Intro logo

Intro

Community
Illyism
intro

Write short, Semrush-style blog post intros with journey teasers, practical relevance, and reader intent matching. Use when the user asks for /intro, a blog intro, opening paragraph, article lead, listicle intro, or hook copy for a post.

Overview

PublisherIllyism
Repositoryseo-skills
Skill nameintro
Stars
584
Forks
60
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Intro 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/Illyism/seo-skills/tree/main/content/intro
  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/Illyism/seo-skills.git /tmp/seo-skills
mkdir -p .claude/skills
cp -r /tmp/seo-skills/content/intro .claude/skills/intro
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Intro 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 Intro 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 Intro 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.

Blog Intro Writer

Write engaging blog intros in the style of high-performing SEO listicles and guides (examples.md).

Contents

When this applies

The user invoked /intro, or asked for a blog intro, opening paragraph, or lead copy for a post.

Works on its own or after title work (see the seo-title-optimization skill). If the slug or title is missing, ask briefly or propose one.

First step

Say: "Tell me a bit about your content and I'll write an intro for it."

Gather enough to match intent:

  • Topic, primary keyword, and search intent (informational, listicle, how-to, comparison)
  • Target reader and their goal
  • Article shape: listicle count, H2/H3 outline, or key sections
  • Product angle, if the post promotes one
  • Optional: chosen title, slug, featured image subject

If the user already pasted an outline or draft, use it. Do not invent stats, market share, or legal claims unless they provided them.

Commitments

I will:

  • Use simple, concise English
  • Return an image alt text
  • Give a slug and a title
  • Use lists where they help scanning
  • Match the reader's intent to the content
  • Introduce the topic and why it matters
  • Tell readers what they will learn
  • Journey teaser: a roadmap of the key steps or sections ahead
  • Explain why: the practical importance of the topic
  • Relevance: how the topic relates to the reader's goal
  • Use short sentences and keep it short

Intro patterns

Pick the pattern that fits the article type.

Listicle (e.g. "21 Best Search Engines")

Reference: listicle example

  1. One sentence: what the thing is.
  2. One sentence: why the default option is not enough, or why the list matters.
  3. Journey teaser: what the list covers and how it is organized (grouped by type, in no particular order).
  4. Optional jump line: Or jump straight to our [FAQs](#anchor).

How-to / guide (e.g. reverse image search)

Reference: how-to example

  1. Lead with the task or problem in plain language.
  2. Explain why in one or two short sentences.
  3. Optional bullet list of outcomes (3–5 items) when it clarifies value.
  4. Journey teaser: what platforms or steps the article covers.
  5. Close with what they will learn by the end (one short sentence).

Definition-first (e.g. "What Is SEO?")

Reference: definition example

  1. Open with the term and a tight definition (expand acronyms on first use).
  2. One sentence on the user need and outcome (visibility, traffic, accuracy).
  3. Optional short bullet list of what the practice involves.
  4. Journey teaser: the main sections ahead.

Debate / evidence piece

Reference: debate example

  1. Frame two extremes the reader has heard.
  2. Position the article as the level-headed referee and name the method.
  3. Promise a concrete payoff.
  4. List the questions the article answers, in the order the H2s answer them.

Writing rules

  • Short sentences. Prefer 8–15 words. Break long lines into two sentences.
  • Keep it short. 2–4 short paragraphs or 80–120 words unless the user asks for more.
  • Listicles: mirror the count in the title (three proven ways, five common mistakes).
  • Voice: direct, practical, confident. No hype words.
  • Emphasis (sparingly): bold 2–4 hook words per intro (primary keyword, pain point, or outcome). Use italic for one short aside or contrast. Never both on the same phrase.
  • No H2 in the intro unless the outline starts with a definition block (What Is X?) right after the intro.
  • The intro is the first prose block after frontmatter, not the meta description or excerpt.

Slug, title, and image alt

  • Slug and title: use the ones the user has. If not, propose one slug and one title that fit the intro.
  • Image alt: describe the featured image for accessibility: subject plus context (mock UI, diagram, before/after). One sentence, under 125 characters when possible.

Default output

Unless the user asks for full, slug, title, or alt, return only the intro: the markdown body paragraphs, ready to paste under frontmatter.

Full output format

Use when the user asks for full or everything in one pass. Reference: full output example.

markdown
**Slug:** `[slug]`

**Title:** [title]

**Image alt:** [one sentence, under 125 characters when possible]

**Intro:**

[1–2 sentences: definition or what the thing is]

[Optional: "That means…" + 2–4 short bullets: outcomes or jobs to be done]

[1–2 sentences: **explain why**, the practical stakes; use stats only if the user provided them]

**In this guide, you'll learn:**

- [Section or outcome 1](#heading-anchor)
- [Section or outcome 2](#another-anchor)
- [Section or outcome 3](#another-anchor)
- [Section or outcome 4](#another-anchor)

[One short closing line. Vary it; do not default to "Let's dive in."]

Closing lines (pick one that fits; avoid repeating across a batch):

  • Here's how it works.
  • Below is the full walkthrough.
  • We'll break down each approach below.
  • Here's what to know before you build.
  • Use the sections below as your playbook.
  • Read on for the step-by-step workflow.
  • Here's how each platform compares.
  • The rest of this guide covers it in order.

Rules for full output:

  • Label fields with Slug, Title, Image alt, Intro so they are easy to copy.
  • Use the heading In this guide, you'll learn: (or a close variant the user prefers).
  • Link each journey bullet to the matching H2 anchor on the same post when the heading slugs are known. Anchors must match the live post.

Quality check

Before returning, confirm:

  • Reader intent matches the listicle, how-to, definition, or debate pattern
  • Why the topic matters (practical, not abstract)
  • Relevance to the reader's goal is clear
  • Journey teaser names sections or outcomes
  • Journey bullets link to real anchors in full output for existing posts
  • 2–4 bold hooks and at most one italic aside
  • Sentences are short; total length is tight
  • No fabricated data or competitor claims

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 Intro AI skill do?

Write short, Semrush-style blog post intros with journey teasers, practical relevance, and reader intent matching. Use when the user asks for /intro, a blog intro, opening paragraph, article lead, listicle intro, or hook copy for a post.

Why use Intro on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Illyism/seo-skills/tree/main/content/intro. 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 Intro?

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 Intro?

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

Is the Intro AI skill free?

It is published on GitHub by Illyism. 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 👇