Thread Writer logo

Thread Writer

Organization
social-media-skills
thread-writer

Use to write a thread — a connected sequence of posts on X/Twitter or Threads that tells one story or makes one argument across multiple posts. Run when the user says "write a thread," "turn this into a thread," "X thread," "Twitter thread," "thread about X," or has a multi-beat idea that won't fit one post. Reads brand-profile and voice first, uses hook-writer for the opening post (which must hook AND promise the payoff), builds one cohesive idea where every post earns the next, and lands a close with one CTA. Knows when a single post beats a thread. Naming trap: "write a thread" means this multi-post chain; "post on/to Threads" means a single post on Meta's Threads app — use threads-post for that. For a single caption use caption-writer; for just the opening hook use hook-writer.

Overview

Publishersocial-media-skills
Repositoryskills
Skill namethread-writer
Stars
215
Forks
44
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Thread Writer 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/social-media-skills/skills/tree/main/skills/thread-writer
  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/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/thread-writer .claude/skills/thread-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Thread 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 Thread 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 Thread 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.

Thread Writer

A thread is a retention machine in text: a sequence of posts where each one has to earn the next, or the reader drops off. Done well it's one of the best formats for depth, saves, and follower growth on X. Done lazily — a blog chopped into arbitrary chunks — it's worse than a single post.

Three principles run through it:

  1. The opener is the whole game. Post 1 must hook (stop the scroll) and promise the payoff (give a reason to read all the way down). It's also the post that gets reshared, so the thread's reach lives or dies here.
  2. One idea per thread, one idea per post. A thread makes a single cohesive point; each post advances it by exactly one beat. Cramming kills it.
  3. Every post earns the next. Momentum is the metric. A post that doesn't pull the reader forward — or doesn't deserve its place — gets cut.

Step 0 — Read the foundation first

Load brand-profile.md and voice.md. Voice carries across every post; the X/Threads register is usually more conversational (use the voice tone-map). Carry guardrails throughout.

Step 1 — Lock one idea, the payoff, and check it should be a thread

  • One idea — the single point or story. If there are several, pick one or plan separate threads.
  • The payoff — what the reader gets by the end (the lesson, the list, the result).
  • Thread or single post? Thread only if the idea genuinely needs multiple beats. If it fits one post, a single punchy post almost always beats a forced thread. See references/platform-and-when.md.

Step 2 — Write the opener (hook + promise)

Use hook-writer for post 1. It must do two jobs at once: hook with a real mechanism, and promise the payoff ("here's how we did it," "7 lessons," "the story of how it broke"). The opener must also stand alone as a strong post, since it's what gets reshared. No slow wind-up. See references/post-craft.md.

Step 3 — Architect the thread

Pick the structure that fits the idea — listicle, story, argument, how-to, or breakdown — and outline the spine: the opener's promise and the ordered posts that deliver it. The spine is what makes a thread cohesive instead of a chopped article. One idea per post. See references/architecture.md.

Step 4 — Write the body posts

Each post: front-load the point, deliver one beat, stay within the platform's limit, and pull forward to the next (a mini-hook, a numbered step, "but here's the thing"). Cut any post that's filler or throat-clearing. Keep every post in the brand voice. See references/post-craft.md.

Step 5 — Land the close and one CTA

The final post delivers/summarizes the payoff, then makes one ask — matched to the goal and in voice. On X, the native growth move is asking people to reshare the opener ("If this was useful, RT the first post") and/or follow. One CTA only; a link, if any, goes here or in a reply.

Step 6 — Format for the platform

Apply X vs Threads mechanics (limits, numbering, links, hashtags) from references/platform-and-when.md. Number posts where it aids orientation; never split mid-thought awkwardly; use line breaks within posts for readability.

Quality bar — self-check

  • Does the opener hook AND promise, and stand alone as a reshareable post?
  • Is it one idea, with a clear spine — not a chopped article?
  • Does every post earn the next (momentum, no filler)?
  • Does each post front-load the point and respect the platform limit?
  • Does the close land the payoff with exactly one CTA?
  • Is it in the brand voice, at the right register?
  • Should this even be a thread — or is a single post stronger?

If any post doesn't pull the reader forward, cut or rewrite it before delivering.

Edge cases

  • Should be a single post → say so and write the strong single post instead of padding a thread.
  • Multiple ideas → one idea per thread; propose a series.
  • Chopped long-form (a blog "made into a thread" by splitting) → don't. Atomize the idea and rebuild it as a native thread (see cross-platform-repurposing for the source→thread flow).
  • Threads (Meta) vs X → adapt: Threads is more casual, less thread-culture, 500/post; X has strong thread culture and the reshare-opener mechanic. A single conversational Threads post → threads-post.
  • No genuine payoff → if the idea has no real takeaway, it's not a thread; sharpen the idea first.
  • Sensitive/regulated → carry compliance guardrails into every post; no overstated claims.

Related skills

  • brand-profile, voice-builder — voice + register + guardrails.
  • hook-writer — the opener (and re-hooks).
  • caption-writer — single posts/captions; threads-post — a single Meta Threads post (not a chain); cross-platform-repurposing — turn long-form into a thread.
  • scheduling-and-queue — schedule via WoopSocial. Note: WoopSocial publishes single posts only (no native multi-post chain), so schedule the opener and post the chain natively/manually.

References

  • references/architecture.md — thread structures, the spine, one-idea-per-post, length.
  • references/post-craft.md — the opener formula, post-as-unit, transitions, the close + CTA.
  • references/platform-and-when.md — X vs Threads mechanics, and when NOT to thread.
  • references/examples.md — full worked threads (listicle and story), on-voice.

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 Thread Writer AI skill do?

Use to write a thread — a connected sequence of posts on X/Twitter or Threads that tells one story or makes one argument across multiple posts. Run when the user says "write a thread," "turn this into a thread," "X thread," "Twitter thread," "thread about X," or has a multi-beat idea that won't fit one post. Reads brand-profile and voice first, uses hook-writer for the opening post (which must hook AND promise the payoff), builds one cohesive idea where every post earns the next, and lands a close with one CTA. Knows when a single post beats a thread. Naming trap: "write a thread" means thi...

Why use Thread Writer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/thread-writer. 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 Thread 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 Thread Writer?

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

Is the Thread Writer AI skill free?

Yes. It is published on GitHub by social-media-skills 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 👇