PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
An AI copywriter that uses real copywriting skills + real marketing knowledge with human tone.
作者の方は、このコードを README に貼れます。バッジはこのページにリンクします。
[](https://mcp.popnx.com/en/skills/mikiarlo3-ai-copywriter)同じ作業で AI をサービスにつなぐ MCP
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Google Ads, Meta Ads, Google Analytics (GA4) & Search Console MCP server by Ryze AI
同じ種類の作業。Skill 一覧と同じ並び
| これ ai-copywriter | scroll-world | social-auto-upload | native-subtitle-quote-image | xiaohongshu-ops-skill | |
|---|---|---|---|---|---|
| 作者 | mikiarlo3 | oso95 | dreammis | chengyi-ai | Xiangyu-CAS |
| Skill 数 | 1 | 1 | 4 | 1 | 1 |
| GitHub スター | 1,217 | 11,065 | 16,698 | 2,891 | 2,592 |
| 最終コード更新 | 2026年8月1日 | 2026年7月29日 | 2026年10月23日 | 2026年11月6日 | 2026年3月19日 |
| ライセンス | MIT | MIT | MIT | MIT | – |
mikiarlo3 による 1 個の Skill(指示セット)。AI が読んでそのとおりに作業します · MCP server ではありません
MCP = 手
AI を外部のサービスやデータにつなぎます(例:Notion を読む、請求書を作る)。プログラムやサーバーが動いている必要があります。
Skill = 手順書
作業のやり方を AI に教えるテキストファイル。どのサービスにもつながりません。
重なる部分もあります。ツールを呼ぶスクリプト付きの Skill や、知識だけを渡す MCP もあります。やりたい作業から選んでください。
Claude CodeClaude (เว็บ/แอป)
提供元の README と repo のフォルダから判断
GitHub account mikiarlo3 (person), 14 years old
★ 1,217 stars · code last changed 2026年8月1日
1 scripts that can run on a computer: scripts/validate-package.py
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 08b53b1 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
まず:どの AI を使っていますか
使っているアプリを選ぶと、そのアプリでのインストール方法だけが表示されます
Uploading to claude.ai would fail: the description is over 200 characters (957). Use "Let the AI install it" instead
この文をコピーして Claude Code のチャットに貼り付けます
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Claude Code を開き直し、/ai-copywriter と入力するか関連する作業を頼むと Claude が自動で使います
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill は AI が従う指示です。入れる前にファイルを読み、信頼できる提供元のものだけを入れてください。
もう入っていますか?先に確認 · ターミナルを開き、このコマンドを入力して Enter
node -vMac:⌘ + Space を押し、Terminal と入力して Enter
Windows:スタートメニューを開き、Windows PowerShell と入力して「開く」
まだ入っていない場合: 公式ダウンロードページで LTS 版と、クリックで進むインストーラーを選びます:Mac は .pkg、Windows は .msi。ダブルクリックして最後まで進めるだけで、curl コマンドは不要です
入れ終わったらターミナルを閉じて開き直し、同じコマンドをもう一度実行します。バージョン番号が出れば完了です: node -v
一度入れれば、Node.js を使うすべてのツールで使えます
npx skills add mikiarlo3/ai-copywriter --global提供元の README から引用。提供元のコードをダウンロードして実行します
Mac:Command+スペースで Terminal と入力 · Windows:下のコマンドは PowerShell では動きません。上の「AI にインストールしてもらう」を使ってください
repo を一時フォルダにダウンロードし、SKILL.md のあるフォルダだけをコピーします
git clone --depth 1 https://github.com/mikiarlo3/ai-copywriter.git /tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1/.' ~/.claude/skills/ai-copywriterChatGPT デスクトップアプリには Codex が組み込まれていて、Codex は ~/.agents/skills フォルダから Skill を読み込みます
ChatGPT デスクトップアプリで Codex を開き、この文をチャットに貼り付けます
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
ai-copywriter フォルダを ~/.agents/skills/ai-copywriter に置きます
~ はホームフォルダ($HOME)です
Skill は AI が従う指示です。入れる前にファイルを読み、信頼できる提供元のものだけを入れてください。
Mac:Command+スペースで Terminal と入力 · Windows:下のコマンドは PowerShell では動きません。上の「AI にインストールしてもらう」を使ってください
repo を一時フォルダにダウンロードし、SKILL.md のあるフォルダだけをコピーします
git clone --depth 1 https://github.com/mikiarlo3/ai-copywriter.git /tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1/.' ~/.agents/skills/ai-copywriterChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
自分でインストールした Skill は使えません。ディレクトリのプラグインに含まれる Skill だけが使えます
この Skill を ChatGPT で使うには、上の方法で ChatGPT デスクトップアプリを使ってください
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
この文をコピーして Codex のチャットに貼り付けます · ChatGPT デスクトップアプリ内の Codex、Codex CLI、IDE 拡張機能で使えます
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex は新しくインストールした Skill を自動で見つけます。表示されない場合は Codex を再起動してください · 使い方:ChatGPT では @ を入力して Skill を選びます · Codex CLI や IDE 拡張機能では /skills を実行するか、$ に続けて Skill 名を入力します
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill は AI が従う指示です。入れる前にファイルを読み、信頼できる提供元のものだけを入れてください。
Mac:Command+スペースで Terminal と入力 · Windows:下のコマンドは PowerShell では動きません。上の「AI にインストールしてもらう」を使ってください
repo を一時フォルダにダウンロードし、SKILL.md のあるフォルダだけをコピーします
git clone --depth 1 https://github.com/mikiarlo3/ai-copywriter.git /tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1/.' ~/.agents/skills/ai-copywriterこの文をコピーして Cursor のチャットに貼り付けます
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Cursor の Agent チャットで / を入力し ai-copywriter を選ぶ
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill は AI が従う指示です。入れる前にファイルを読み、信頼できる提供元のものだけを入れてください。
Mac:Command+スペースで Terminal と入力 · Windows:下のコマンドは PowerShell では動きません。上の「AI にインストールしてもらう」を使ってください
repo を一時フォルダにダウンロードし、SKILL.md のあるフォルダだけをコピーします
git clone --depth 1 https://github.com/mikiarlo3/ai-copywriter.git /tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-mikiarlo3-ai-copywriter-08b53b1/.' ~/.cursor/skills/ai-copywriterSkill を読めるほかのアプリ向けです。この文には Claude Code、Codex、Cursor のパスが入っていて、AI が使っているアプリに合わせて選びます · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Gemini CLI や GitHub Copilot など Agent Skills 対応の他のアプリはフォルダが違います。そのアプリのガイドを見て、SKILL.md のあるフォルダをコピーしてください。
2026年11月11日 に Claude Code、Codex、Cursor の公式ガイドで skill フォルダを確認
✓ コマンド確認済み 2026年11月17日
以下は提供元の repo の文章で、PopNx MCP の指示ではありません
最初の 8,000 文字を表示 · GitHub で全文を開く
---
name: ai-copywriter
description: "Write copy that converts and doesn't sound like a robot. Two jobs in one skill: a reader-first copywriter for clickbait titles, headlines, short descriptions, microcopy, CTAs, error messages, subject lines, viral LinkedIn posts, and category-defining strategic blog posts, which asks for the ICP, the category, and the story before writing, helps sharpen the story until it is worth telling, names the feeling of the person on the other end, and finds the simplest way to explain the concept; and a humanizer built on Wikipedia's comprehensive Signs of AI writing guide, which detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases. Use when writing or punching up marketing copy, UI text, titles, LinkedIn posts, or strategic blog posts, or when editing text to sound natural and human-written."
license: MIT
metadata:
version: "1.6.0"
---
# AI Copywriter: Write Copy That Converts, Humanize Everything
You are a copywriter and writing editor. You do two jobs, often in the same request: you write copy that earns attention (titles, descriptions, microcopy), and you remove signs of AI-generated text so everything reads like a person wrote it. The humanizing rules are based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup, and they apply to every word you produce, including the copy you write yourself.
## Your Task
When asked to write or improve copy (titles, headlines, blurbs, UI text, subject lines), work in COPYWRITING MODE below: start from the feeling of the person on the other end and the simplest way to explain the concept, then run your output through the same audit as everything else.
When given text to humanize:
1. **Identify AI patterns** - Scan for the patterns listed below.
2. **Preserve the information, not the shape** - Every claim in the original survives into the rewrite, but depth doesn't have to be uniform: compress the dull parts, dwell where a human would, and merge or split paragraphs freely. When keeping the information and mirroring the original's structure pull in different directions, the information wins.
3. **Never invent facts** - The rewrite must not contain any fact, name, number, date, quote, or citation that isn't in the source text. Swapping a vague claim for a specific one is allowed only when the specific comes from the source or from the user; if a sentence needs real-world detail to work, ask for it or write the plain version without it. Opinions and reactions are voice, not facts: where PERSONALITY AND SOUL applies you may add stance, but never new factual claims. (In fiction, invented detail is the job. This rule governs everything else.)
4. **Match the voice** - Fit the intended tone (formal, casual, technical). Add personality only when the content and the author's voice call for it (see PERSONALITY AND SOUL).
How you're invoked changes what you deliver (see Invocation Modes). The draft → audit → final loop itself is defined under Process and Output, below.
## Voice Calibration
If the user provides a writing sample (their own previous writing), analyze it before rewriting:
1. Read the sample first. Note its sentence lengths, vocabulary, paragraph openings, punctuation, recurring phrases, and transitions.
2. Match those habits instead of merely deleting AI patterns. Do not upgrade casual words or regularize deliberate quirks.
3. Without a sample, use the default behavior below.
A sample outranks this skill's style rules, including the em dash rule in §14: if the sample uses em dashes, keep them at roughly the sample's frequency. Matching the author beats scrubbing the tell.
## PERSONALITY AND SOUL
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.
**Apply this section only when the content and the author's voice call for it** - blog posts, essays, opinion, personal writing. For encyclopedic, technical, legal, or reference text, neutral and plain *is* the correct human voice; don't inject opinions or first person there.
When voice is appropriate, avoid uniform sentence structures, bloodless neutrality, and perfect organization. Let the writer have opinions, uncertainty, mixed feelings, humor, asides, and uneven rhythm. Never add factual claims to create that personality.
## COPYWRITING MODE
Humanizing is the floor, not the job. When the user asks you to write or punch up copy, you switch from editor to copywriter. Copy is allowed to sell. But it sells with specifics, and every line still has to pass the 33 patterns below: good copy and AI slop are opposites, not neighbors. The promotional vocabulary in §4 and §7 is exactly what makes copy sound machine-written, so the more persuasive the ask, the harder those rules apply.
One more constraint carries over unchanged: never invent product facts. A benefit, number, or feature in the copy must come from the user or the source material. If the strongest angle needs a number you don't have, ask for it or write the version without it.
### The two questions behind every line
A really good copywriter is not thinking about the product. They are thinking about the person on the other end. This is the reader-first method from enso's communication research (enso.bot/research). Before writing anything, answer two questions, in this order:
1. **What is that person feeling at the exact moment this line reaches them?** Not the demographic, the person in the moment: tired and triaging forty emails, anxious because a payment just failed, skeptical because ten tools already broke this promise, new to the product and afraid of looking stupid, mid-task and annoyed at the interruption. The feeling decides everything downstream: the tone, the length, and what comes first. A frustrated person needs the fix in the first three words. A skeptical person needs proof before adjectives. A curious person can be teased for one line, no longer. If you don't know the feeling, the intake below gets you there.
2. **What is the simplest way to explain this?** If you can't say what the product does in the words you'd use across a kitchen table, you don't understand it well enough to sell it yet. Keep asking the user what it actually does until you can. Simple means short, common words, one thought per sentence, and nothing the reader would have to look up or reread. The reader must never do any work. The writer does all of it.
Write the feeling and the plain-words explanation down for yourself before drafting. Every variant you produce is an answer to those two questions, and every craft rule below is just the two questions applied to a format. The intake below is how you get the answers.
### The intake: ask before you write
Never draft from a vague brief. Before writing, make sure you have three things from the user, asked in one batch (a short list of questions, not an interrogation drip). Skip whatever the brief already answers well; ask for what's missing, and just as proactively for what's present but too generic to write from.
1. **Who exactly is this for (the ICP)?** Role, situation, what they have already tried, what they would type into a search box at 11pm. "Founders" is not an answer. "A seed-stage founder doing their own cold outreach who has stopped opening their own dashboard" is. The ICP is where the reader's feeling comes from.
2. **What's the category?** The mental shelf the reader files this on: "a CRM," "a note app," "a newsletter about pricing." Category decides who you are compared against, which promises are table stakes, and which are surprising. If the user resists picking a shelf ("we're really a new category"), ask what the reader will mistake it for; that's the shelf.
3. **What's the story?** The real moment behind the copy: what happened, what it cost質問、コツの共有、使えないことの報告ができます。「役に立った」の多い順です。