Content Marketing by vibeeval — AI Skill for Any LLM

Overview

Publisher	vibeeval
Repository	`vibecosystem`
Skill name	`content-marketing`
Stars	533
Forks	44
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 vibeeval on GitHub. Read the source before you install it.

Installation

Install the Content Marketing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/vibeeval/vibecosystem/tree/main/skills/content-marketing
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.

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/vibeeval/vibecosystem.git /tmp/vibecosystem
mkdir -p .claude/skills
cp -r /tmp/vibecosystem/skills/content-marketing .claude/skills/content-marketing

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Marketing 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 Content Marketing 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 Content Marketing 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.

Content Marketing

AI destekli icerik uretimi icin kalite kontrol, SEO optimizasyonu ve pazarlama psikolojisi.

AI Slop Detector (30+ Pattern)

AI tarafindan yazildigini ele veren kaliplari tespit et ve temizle.

Yasak Acilis Cumleri


TESPIT ET VE SIL:
- "In today's digital landscape..."
- "In the ever-evolving world of..."
- "Let's dive in..."
- "Let's dive deep into..."
- "In this comprehensive guide..."
- "Welcome to our deep dive..."
- "Are you ready to discover..."
- "Have you ever wondered..."
- "In an era where..."
- "The landscape of X is rapidly changing..."

Yasak Kelimeler ve Ifadeler


YUKSEK RISK (hemen degistir):
- "leverage" → "use" veya "apply"
- "utilize" → "use"
- "delve" → "explore" veya "look at"
- "tapestry" → SIL veya yeniden yaz
- "paradigm shift" → "change" veya "new approach"
- "synergy" → SIL
- "holistic" → "complete" veya "full"
- "robust" → "strong" veya "reliable"
- "seamless" → "smooth" veya "easy"
- "cutting-edge" → "modern" veya "new"
- "game-changer" → spesifik etkiyi yaz
- "revolutionize" → ne degistigini yaz
- "empower" → ne yaptigini yaz
- "streamline" → nasil basitlestirdigini yaz

ORTA RISK (context'e gore):
- "It's worth noting that..." → direkt soyle
- "It's important to understand..." → direkt soyle
- "Interestingly enough..." → SIL
- "As we all know..." → SIL
- "At the end of the day..." → SIL
- "Moving forward..." → SIL
- "That being said..." → SIL
- "Without further ado..." → SIL

Yapi Kaliplari


TESPIT ET:
- Her paragraf tam 3 cumle (AI pattern)
- Her baslik soru formunda (AI pattern)
- "First... Second... Third..." listeleme (dogal degil)
- Her bolum ayni uzunlukta (insan boyle yazmaz)
- Emoji arasinda icerik (LinkedIn AI slop)

Regex Tarama

bash
# AI slop tarama script'i
grep -inE "(let's dive|in today's|ever-evolving|comprehensive guide|paradigm shift|leverage|utilize|delve|tapestry|synergy|holistic|robust|seamless|cutting-edge|game-changer|revolutionize|empower|streamline)" "$1" | while read line; do
  echo "SLOP TESPIT: $line"
done

Icerik Kalite Skorlama (5 Boyut)

Her icerik parcasini 5 boyutta skorla. Toplam 100 puan, gecme esigi 70.

Boyut	Agirlik	Olcum
Insanilik	%30	AI slop pattern sayisi (az = iyi), kisisel ton, gercek ornekler
Spesifiklik	%25	Somut rakamlar, gercek isimler, detayli ornekler (belirsiz = dusuk skor)
Yapi Dengesi	%20	Paragraf uzunlugu varyasyonu, baslik cesitliligi, liste/metin dengesi
SEO	%15	Keyword yogunlugu (%1-3), baslik optimizasyonu, meta description, internal link
Okunabilirlik	%10	Cumle uzunlugu varyasyonu, aktif dil, gereksiz kelime orani

Skorlama Formulu


Insanilik = 30 - (slop_pattern_sayisi * 3)  // max 30
Spesifiklik = somut_ornek_sayisi * 5         // max 25
Yapi = paragraf_varyasyon_skoru              // max 20
SEO = keyword_skor + meta_skor + link_skor   // max 15
Okunabilirlik = cumle_varyasyon + aktif_oran  // max 10

TOPLAM = Insanilik + Spesifiklik + Yapi + SEO + Okunabilirlik

70+ = YAYINLA
50-69 = REVIZE ET (otomatik, max 2 deneme)
<50 = YENIDEN YAZ

AI Watermark Temizleme

AI uretimi metinlerde gorunmeyen Unicode karakterler olabilir:

bash
# Gorunmeyen watermark'lari temizle
sed -i '' 's/\xe2\x80\x8b//g' "$1"    # Zero-width space (U+200B)
sed -i '' 's/\xe2\x80\x8c//g' "$1"    # Zero-width non-joiner (U+200C)
sed -i '' 's/\xe2\x80\x8d//g' "$1"    # Zero-width joiner (U+200D)
sed -i '' 's/\xef\xbb\xbf//g' "$1"    # BOM (U+FEFF)
sed -i '' 's/\xc2\xad//g' "$1"        # Soft hyphen (U+00AD)

# Em dash asiri kullanimi (AI belirtisi)
# 3+ em dash varsa 1'e dusur
sed -i '' 's/—/--/g' "$1"  # em dash -> double hyphen

Copywriting Formulleri

AIDA (Attention-Interest-Desire-Action)


ATTENTION: Dikkat cekici baslik veya istatistik
  "Kullanicilarin %73'u ilk 3 saniyede karar veriyor"

INTEREST: Problemi detaylandir, empati kur
  "Her gun saatlerce icerik yazip sonuc alamiyorsun"

DESIRE: Cozumun faydasini goster
  "Bu framework ile 30 dakikada SEO-optimized icerik uret"

ACTION: Net CTA
  "Simdi dene -- ilk 7 gun ucretsiz"

PAS (Problem-Agitate-Solve)


PROBLEM: Sorunu tanimla
  "Blog'un organik trafik almiyor"

AGITATE: Sorunun etkilerini buyut
  "Her gun rakiplerin senden once siralamalara giriyor.
   Her gecen gun daha fazla potansiyel musteri kaybediyorsun."

SOLVE: Cozumu sun
  "Keyword research + content cluster stratejisi ile
   3 ayda organik trafigi 5x artir"

BAB (Before-After-Bridge)


BEFORE: Mevcut durum
  "Haftalik 2 blog yazisi, 500 organik ziyaretci"

AFTER: Hedef durum
  "Haftalik 5 optimized yazi, 5000 organik ziyaretci"

BRIDGE: Nasil ulasacaksin
  "Content cluster + pillar page stratejisi"

SEO Icerik Checklist

Yazi Oncesi


[ ] Keyword research yapildi (ana + 5-10 long-tail)
[ ] Search intent belirlendi (informational/transactional/navigational)
[ ] Rakip analizi yapildi (ilk 5 sonuc incelendi)
[ ] Content outline olusturuldu (H2/H3 yapisi)
[ ] Internal link firsatlari belirlendi

Yazi Icinde


[ ] Baslik keyword iceriyor (ilk 60 karakter)
[ ] Meta description yazildi (155 karakter, CTA iceriyor)
[ ] H1 tek ve keyword iceriyor
[ ] H2'ler keyword varyasyonlari iceriyor
[ ] Ilk 100 kelimede ana keyword var
[ ] Keyword yogunlugu %1-3 arasi
[ ] Internal link'ler eklendi (min 3)
[ ] External link'ler eklendi (otorite kaynaklara, min 2)
[ ] Gorseller alt text iceriyor
[ ] URL slug kisa ve keyword iceriyor

Yazi Sonrasi


[ ] AI slop taramasi yapildi (0 pattern)
[ ] Kalite skoru 70+ (5 boyut)
[ ] Watermark temizligi yapildi
[ ] Okunabilirlik kontrolu (Hemingway Grade 6-8)
[ ] Mobil gorunum kontrolu
[ ] Schema markup eklendi (Article/HowTo/FAQ)

Programmatic SEO

Sablonla olceklenebilir icerik uretimi:


SABLON: "[Sehir]'de En Iyi [Kategori] [Yil]"
  → "Istanbul'da En Iyi Kahve Dukkanlari 2026"
  → "Ankara'da En Iyi Co-working Alanlari 2026"
  → "Izmir'de En Iyi Vegan Restoranlar 2026"

VERI KAYNAKLARI:
  - Sehir listesi (81 il)
  - Kategori listesi (50+ is tipi)
  - Google Places API (isletme verileri)

URETIM:
  81 sehir x 50 kategori = 4,050 sayfa
  Her sayfa benzersiz veri iceriyor (template degil)

Content Cluster Stratejisi


PILLAR PAGE (3000+ kelime):
  "Mobil Uygulama Monetizasyonu Rehberi"
    │
    ├── CLUSTER 1: "Freemium vs Premium Model Karsilastirmasi"
    ├── CLUSTER 2: "In-App Purchase Stratejileri"
    ├── CLUSTER 3: "Subscription Pricing Rehberi"
    ├── CLUSTER 4: "Paywall Tasarim Best Practices"
    ├── CLUSTER 5: "A/B Test ile Fiyat Optimizasyonu"
    └── CLUSTER 6: "Regional Pricing (PPP) Uygulama"

Her cluster pillar page'e link verir.
Pillar page her cluster'a link verir.
Topical authority olusur.

Icerik Uretim Pipeline


1. KEYWORD RESEARCH
   └─ Ana keyword + 10 long-tail sec

2. OUTLINE
   └─ H2/H3 yapisi olustur (rakip analizi bazli)

3. DRAFT
   └─ Yazildi (AI veya insan)

4. SLOP CHECK
   └─ 30+ pattern taramasi
   └─ Bulunan pattern'leri temizle

5. QUALITY SCORE
   └─ 5 boyut skorlama
   └─ 70+ = devam, <70 = revize

6. WATERMARK CLEAN
   └─ Unicode temizligi

7. SEO CHECK
   └─ Keyword, meta, link kontrolu

8. PUBLISH

vibecosystem Entegrasyonu

copywriter agent: Bu skill'i birincil referans olarak kullanir
growth agent: Content stratejisi ve programmatic SEO icin
seo-specialist agent: Teknik SEO kontrollerini uygular
ai-slop-cleaner skill: Slop pattern'leri bu skill'den besler
technical-writer agent: Dokumantasyonda da slop kontrolu yapar

Frequently asked questions

What does the Content Marketing AI skill do?

Icerik pazarlama ve SEO odakli yazi uretimi. AI slop temizleme (30+ pattern), icerik kalite skorlama (5 boyut), watermark temizleme, copywriting formulleri (AIDA, PAS, BAB), programmatic SEO ve icerik stratejisi.

Why use Content Marketing on TypingMind?

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

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

Which AI models can use Content Marketing?

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 Content Marketing?

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

Is the Content Marketing AI skill free?

Yes. It is published on GitHub by vibeeval 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.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Content Marketing

AI Slop Detector (30+ Pattern)

Yasak Acilis Cumleri

Yasak Kelimeler ve Ifadeler

Yapi Kaliplari

Regex Tarama

Icerik Kalite Skorlama (5 Boyut)

Skorlama Formulu

AI Watermark Temizleme

Copywriting Formulleri

AIDA (Attention-Interest-Desire-Action)

PAS (Problem-Agitate-Solve)

BAB (Before-After-Bridge)

SEO Icerik Checklist

Yazi Oncesi

Yazi Icinde

Yazi Sonrasi

Programmatic SEO

Content Cluster Stratejisi

Icerik Uretim Pipeline

vibecosystem Entegrasyonu

Frequently asked questions

Related AI Skills

Set up your own AI workspace now