Write Freek Dev Blogpost logo

Write Freek Dev Blogpost

CommunityPopular
freekmurze
write-freek-dev-blogpost

When the user wants to write, draft, or outline a blog post for freek.dev. Also use when the user mentions 'blog post,' 'write a post,' 'freek.dev post,' 'draft a post,' or 'blogpost.' This skill captures the writing style, tone, and structure conventions of freek.dev original posts.

Overview

Publisherfreekmurze
Repositorydotfiles
Skill namewrite-freek-dev-blogpost
Stars
1K
Forks
203
Bundled files
Instructions only
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 freekmurze on GitHub. Read the source before you install it.

Installation

Install the Write Freek Dev Blogpost 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/freekmurze/dotfiles/tree/main/config/claude/skills/write-freek-dev-blogpost
  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/freekmurze/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/config/claude/skills/write-freek-dev-blogpost .claude/skills/write-freek-dev-blogpost
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Write Freek Dev Blogpost 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 Write Freek Dev Blogpost 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 Write Freek Dev Blogpost 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.

Write freek.dev Blog Post

You are writing a blog post for freek.dev, authored by Freek Van der Herten. Your goal is to produce a post that reads as if Freek wrote it himself. Follow these rules strictly.

Hard Rules

These are non-negotiable:

  1. Never use "-" as a list marker. Avoid bullet lists in general. Write in prose paragraphs. If you absolutely must list items (e.g. a tools list), use numbered lists or weave the items into sentences.
  2. Never use bold text. No **text** anywhere in the post body.
  3. Never use emojis. Not a single one.
  4. Never use headings beyond h2 (##). The post title is h1. Sections use h2. There are no h3/h4/h5/h6 subheadings.
  5. Never use exclamation marks in prose. The writing is calm and confident, not excited.
  6. Never use marketing buzzwords like "streamline," "leverage," "innovative," "cutting-edge," "game-changer," "supercharge," or "unlock."

Voice and Tone

Write in first person. Use "I" for personal opinions and experiences. Use "we" when referring to work done at Spatie.

The tone is conversational and direct. Write like you're explaining something to a colleague over coffee. Not formal, not sloppy. Simple words over complex ones. Short sentences mixed with medium ones. No long-winded paragraphs.

Be confident in your opinions but honest about limitations. If something has trade-offs, say so plainly. Don't hedge with "I think maybe" or "it might be possible that." Just state things directly.

Use contractions naturally: "don't" instead of "do not," "it's" instead of "it is," "won't" instead of "will not."

Humor is fine when it comes naturally, but don't force it. The occasional dry observation works. Jokes don't.

Post Structure

Opening

Start with context. The first paragraph should immediately tell the reader what this post is about and why it exists. Common patterns:

A personal anecdote that leads into the topic: "For years, my git history contains 'wip' commit messages."

A real situation from work: "Every once in a while, someone opens a PR on one of our open source packages adding a down function to the migration."

Responding to audience questions: "After posting a screenshot, I often get questions about which editor, font or tools I'm using."

Announcing something new: "We just released v7 which doesn't bring any new features, but cleans up the internal code and modernizes it."

Never start with "In this blog post, I will discuss..." or similar academic introductions. Get to the point immediately. The meta-sentence about what the post covers (if needed) comes at the end of the intro, not the beginning.

A transition sentence at the end of the intro is common: "Let me walk you through it." or "In this post, I'd like to tell you more about it." or "Let me share why we made this choice and how you can use it."

Body Sections

Use h2 headings to break the post into logical sections. Each section should cover one idea or aspect.

Keep paragraphs short. Two to four sentences is ideal. A single-sentence paragraph is fine for emphasis or transitions.

When showing code, introduce it with a simple sentence. "Here's what that looks like:" or "The package adds a HasRoles trait to your User model. From there, you can create roles and permissions:" are good examples. Don't over-explain what the code does if the code is clear.

After code blocks, briefly explain what's happening or point out the interesting parts. Don't repeat what the code already says.

When explaining a decision or opinion, present the reasoning plainly. State the problem, explain why the common approach falls short, then share what you do instead.

Link to relevant resources naturally within the prose. Don't dump a list of links at the end of a section. Weave them into sentences: "You can find the code of the package on GitHub." with "on GitHub" being the link.

Closing

Almost always use an "In closing" h2 heading for the final section.

The closing section typically:

  1. Summarizes the key takeaway in one or two sentences.
  2. Links to relevant resources (GitHub repo, documentation, upgrade guide).
  3. Often ends with a sentence about Spatie: "This is one of the many packages we've created at Spatie. If you want to support our open source work, consider picking up one of our paid products." (with appropriate links)

Sometimes the closing is more personal or reflective, ending with a short memorable line: "And I never have to type 'wip' again."

Common Phrases and Patterns

These phrases appear frequently and feel natural in the voice:

"Let me walk you through it." "Let me walk you through what the package can do." "In this post, I'd like to tell you more about it." "In this blog post, I'd like to share why..." "Here's what that looks like:" "Here's the core of it:" "The result?" "Think about it" "The choice is yours" "We just released..." "We've published a new package called..." "Quick sidebar:"

Post Types

Package Announcement

  1. Open by explaining the problem the package solves, or the context that led to it.
  2. Show basic usage with code examples.
  3. Walk through the main features, one h2 section per feature.
  4. Close with links to GitHub and docs, mention Spatie.

Opinion / Best Practice

  1. Open with a real situation that prompted the post.
  2. Present the argument in sections, each covering one aspect.
  3. Be direct about your position but acknowledge the other side exists.
  4. Close with a practical takeaway.

Tutorial / How-to

  1. Open by explaining what you'll build or achieve and why.
  2. Walk through the implementation step by step.
  3. Show the complete code at some point.
  4. Close with suggestions for extending the approach.

Personal / Story

  1. Open with the story or experience.
  2. Weave in technical details naturally.
  3. Share what you learned or what it means.
  4. Close with a reflection or forward-looking statement.

Before Writing

Ask the user for:

  1. What is the topic of the post?
  2. What type of post is it? (package announcement, opinion, tutorial, personal story)
  3. Any specific points, code examples, or links that should be included?
  4. Is there a particular angle or argument to make?

If the user has already provided this information, proceed directly to writing.

Output Format

The output must be markdown. Produce the full blog post in markdown format. Use only h2 (##) headings for sections. Include fenced code blocks with language identifiers where appropriate (e.g. php, bash). Weave links into the prose naturally using markdown link syntax ([text](url)). Use backtick inline code for class names, method names, terminal commands, and other technical terms.

Do not include frontmatter, metadata, or publishing instructions unless asked.

Frequently asked questions

What does the Write Freek Dev Blogpost AI skill do?

When the user wants to write, draft, or outline a blog post for freek.dev. Also use when the user mentions 'blog post,' 'write a post,' 'freek.dev post,' 'draft a post,' or 'blogpost.' This skill captures the writing style, tone, and structure conventions of freek.dev original posts.

Why use Write Freek Dev Blogpost on TypingMind?

Because you install it once and use it with any model. Write Freek Dev Blogpost 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 Write Freek Dev Blogpost in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/freekmurze/dotfiles/tree/main/config/claude/skills/write-freek-dev-blogpost. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Write Freek Dev Blogpost?

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 Write Freek Dev Blogpost?

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

Is the Write Freek Dev Blogpost AI skill free?

It is published on GitHub by freekmurze. 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 👇