defluffReverse the AI in corporate email. Detect whether a message was written by AI, AI-assisted, or by a human. When AI was involved, guess the prompt the sender...
Install via ClawdBot CLI:
clawdbot install yozaz/defluffGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://openclaw.aiAudited Apr 21, 2026 · audit v1.0
Generated Oct 2, 2026
A busy executive forwards a batch of 20-40 unread emails and asks which ones need a decision, which are noise, and whether any are AI-written outreach. The skill classifies authorship, surfaces action items, and flags scam emails that impersonate internal colleagues.
A sales rep pastes a long email thread with a prospect who has gone quiet, asking for a summary of intent, urgency, and the most recent commitment. The skill extracts real intent, detects AI-polished responses, and highlights where the buyer is waiting on an answer.
A finance team member pastes suspicious payment or late-fee notices forwarded from the shared AP inbox. The skill names the scam pattern (invoice fraud, BEC, phishing), enumerates red flags such as lookalike domains and fake approval chains, and marks the message as NOISE.
A job seeker forwards several recruiter outreach emails and asks which are legitimate. The skill identifies generic templates, fake recruiter patterns, and crypto or MLM projects offering unrealistic C-level titles, while preserving the few emails that require a reply.
A customer support lead pastes a mixed-language batch of inbound messages and wants the actionable ones surfaced first. The skill mirrors each email's language in its output, classifies urgency, and separates real customer issues from automated noise.
A subscription web app that connects to a user's mailbox or accepts pasted email, classifies authorship and urgency, extracts action items, and flags scams. Sold per-seat to professionals and small teams who want to reclaim time from inbox overload.
An API that exposes the scam-pattern and authorship detection capabilities to email security vendors, CRMs, or helpdesk tools so their users see defluff verdicts inline. Priced by API call volume with enterprise SLAs.
A service layer that uses the skill as an assessment engine: auditors run batches of client emails to detect BEC risks, and trainers teach employees to spot AI-generated outreach and phishing. Delivered as one-off audits or ongoing advisory.
💬 Integration Tip
Chain defluff with a mail-read skill: fetch unread messages into a batch, pass the raw content to the skill, and parse the consistent Authored / Prompt / Verdict / bullets format directly into a task list or CRM note.
Scored Oct 2, 2026
API-first email platform designed for AI agents. Create and manage dedicated email inboxes, send and receive emails programmatically, and handle email-based workflows with webhooks and real-time events. Use when you need to set up agent email identity, send emails from agents, handle incoming email workflows, or replace traditional email providers like Gmail with agent-friendly infrastructure.
Secured Email Mnagement - Gmail, Outlook & Exchange - list, search, read, send, reply, forward, delete, and modify emails across multiple accounts (gog-cli s...
王昊自动回复助手。帮王昊自动响应同事的业务咨询。王昊是追光战队拓新主管。触发场景:(1) cron定时自动扫描未回复消息 (2) 用户说「帮我回复」「自动回复一下」手动触发。(3) 王昊问「今天有什么未完成的事项」。
Email Template Builder
Send emails via Resend API from any verified domain. Use when sending emails, notifications, or automated messages. Supports HTML and plain text. Default voi...
通过阿里云邮箱、QQ邮箱或163邮箱等发送和接收邮件。支持发送普通邮件、带附件邮件、接收邮件、检查新邮件。当用户要求发送邮件、查看邮件、检查新邮件时使用。