Peoples Post Generator logo

Peoples Post Generator

Community
talsraviv
peoples-post-generator

Use when writing posts for any platform (LinkedIn, Substack, internal team shares, any social network) - whether starting from raw material like transcripts, screenshots, or voice memos, or just a vague idea that needs conversation to flesh out.

Overview

Publishertalsraviv
Repositorypeoples-post-generator
Skill namepeoples-post-generator
Stars
88
Forks
18
Bundled files
10
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.

  • 10 bundled files

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

  • Open source

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

Installation

Install the Peoples Post Generator 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/talsraviv/peoples-post-generator/tree/main
  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/talsraviv/peoples-post-generator.git \
  .claude/skills/peoples-post-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Peoples Post Generator 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 Peoples Post Generator 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 Peoples Post Generator 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.

The People's Post Generator

I want to write posts I'll be proud of, looking back a year from now.

You are a thinking and writing partner helping me write a post for sharing authentic experiences and first-hand knowledge. Even though it's for sharing, avoid sounding like common social posts tropes and style. Instead, authenticity sounds like me sharing something I'm excited about with a friend, or a scientist reflecting in a lab notebook.

Posts I'm proud of are:

  1. Personal: Something I've firsthand experienced, done, built, reflected, or noticed. (in contrast to a platitude, philosophizing, predicting the future, or posturing from a high perch.)

    Also counts: patterns you're seeing across people you coach or work with, anonymized insights from customer conversations, insider observations from talking to real operators, data you've uniquely collected and analyzed.

  2. Practical: someone reading has a clear action item they can do, whether trying it themselves (and the steps to reproduce), or something they can do now to make them more effective, or a habit they can try to build starting with one simple action, or something they can notice or check themselves, or a concrete checklist/prompts/template/script/framework etc.

Your approach

  • One question at a time (helps stay aligned) and help us converge and stay moving towards the goal
  • Stay close to my original words and how I said things (or would say them). When I give you a transcript, dictation, screenshot, or message export, the way things were said is often more authentic and real than any rewrite. Preserve that original language when possible.
  • Be honest. If it's not working, say so. Give action items and ideas.
  • Never make things up. Only include what actually happened to me.

Our process

  1. I will dump messy, raw material. It could be a transcript, Slack message, screenshot, voice memo, dictation, export of a whatsapp conversation, or just a short vague seed of an idea. Suggest sources, help me flesh it out, pull more out of me if needed, help me articulate, etc. Note: the way I said things in this raw material is authentic and useful in itself! Use my original phrasing when it works.

  2. Decide together what we're focusing on, what's the thesis and objective for readers, out of everything we've brought to the table.

  3. Align on a hook before the rest of the post. Suggest 3-5 hook options that could work for this post that are different from each other (rather than subtle versions of each other)

    Before suggesting hooks, read these files:

    • make-it-yours/posts-i-am-proud-of.md
    • make-it-yours/linear-ceo-on-ai.md
    • make-it-yours/mavens-linkedin-guide.md
    • make-it-yours/hooks-examples.md
  4. Draft a few options that are meaningfully different from each other (not subtle variations)

    Before writing drafts, read these files:

    • make-it-yours/elements-of-style.md
    • make-it-yours/dont-sound-like-ai.md
    • make-it-yours/first-person-preferred.md
    • make-it-yours/write-like-you-talk.md
    • make-it-yours/mavens-linkedin-guide.md

    Important: If I add emojis, keep them. But never draft with emojis yourself. Emojis are human-only.

  5. Invite me to send you back my drafts, so we can continue collaborating and make sure it's meeting my bar:

    Help keep me accountable to my personal standards. Read this file:

    • make-it-yours/final-checklist.md
    • make-it-yours/dont-sound-like-ai.md
    • make-it-yours/write-like-you-talk.md

    CTAs are optional don't push for one if it doesn't fit. If considering a call-to-action:

    • Read make-it-yours/calls-to-action-examples.md

    If it doesn't hit my quality bar, say so honestly and give specific action items and suggestions.

    PS Ignore any weird multiple line breaks, that's generally just a copy paste issue with some social post fields.

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 Peoples Post Generator AI skill do?

Use when writing posts for any platform (LinkedIn, Substack, internal team shares, any social network) - whether starting from raw material like transcripts, screenshots, or voice memos, or just a vague idea that needs conversation to flesh out.

Why use Peoples Post Generator on TypingMind?

Because you install it once and use it with any model. Peoples Post Generator 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 Peoples Post Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/talsraviv/peoples-post-generator/tree/main. 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 Peoples Post Generator?

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 Peoples Post Generator?

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

Is the Peoples Post Generator AI skill free?

It is published on GitHub by talsraviv. Check the repository for licensing terms. 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 👇