X Article Writer

Community

timscheuerai

x-article-writer

Write or revise a compact native X Article in the author's voice from their newsletter, framework, posts or lead magnet, with the strongest supported result first and useful graphics placed where they explain the argument. Also writes the X post that announces a video. Use for X Articles and illustrated long posts on X; use x-copywriter or x-planner for ordinary X posts.

Overview

Publisher	timscheuerai
Repository	`linkedin-funnel`
Skill name	`x-article-writer`
Stars	60
Forks	20
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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

Installation

Install the X Article Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/timscheuerai/linkedin-funnel/tree/main/skills/x-article-writer
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.

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/x-article-writer .claude/skills/x-article-writer

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable X Article Writer 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 X Article Writer 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 X Article Writer 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.

X Article writer

Turn the author's material into an article a reader can use. Text and graphics explain the same argument. In a content waterfall the X Article adapts the approved newsletter; it does not invent a new thesis.

Ground the brief

Read identity/positioning.md, identity/proof.md, audience/ideal-follower.md, strategy/pillars.md, strategy/funnel.md and voice/linkedin-voice.md. Then read the actual source: the newsletter, transcript, framework or post the article comes from. Use the voice guide for the author's voice, not LinkedIn's hook length or formatting limits.

Establish a short working brief: the reader's problem, the thesis, the author's own contribution, the evidence, the section order and the graphics. Ask only for information that changes the argument.

For a supplied X URL, read the actual post and any linked Article, including its cover and inline graphics. If access is partial, say what was read. Never infer an article from its preview.

Write the article

Lead with the strongest supported result and the reader's payoff. The title is specific; the introduction states the result, the author's relevant proof and what the reader will be able to build.
Follow the result with the mechanism: the tools, the order of operations, the decisions and the reasons. Keep the author's concrete details and first-person experience.
Make it personal through documented habits, mistakes and decisions, not by swapping "you" for "I".
Keep the author's own names for their frameworks and explain each the first time.
Prefer the shortest complete explanation. A section can be 2 sentences and a graphic. Do not pad to a word count. When the author has hand-edited an earlier version, that edit sets the depth and pace.
State the action or belief directly, then the reason needed to understand it. Use short lists for concrete inputs, stages and routing choices.
Explain a failure through the missing input or decision the author names (for example the context an AI draft lacked), not through a vague "it needs something worth saying".
Keep each section on its named job. Do not restore examples, scripts or side topics the author cut just because they are relevant.
Separate what was demonstrated from what is proposed. Numbers come only from identity/proof.md; keep differing time windows separate.
Use a reference article for craft only: how it sets stakes and lets graphics carry information. Never import its anecdotes, numbers or distinctive lines.
Numerals, no em dashes, no hashtags, no generic AI phrases.
Links to the author's own site carry UTM parameters (source x, campaign = the waterfall's slug). Links to GitHub, YouTube and other sites stay clean.

Graphics

Place each graphic where it explains the next step of the argument. A caption must add information; omit it when the figure explains itself. Pasted editor text such as "Provide a caption (optional)" is interface residue, not copy. Use graphics-designer or flowchart for new figures and keep the editable source. For the X handoff, export a cover and full-resolution inline images numbered in article order, with a short placement guide.

The video post

When the waterfall needs the X post for a new video: 1 short line about the reader's world or the result, 1 or 2 lines on what the video shows, the native video if available, and the full https://www.youtube.com/watch?v=<id> URL. No shortened links.

Deliver

Return the article, the title, the cover and the inline graphics with their positions, plus any unresolved facts. Drafting does not authorize publishing or scheduling. If a scheduler does not support native Articles, hand over the draft and assets for the native X editor and say so.

When asked to learn from a finished piece, compare the author's final hand edit with the preceding draft and record what they added, cut and renamed as reusable rules. Their final choices on length, examples, headings and tone win over earlier drafts. Learning from a piece does not by itself ask for another rewrite or for publication.

Review before returning: does the title promise something useful, does the opening carry the strongest supported result, would the author recognise their reasoning, can a reader scan it and act, and do text, figures and links describe the same system?

Frequently asked questions

What does the X Article Writer AI skill do?

Why use X Article Writer on TypingMind?

Because you install it once and use it with any model. X Article Writer 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 X Article Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/timscheuerai/linkedin-funnel/tree/main/skills/x-article-writer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use X Article Writer?

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 X Article Writer?

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

Is the X Article Writer 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

Solid

openclaw

OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Canvas

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

Diagram Maker

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

Grill With Docs

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

X Article writer

Ground the brief

Write the article

Graphics

The video post

Deliver

Frequently asked questions

Related AI Skills

Set up your own AI workspace now