-video.published.json         ← sidecar (marks as published)
  └── thumbnails/                      ← optional: matching thumbnails
      └── how-to-build-ai-agents.jpg   ← auto-matched by filename

Naming Convention

Name files descriptively — Gemini uses the filename for context:

  • how-to-build-ai-agents-2024.mp4 → title about building AI agents
  • day-in-my-life-austin-texas.mov → vlog-style title about Austin

Thumbnails

Put matching thumbnails in a thumbnails/ subfolder with the same base name:

  • Video: my-video.mp4
  • Thumbnail: thumbnails/my-video.jpg (or .png)

Usage

bash
# Publish the next unpublished video
node skills/longform-publish-folder/scripts/longform-publish-folder.js

# Publish a specific file
node skills/longform-publish-folder/scripts/longform-publish-folder.js --file "~/Long form videos/my-video.mp4"

# Preview metadata without publishing
node skills/longform-publish-folder/scripts/longform-publish-folder.js --dry-run

# Custom watch folder
node skills/longform-publish-folder/scripts/longform-publish-folder.js --folder "~/Desktop/youtube"

# Publish ALL unpublished videos (batch mode)
node skills/longform-publish-folder/scripts/longform-publish-folder.js --all --limit 3

# Override video topic for better metadata
node skills/longform-publish-folder/scripts/longform-publish-folder.js --topic "Tutorial on building AI automation systems"

# Schedule for later
node skills/longform-publish-folder/scripts/longform-publish-folder.js --schedule "2026-03-20T14:00:00"

# Set visibility (public/private/unlisted)
node skills/longform-publish-folder/scripts/longform-publish-folder.js --visibility unlisted

Flags

FlagDescription
--file PATHPublish a specific video file
--folder PATHOverride watch folder (default: ~/Long form videos/)
--schedule DATETIMEISO datetime to schedule publish
--topic TEXTOverride topic for metadata generation
--visibilityYouTube visibility: public, private, unlisted (default: public)
--allPublish all unpublished videos in folder
--limit NMax videos to publish in --all mode (default: 3)
--dry-runPreview metadata, skip publishing

Environment Variables

VariableRequiredDescription
LATE_API_KEYYesLate API key for publishing
GEMINI_API_KEYYesGemini API key for metadata generation
INSFORGE_CONNECTION_STRINGNoDatabase for post tracking

Generated Metadata

Gemini generates:

  • Title — Clickable, YouTube-optimized (under 100 chars)
  • Description — Full description with timestamps placeholder, links, hashtags
  • Tags — 10-15 relevant tags for discoverability

Output

After publishing, each video gets a .published.json sidecar:

json
{
  "source_file": "how-to-build-ai-agents.mp4",
  "media_url": "https://cdn.getlate.dev/media/...",
  "late_post_id": "post_abc123",
  "youtube_video_id": "dQw4w9WgXcQ",
  "published_at": "2026-03-13T12:00:00Z",
  "title": "How I Built an AI Agent That Runs My Entire Business",
  "description": "...",
  "tags": ["ai", "automation", "business", ...]
}

Cron Schedule (Recommended)

Check for new videos daily:

0 10 * * * node skills/longform-publish-folder/scripts/longform-publish-folder.js

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 Longform Publish Folder AI skill do?

Publish long-form videos to YouTube from a local folder. Drop your edited videos into the watch folder and this skill uploads them with AI-generated titles, descriptions, and tags. Trigger when asked to publish YouTube videos, upload long-form content, or automate YouTube publishing.

Why use Longform Publish Folder on TypingMind?

Because you install it once and use it with any model. Longform Publish Folder 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 Longform Publish Folder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinbadi/ai-os-skills/tree/main/longform-publish-folder. 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 Longform Publish Folder?

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 Longform Publish Folder?

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

Is the Longform Publish Folder AI skill free?

It is published on GitHub by kevinbadi. Check the repository for licensing terms. 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 👇