Tweet Thread From Blog logo

Tweet Thread From Blog

Organization
Varnan-Tech
tweet-thread-from-blog

Converts a blog post URL or article into a Twitter/X thread with a strong hook, one insight per tweet, and a CTA. Optionally posts the full thread to X via Composio using a reply chain. Use when asked to turn a blog post into a tweet thread, repurpose an article for Twitter, create a thread from a blog, write a Twitter thread about a topic, or share a blog post as a thread. Trigger when a user mentions Twitter thread, X thread, tweet thread, or wants to repurpose blog content for X/Twitter.

Overview

PublisherVarnan-Tech
Repositoryopendirectory
Skill nametweet-thread-from-blog
Stars
674
Forks
74
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by Varnan-Tech on GitHub. Read the source before you install it.

Installation

Install the Tweet Thread From Blog 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/Varnan-Tech/opendirectory/tree/main/skills/tweet-thread-from-blog
  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/Varnan-Tech/opendirectory.git /tmp/opendirectory
mkdir -p .claude/skills
cp -r /tmp/opendirectory/skills/tweet-thread-from-blog .claude/skills/tweet-thread-from-blog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tweet Thread From Blog 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 Tweet Thread From Blog 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 Tweet Thread From Blog 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.

Tweet Thread from Blog

Convert a blog post or article into a 7-10 tweet thread. One insight per tweet. Strong hook. CTA in the final tweet. Optionally post the thread directly to X via Composio.

Writing Style

Apply these rules to every tweet you write:

  • Active voice only
  • Conversational, like a person typed it on their phone
  • Contractions required: don't, it's, won't, can't, I've
  • Short sentences, one idea per tweet
  • No em dashes — use a period or comma instead
  • No semicolons
  • No markdown or asterisks
  • No hashtags anywhere in the thread

Banned words — do not use any of these: incredible, amazing, leveraging, synergize, game-changing, game changer, let's dive in, buckle up, it's worth noting, delve, harness, unlock, groundbreaking, cutting-edge, remarkable, paradigm, revolutionize, disruptive, transformative, thrilled, excited to share, powerful, innovative, comprehensive, actionable, crucial, vital, pivotal, elucidate, utilize, can, may, just, that, very, really, literally, actually, certainly, probably, basically, could, maybe

If a draft tweet contains any banned word, rewrite it before presenting.

CRITICAL RULE

Do not invent specifics. Every claim, stat, and example in the thread must come from the blog post. Never fabricate data, quotes, or outcomes.


Step 1: Check Setup

Confirm input is present. The user must provide one of:

  • A blog post URL
  • Pasted article text

If no input is present, ask: "What blog post or article should I turn into a thread? Share a URL or paste the content."

COMPOSIO_API_KEY is only needed for direct posting to X. Output-only mode works without it.


Step 2: Fetch and Extract Content

If input is a URL: Use WebFetch or Chrome DevTools MCP to fetch the page. Extract:

  • Title
  • Author name
  • Publish date
  • All body text
  • Key statistics and data points
  • Numbered lists or steps
  • Subheadings
  • Any quotes

If input is pasted text: Read it directly.

After fetching, identify:

  • The single most surprising or counterintuitive insight
  • 6-9 supporting insights, data points, or steps
  • Any specific numbers, percentages, or concrete results
  • The core argument or main takeaway

QA checkpoint: State the core thesis and list the top insights you will use. Confirm every insight comes directly from the source. Do not proceed if you cannot verify a claim.


Step 3: Choose Thread Style

Four styles. Auto-detect from content signals. Respect explicit user override.

StyleWhen to UseSignals
Data/InsightEvidence-based article with stats or research findingsNumbers, percentages, study results, data points
How-ToTutorial, guide, or step-by-step articleNumbered lists, step headers, "how to" in title
Story/JourneyPersonal experience, build log, lessons learnedFirst-person narrative, "I learned", "we built"
Hot TakeOpinion piece, contrarian argument"Why X is wrong", "Stop doing X", counterintuitive claim

Decision logic:

  • Article has specific stats or data: Data/Insight
  • Article is structured as steps or tips: How-To
  • Article is first-person narrative: Story/Journey
  • Article argues against a common belief: Hot Take

State the chosen style and reason. If ambiguous, pick one and note it.


Step 4: Read Format Rules

Read references/thread-format.md in full before writing any tweet. Internalize:

  • Hook tweet rules (tweet 1 must stop the scroll)
  • One-insight-per-tweet rule
  • Character limit (280 per tweet, count carefully)
  • Thread numbering format (1/8, 2/8, etc.)
  • CTA tweet rules (final tweet only)
  • No hashtags
  • No em dashes
  • Banned word list

Read references/output-template.md and select the template matching the chosen style.


Step 5: Generate the Thread

Produce three things:

(A) The full thread (7-10 tweets)

Each tweet:

  • Under 280 characters including the tweet number ("1/8 " = 4 characters)
  • Contains exactly one insight, step, or idea
  • Sounds like a human typed it
  • No URLs in tweets 1 through N-1
  • No hashtags

(B) The CTA tweet (final tweet)

  • Summarizes the key takeaway in one sentence
  • Ends with one action: "Read the full post in the replies." or "What's your take?" or "Follow for more like this."
  • Includes the source URL if one was provided

(C) One alternative hook tweet

  • Uses a different format from the primary hook
  • If primary used a stat, offer a question-based hook
  • If primary used a bold claim, offer a before/after hook

Step 6: Self-QA

Run every check before presenting. Fix violations first.

  • Tweet 1 creates a curiosity gap or leads with the most surprising insight
  • Every tweet is under 280 characters (count including tweet number)
  • Each tweet contains exactly one idea
  • No tweet starts with "I" (exception: Story/Journey style)
  • No banned words in any tweet
  • No em dashes in any tweet
  • No hashtags in any tweet
  • No URLs except in the final CTA tweet
  • No invented data. Every stat and example traces to the source.
  • Thread reads naturally in sequence
  • Total tweet count is between 7 and 10

State total tweet count and confirm every tweet is under 280 characters before presenting.


Step 7: Post via Composio or Output

Check for COMPOSIO_API_KEY.

If set: "Thread ready. Confirm to post to X via Composio, or say 'output only' to get the text."

On confirmation:

  1. Post tweet 1 using action TWITTER_CREATION_OF_A_POST with text set to tweet 1 content
  2. Capture the returned tweet ID
  3. Post tweet 2 with reply_in_reply_to_tweet_id = tweet 1 ID, capture its ID
  4. Continue for each tweet in sequence, each replying to the previous tweet's ID
  5. Wait 1 second between posts to avoid rate limiting
  6. After all tweets post: "Thread posted. Tweets 1-N are live."

If not set: Present each tweet in a numbered list inside a code block. Add:

"To enable direct posting, add COMPOSIO_API_KEY to your .env file. See README.md for Composio setup."

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 Tweet Thread From Blog AI skill do?

Converts a blog post URL or article into a Twitter/X thread with a strong hook, one insight per tweet, and a CTA. Optionally posts the full thread to X via Composio using a reply chain. Use when asked to turn a blog post into a tweet thread, repurpose an article for Twitter, create a thread from a blog, write a Twitter thread about a topic, or share a blog post as a thread. Trigger when a user mentions Twitter thread, X thread, tweet thread, or wants to repurpose blog content for X/Twitter.

Why use Tweet Thread From Blog on TypingMind?

Because you install it once and use it with any model. Tweet Thread From Blog 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 Tweet Thread From Blog in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Varnan-Tech/opendirectory/tree/main/skills/tweet-thread-from-blog. 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 Tweet Thread From Blog?

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 Tweet Thread From Blog?

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

Is the Tweet Thread From Blog AI skill free?

Yes. It is published on GitHub by Varnan-Tech 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 👇