- Home
- Skills
- Sales & Lead Gen
- Sales Email & Outreach Quality Gate
Works with the AI Agents you already use
Sales Email & Outreach Quality Gate
The Sales Email & Outreach Quality Gate is an adversarial reviewer for sales outreach: cold emails, follow-ups, LinkedIn messages, and multi-step sequences.
$9
Sales Email & Outreach Quality Gate
Example session with this skill installed
Subject: RE: FOLLOW UP!!! URGENT opportunity you can't miss
Hi {{first_name}}, I emailed you last week and you didn't reply. Our platform is the BEST in the world and will 10x your revenue guaranteed. Let's hop on a 60-minute call this week to discuss. Click here now!!!
- Read your context and instructions
- Compiled the sales email
VERDICT: HOLD
SUMMARY: Spam-trigger subject, broken personalization, and pushy tone; likely to hurt deliverability and the relationship.
SUBJECT & OPEN:
- Fake RE:, ALL CAPS, URGENT, and triple exclamation points are classic spam triggers.
CLARITY & ASK: - A 60-minute call is a high-friction first ask; offer a lower-commitment step.
PERSONALIZATION
- The first-name merge field is unrendered; no recipient-specific relevance.
DELIVERABILITY & SPAM RISK: - BEST in the world, guaranteed, and Click here now raise spam-filter risk.
TONE
- you didn't reply is guilt-tripping and presumptuous.
FIX FIRST
- Rewrite the subject without RE:/caps/exclamations and fix the merge field.
- Replace the unsupported 10x-guaranteed claim and lower the ask.
Connects securely to your tools. The creator never sees your data.
About this skill
The Sales Email & Outreach Quality Gate is an adversarial reviewer for sales outreach: cold emails, follow-ups, LinkedIn messages, and multi-step sequences. You hand it a draft you are about to send — often AI-generated at volume — and it reads it the way a skeptical prospect and a deliverability-aware sales leader would.
It runs five passes — subject & open, clarity & single ask, personalization & relevance, deliverability & spam risk, and tone & pushiness — and returns a structured SEND / REVISE / HOLD verdict with line-level flags and the highest-impact fixes first. It is built to be the last check before outreach goes out, when volume is high and nobody has read each message for clarity, deliverability, and tone.
It judges; it does not write. It never drafts emails, rewrites your copy, builds sequences, or sends anything, and its spam-risk flags are heuristics, not a guarantee of inbox placement.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Sales & Lead Gen.
Its spam-risk flags are heuristics based on common triggers and formatting, not a guarantee of inbox placement — actual deliverability depends on your domain reputation, authentication, and the recipient's filters, which it cannot see. It reviews one message or sequence at a time, does not write, rewrite, or send email, and cannot research the recipient or verify claims for you. It judges against the personalization and context present in the draft; without recipient context, relevance checks are limited.
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 buying a skill.
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
5 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 access is the only permission this skill needs. It reads the single email or sequence you provide and returns a verdict. It never writes files, connects to a network, sends email, or runs commands — nothing is sent anywhere and no recipient data is stored or transmitted.