Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsAI Text Humanizer & Sounds AI Detector Gate
Make AI-written text sound human: flags the phrases, structure and rhythm that read as machine-written and gives specific rewrites, with a PASS / REVISE / FAIL verdict.
$14
AI Text Humanizer & Sounds AI Detector Gate
Example session with this skill installed
Run the humanizer gate on this draft
"Leveraging cutting-edge solutions, our platform empowers businesses to seamlessly unlock unprecedented value. It is important to note that, in today's fast-paced landscape, synergy plays a crucial role. Moreover, stakeholders can effortlessly drive results. In conclusion, the possibilities are truly endless."
- Read your context and instructions
- Compiled the ai text humanizer
VERDICT: FAIL
SCORE: 14
TELLS FOUND
- [filler-phrase] "It is important to note that" -> throat-clearing that adds no meaning -> delete and state the point directly
- [filler-phrase] "in today's fast-paced landscape" -> generic stock opener -> replace with a concrete, specific situation
- [substance] "leveraging ... unlock unprecedented value ... synergy" -> buzzwords with zero verifiable content -> name the actual product, the actual benefit, and who gets it
- [tone-and-cadence] "seamlessly ... effortlessly ... truly endless" -> relentless adverb-driven hype -> cut the adverbs and show one real result
- [formulaic-structure] "In conclusion, the possibilities are truly endless" -> rote template ending -> close on one specific takeaway
- [punctuation-and-tic] "Moreover," opening a sentence -> default model transition -> vary or remove
TOP THREE FIXES
- Replace every abstract noun with a concrete example, name, or number
- Cut all three filler openers and lead with the real claim
- Remove the hype adverbs and the template conclusion
ONE-LINE SUMMARY: Rewrite around one specific, verifiable result before this ships.
Connects securely to your tools. The creator never sees your data.
About this skill
The AI Text Humanizer & Sounds-AI Detector Gate turns your agent into a strict editor that explains exactly why a draft reads as machine-generated — and then stops, leaving the rewrite to you so you keep your own voice.
It runs five fixed passes over any AI-assisted text: a formulaic-structure check (rote intros, rule-of-three lists, template conclusions), a filler-phrase check ("it is important to note," "in today's fast-paced world," and other throat-clearing), a tone-and-cadence check (no contractions, uniform sentence length, relentless polish), a punctuation-and-tic check (em-dash overuse, repeated transition words, list-introducing colons), and a substance check (whether the text contains any specific, verifiable detail at all).
Every run returns a structured verdict: PASS, REVISE, or FAIL, plus a 0-100 human-voice score, each tell quoted with the reason it reads as AI and a direction for the fix, the top three highest-impact changes, and a one-line summary. Because it quotes the offending spans and refuses to rewrite, it teaches you to recognize the patterns yourself instead of laundering them into a new synthetic voice.
Who it's for: anyone shipping AI-assisted writing who needs it to sound human — marketers, newsletter and blog writers, founders, students, cover-letter writers, and content teams running a publish-time quality gate. It is model-agnostic, read-only, and adds no network or write access. It is an editorial gate, not a paraphraser, and it makes no claim about evading any third-party AI-detection service.
This is a judgment aid, not a guarantee. It flags common AI tells but cannot certify that any text will pass a third-party AI-detection service, and it makes no claim about those services' accuracy or fairness. It evaluates English prose; results on other languages, code, or highly technical writing are less reliable. It deliberately does not rewrite — the author makes the final edits. Style is subjective, so treat low scores as prompts to review, not absolute rulings.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
12 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
File Scopes
Read-only by design. The skill only reads the draft text you give it so it can quote the exact spans that read as AI. It never writes, edits, or rewrites your files, and needs no network, shell, or environment access.