Marketing sends MQLs. Does sales work them?
Paste how leads get from marketing to sales today - the lifecycle stages, what makes an MQL, the scoring rules and their points, how a lead gets an owner, how fast sales responds, what happens to a rejected lead, the pipeline stages - and, if you have them, the leads, MQLs, SQLs, opportunities and wins for one period. Your browser reads every scoring rule, checks that an MQL needs both fit and engagement, and holds your funnel against the revops skill's benchmarks (MQL-to-SQL 30-50%, SQL-to-opportunity 50-70%). It flags what leaks: an MQL anyone gets by downloading an ebook, no negative scoring, leads in a shared inbox, a two-day follow-up, rejected leads that vanish, deals that sit in Proposal for months. Free, before you sign in, and nothing is uploaded. Then the audit says what to fix, and the spec writes the lifecycle, scoring, routing, SLAs and reason codes to build in your CRM.
The businesses and numbers in the examples are invented. Two are audits (the logistics one also carries its spec, one click after the audit) and one is a spec; each comes with a saved model reply, so you can see the whole page without signing in or spending a credit.
What this does, and what it does not
Leads leak at handoffs. An MQL that needs only a download sends sales students and job seekers; scoring with no negative points lets competitors through; a lead in a shared inbox has no owner; a reply after 24 hours reaches a lead that has gone cold; a rejection with no reason code teaches nobody anything. The revops skill's answer is a written lifecycle with entry and exit criteria and owners, an MQL that needs both fit and engagement, scoring with negative signals and a calibrated threshold, routing to the most specific match with a fallback, an SLA with an escalation, recycling for rejected leads, and a funnel measured against benchmarks. This page reads your paste, finds the line that shows each of those, works out your funnel rates, and raises the mistakes the skill warns about.
The paid lanes see your lead process (the middle is cut past 6,000 characters, and the page says so), your context (past 4,000) and the page's scan. Your input stays in this browser unless you run a lane. Every reply is held to your input: quotes are checked word for word, and no count, rate, price or window about your business may be invented beyond the skill's own constants - the spec writes [placeholders] for what only you know, such as a target industry or a rep's name. The scoring points in a spec are design values from the skill's templates, to be tested against your past wins. Derived from the agent skill @coreyhaines31/revops by Corey Haines (coreyhaines31/marketingskills, MIT): its principles, lifecycle framework, MQL definition, handoff SLA, scoring models and calibration, routing rules and speed-to-lead data, pipeline hygiene, reason codes and recycling, and metrics. Sources are listed in llms.txt.