Content & Video Skill
AI Influencer Pipeline
Standalone 5-step pipeline
$15
Content Quality Gate
Score content quality with AI phrase detection, readability analysis, keyword density, and…
An automatic quality barrier between content production and publishing that scores any blog post, service page, or landing page across five dimensions on a 0-100 scale. It detects AI-typical phrasing, checks readability and keyword density, scrubs invisible Unicode and vague filler, and routes anything below threshold into an auto-revision loop.
$15 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Skill
- Category Content & Video
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
Between draft and publish sits a scored gate: five weighted dimensions, a 70-point bar, and a revise loop that fixes the weakest dimension first while scrubbing AI cliches, invisible characters and fuzzy words.
- Runs the content-analyzer CLI on the draft with language and target keyword flags, producing a JSON composite score from 5 weighted dimensions: humanity and voice 30 percent, specificity and depth 25, structure and readability 20, SEO optimization 15, readability score 10.
- Applies the threshold system: 70 and above passes to publish, 50 to 69 enters the auto-revise loop, below 50 stops and escalates for human review.
- In the revise loop, fixes the single lowest-scoring dimension first instead of rewriting everything: if humanity is at 41, it removes the flagged AI phrases and replaces them with specific data, then rescores. Maximum 2 revision attempts before the content is rewritten from scratch.
- Scrubs AI fingerprints as part of every pass: a banned-phrase dictionary of 50+ AI cliches in English and Turkish, passive-voice detection above 20 percent, keyword stuffing above 2.5 percent density, and context-aware em-dash replacement.
- Strips invisible forensic traces: zero-width spaces, byte order marks and BIDI control characters that betray AI generation are removed with a single regex sweep.
- Hunts vagueness with a 26-word fuzzy-word list (many, significantly, usually, nearly and friends): each hit is either deleted if the sentence survives without it, or replaced with a concrete number, measurement or dated fact.
One power source. 6 lines out.
content-quality-gate · core
core active · 6 lines
- ✓ quality-checking a blog
Quality-checking a blog post or service page before publishing
- ✓ stripping ai-tell phrases
Stripping AI-tell phrases like 'delve into' or 'seamless' from marketing copy
- ✓ verifying keyword density
Verifying keyword density stays in the natural 0.5-2.5% range
- ✓ forcing vague claims to
Forcing vague claims to be replaced with concrete numbers and proof
- ✓ cleaning invisible unicode
Cleaning invisible Unicode watermarks that leave AI-generation traces
- ✓ running content through
Running content through a checker that is separate from the writer (Maker-Checker)
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Stops low-quality content from reaching readers and damaging trust
license: perpetual -
Makes content feel human and specific instead of generic AI slop
license: perpetual -
Reduces waste by fixing only the weakest dimension instead of rewriting everything
license: perpetual -
Protects SEO standing against helpful-content signals that penalize thin writing
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Five-dimension scoring with weights (humanity, specificity, structure, SEO, readability)
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Content and SEO teams who want every published piece to pass an objective, specificity-driven quality bar before it goes live.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
Does it score copy from any source, or only AI-generated drafts?
Any blog post, service page or landing page goes through the same five-dimension score, whoever wrote it. A human draft full of vague filler fails the same checks an AI draft would.
-
A single 0-to-100 number feels arbitrary. What is actually behind it?
It is five dimensions rather than one gut call: AI-typical phrasing, readability, keyword density in the natural range, invisible Unicode and vague filler. Each is a concrete check, so the score traces back to specific issues you can fix.
-
When it flags a piece, does it rewrite it or just block it?
It scrubs invisible Unicode and obvious filler, but for real issues it routes the piece back rather than silently rewriting your voice. A passing score means it cleared an objective bar, not that the argument is automatically compelling.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.