Linkedin Article Adapter logo

Linkedin Article Adapter

Community
timscheuerai
linkedin-article-adapter

Adapt a finished X Article into a native LinkedIn article while preserving its text and inline figures, recompose the cover at LinkedIn's article ratio, and prepare a numbered upload folder plus a short post to share it. Use after x-article-writer when the author wants the same article on LinkedIn.

Overview

Publishertimscheuerai
Repositorylinkedin-funnel
Skill namelinkedin-article-adapter
Stars
60
Forks
20
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Linkedin Article Adapter 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/timscheuerai/linkedin-funnel/tree/main/skills/linkedin-article-adapter
  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/timscheuerai/linkedin-funnel.git /tmp/linkedin-funnel
mkdir -p .claude/skills
cp -r /tmp/linkedin-funnel/skills/linkedin-article-adapter .claude/skills/linkedin-article-adapter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkedin Article Adapter 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 Linkedin Article Adapter 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 Linkedin Article Adapter 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.

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ resolve from this skill directory.

LinkedIn article adapter

Turn a finished X Article into a reviewable LinkedIn article handoff. Read the final X Article and its latest image pack, editable sources, figure map and proof notes before changing anything. The latest hand-edited text is the source; do not reconstruct it from an older brief or preview.

Adapt the article

Keep the title, argument, section order, examples, links, figures and the author's voice substantially intact. The one link change: links to the author's own site switch their UTM source from x to linkedin and keep the campaign slug, so LinkedIn readers are not counted as X. Make only platform-specific edits that improve reading in the LinkedIn article editor: clean up X-only references, adjust an opening or call to action that depends on X, and correct obvious formatting. Do not turn the article into a feed post, add a new hook, inflate its length or update claims without a source. Keep numbers, time windows, qualifiers and the distinction between observed and proposed work exactly scoped, checked against identity/proof.md. If the article is already about LinkedIn, minimal text edits are expected.

Preserve the intended figure insertion points and captions. Reuse approved full-resolution inline exports when they are still accurate. If a figure needs a platform fit change, adapt its editable source and inspect the new export; do not stretch a raster or silently replace a detailed diagram with generic cards. Use graphics-designer for artwork and flowchart when editing a process map. Follow brand/BRAND.md and the approved design of the article. Keep visual changes scoped to this article.

Recompose the article cover

Make a LinkedIn article cover, not a profile background banner. Check LinkedIn's current article-cover guidance at execution time; it has recommended 1920 x 1080 at 16:9, and the profile-banner size does not apply. Recompose the X cover (5:2) from its editable source at the article ratio. Preserve the recognizable result, hierarchy, typography, palette and real system imagery, while giving the taller canvas intentional spacing. Keep key text clear of likely crop edges and inspect at native size and at a narrow feed-preview width. Keep an editable source and export an upload-ready PNG or JPEG within LinkedIn's current size and format limits. Never merely resize a 5:2 bitmap into 16:9.

A cover layout that works for a results-led article: the result headline on the left, 1 or 2 supporting proof numbers together in a card at the upper right, and the real workflow diagram across the full width below. Keep each number's qualifier (time window, unit) attached to that number only. Treat this as one option, not a template for every cover.

Prepare the upload folder

Create 1 clearly named folder in output/ (or where the author asks) for this article. Put only the files needed for manual drag and drop at its top level:

  • 00-cover.png for LinkedIn's cover field.
  • 01-...png, 02-...png, and so on for every inline figure in article order, using the best inspected full-resolution exports.
  • ARTICLE.md with the complete adapted title and body. Reference the local image filenames at the exact insertion points; keep captions and working links.
  • START-HERE.txt with the source article link, the cover instruction, the ordered image placement and any material text changes. This is a short upload guide, not a second manuscript.

Use a new folder or replace only a clearly matching earlier handoff after checking its contents. Do not move or delete the X source assets. Keep editable artwork with its source and link it from the guide. Check file dimensions, type, readability, image order, local links and the complete article text. The folder should be usable without extracting a ZIP.

If the source article is in Notion, read its complete page and image order, then write the local handoff from that final version. Do not rely on expiring signed Notion image URLs when local exports exist. Keep the X draft intact. Save a LinkedIn draft on the content board only when the author asks, using strategy/notion-schema.md, platform LinkedIn, draft state and a full readback. Creating files does not authorize publishing or scheduling.

Description and share post

When the handoff also needs an article description or a post to share it with the network, write a short description and a separate paste-ready post with linkedin-copywriter in the author's LinkedIn voice. The post gives a reason to open the article without repeating its full instructions. Keep public metrics scoped by identity/proof.md. See the worked example for the shape. Include both in the upload folder for convenient pasting.

Finish with the folder path, the adapted article and editable cover, their dimensions, and any remaining editor step. The author should be able to open the folder and drag the files into a native LinkedIn article in order.

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 Linkedin Article Adapter AI skill do?

Adapt a finished X Article into a native LinkedIn article while preserving its text and inline figures, recompose the cover at LinkedIn's article ratio, and prepare a numbered upload folder plus a short post to share it. Use after x-article-writer when the author wants the same article on LinkedIn.

Why use Linkedin Article Adapter on TypingMind?

Because you install it once and use it with any model. Linkedin Article Adapter 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 Linkedin Article Adapter in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/timscheuerai/linkedin-funnel/tree/main/skills/linkedin-article-adapter. 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 Linkedin Article Adapter?

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 Linkedin Article Adapter?

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

Is the Linkedin Article Adapter AI skill free?

Yes. It is published on GitHub by timscheuerai 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 👇