Social Posts logo

Social Posts

Community
j1ngg
social-posts

Generates social media posts from source content. Produces brand or personal posts for LinkedIn or Twitter, tailored to each channel's audience and format.

Overview

Publisherj1ngg
Repositorytech-marketing-framework
Skill namesocial-posts
Stars
59
Forks
8
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by j1ngg on GitHub. Read the source before you install it.

Installation

Install the Social Posts 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/j1ngg/tech-marketing-framework/tree/main/.claude/skills/social-posts
  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/j1ngg/tech-marketing-framework.git /tmp/tech-marketing-framework
mkdir -p .claude/skills
cp -r /tmp/tech-marketing-framework/.claude/skills/social-posts .claude/skills/social-posts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Social Posts 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 Social Posts 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 Social Posts 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.

Social Media Post Generator

This skill transforms source content (blog posts, announcements, product launches) into social media posts.

Step 1: Channel Selection

Before generating any content, ask the user:

Platform:

  • LinkedIn
  • Twitter/X
  • Both

Account type:

  • Brand (company voice)
  • Personal (individual voice)
  • Both

Wait for the user to answer before proceeding. Do not assume.


Step 2: Gather Inputs

Once channel is selected, ask the user for the source content:

How would you like to provide the source content?

  • File path (e.g., /docs/announcements/feature-launch.md)
  • URL to fetch
  • Paste directly

Wait for the user to provide the source before proceeding.

Then confirm you have the remaining required inputs:

  1. Author context (for personal posts): Who is posting? Do they have personal involvement or affiliation to disclose?
  2. Brand/company name (for brand posts): For attribution
  3. Key link: The URL to include in the post

If any required inputs are missing, ask before generating.


Step 3: Generate Posts

Generate only the posts requested. Follow the rules for the selected channel(s) below.


Channel Rules

LinkedIn

LinkedIn reaches VPs, Heads of Engineering, CTOs. Budget holders, not builders. They care about business outcomes, risk, and strategic implications.

Brand LinkedIn:

  • Lead with the problem or market insight, not the product
  • Focus on business impact and governance implications
  • Use concrete numbers (time saved, cost reduced, risk mitigated)
  • Structure: Problem → Impact → Solution exists → CTA
  • Never put a direct link in the post body. End with "Full story in comments." or "Link in comments." and instruct the user to drop the URL as the first comment after publishing.
  • Length: 150 to 250 words
  • No hashtags in body (optional 2 to 3 at end if company standard)
  • No emojis
  • No subject line or greeting

Personal LinkedIn:

  • Lead with personal experience ("I built", "I learned", "I discovered")
  • Include the narrative arc: problem, action, insight
  • Surface personal voice throughout
  • Disclose affiliations explicitly when discussing your own product ("Full disclosure: I helped build X")
  • First person throughout
  • Structure: Personal hook → Story → Insight → Disclosure (if applicable) → CTA
  • Never put a direct link in the post body. End with "Full story in comments." or "Link in comments." and instruct the user to drop the URL as the first comment after publishing.
  • Length: 200 to 350 words
  • No hashtags
  • No emojis

Twitter/X

Twitter reaches engineers, builders, founders. They want technical depth, concrete details, and practitioner credibility.

Brand Twitter:

  • Lead with the most surprising or concrete fact
  • Thread format (4 to 6 posts) for substantial content; single post for simple announcements
  • Post 1: Hook with sharpest insight or number
  • Posts 2 to N: One idea per post, build the argument
  • Final post: Link with minimal framing
  • Each post: Under 280 characters
  • Use line breaks for lists within posts
  • One emoji max per thread, only if it adds signal

Personal Twitter:

  • Lead with "I built" / "I learned" / "Here is what happened when"
  • Thread format for substantial content
  • Include technical details that demonstrate practitioner credibility
  • Share what went wrong or what surprised you
  • Disclose affiliations when relevant
  • Each post: Under 280 characters
  • Structure: Personal hook → Technical details → Insight → Link

Audience Assumptions

  • Assume expert audience. Use acronyms without spelling them out (MFA, FIDO, NHI, EDR, SIEM, CSPM).
  • Vary openers across posts. If generating multiple posts, do not start them the same way.

Content Transformation Rules

What to extract from source

ElementUse in social
Concrete numbersLead with these. "30 seconds" beats "faster."
Personal narrativePersonal posts only. Preserve "I" voice.
Technical architectureTwitter threads. Break into discrete facts.
Business implicationsLinkedIn. Frame as risk, cost, or strategic value.
Surprising insightsHooks for all channels.
Affiliation/disclosurePersonal posts. Explicit "Full disclosure" statement.

What to cut

  • Background context (social readers skim)
  • Hedging language ("we believe", "it is possible that")
  • Section headers (flatten into narrative)
  • Long code blocks (summarize or reference)
  • Repetition

Formatting Rules (All Channels)

  • No dashes. Rewrite sentences that require them.
  • No passive voice.
  • No buzzwords (robust, seamless, transformative, game-changer, revolutionary, cutting-edge, leverage).
  • No soft intros ("In today's world", "As we all know").
  • No dramatic openings ("Passwords are dead", "Everything is broken").
  • No fear-mongering ("catastrophic", "wide open").
  • No formulaic structures ("It wasn't just X, it was Y").
  • No rhetorical questions at the end.
  • No transition word chains (moreover, furthermore, additionally).
  • Specific beats vague. "30 seconds" not "much faster."

Output Format

For LinkedIn (single post)

## [Brand/Personal] LinkedIn

[Post content]

---
Character count: [X]

For Twitter (thread)

## [Brand/Personal] Twitter/X

**Post 1 of N**
[Content]
[Character count: X]

**Post 2 of N**
[Content]
[Character count: X]

...

Review Checklist (Self-Check Before Delivery)

Before delivering, verify:

  • No dashes
  • No passive voice
  • No banned words or phrases
  • No rhetorical questions at end
  • LinkedIn: 150+ words (brand) or 200+ words (personal)
  • Twitter: Each post under 280 characters
  • Personal posts use first person
  • Affiliations disclosed (if applicable)
  • Concrete numbers in hooks where available
  • Exactly one link placement per post/thread (Twitter: in final post; LinkedIn: "Link in comments" CTA, never a direct URL in the post body)

LinkedIn Carousel Prompt

After generating any LinkedIn post (brand or personal), ask the user:

"Want me to generate a LinkedIn carousel to go with this post?"

If yes, invoke the /image skill targeting LinkedIn carousel format. If docs/inputs-local/carousel_style_ceros.md exists, use it as the style reference. Otherwise fall back to docs/inputs/brand_guidelines.md.


Adaptation Notes

  • If source has no personal narrative and user requests personal posts, flag that author input is needed
  • If source has no concrete numbers, flag as a gap
  • If author has no affiliation to disclose, omit disclosure
  • For shallow source content, use single post instead of weak thread

Frequently asked questions

What does the Social Posts AI skill do?

Generates social media posts from source content. Produces brand or personal posts for LinkedIn or Twitter, tailored to each channel's audience and format.

Why use Social Posts on TypingMind?

Because you install it once and use it with any model. Social Posts 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 Social Posts in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/j1ngg/tech-marketing-framework/tree/main/.claude/skills/social-posts. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Social Posts?

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 Social Posts?

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

Is the Social Posts AI skill free?

Yes. It is published on GitHub by j1ngg 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 👇