
AI Outbound Campaign Orchestration Agent
Drazen




AI agentClaude Skills for SDRs
Builds your fit and intent scoring model, disqualifiers, MQL/SQL rules, then scores the leads you paste in. Works with Claude…
$14.99· one file, yours to keep
Yours to keep · instant download
Or all of them, $6.99/mo
Zbigniew and 2,500+ other specialists, in your AI. Ask for any of them by name.
7 days free, then $6.99/mo · cancel anytime
One file
All-in-one
30-day money-back · secure checkout by Stripe
# Zbigniew - AI Lead Qualification and Deal Scoring Agent ## What This Agent Does Zbigniew decides what is worth your time. He builds a qualification and scoring system fitted to one specific business - what "good fit" means, what counts as real intent, what disqualifies immediately, how many points each signal is worth - and then applies it to actual leads or open deals that the user pastes in, returning a ranked list with a reason for every score. Two jobs, one logic. Lead qualification decides whether to engage. Deal scoring decides whether an open opportunity is real and what would make it
Sales team of 4 chases every inbound lead equally, and 70% of pipeline time goes to deals that never close. Build us a scoring model?
Fit and intent score on separate axes - collapsing them into one number is why loud bad-fit leads eat 70% of your pipeline time. We derive the fit profile from your actual closed-won customers and the anti-profile from the losses, set hard disqualifiers as rules rather than point deductions, and build grade bands with a defined action per cell: who gets a call within the hour, who gets nurture, who gets a polite no. MQL and SQL definitions get written so marketing and sales sign the same document. One correction: the model comes from your win-loss history, not from industry templates. How many closed-won and closed-lost deals can you export?
Three things: a qualification model with an ICP and anti-profile, a fit score and a separate intent score with explicit weights, hard disqualifiers and grade bands with an action per band, plus MQL and SQL definitions. A discovery question set tied to each scored criterion. And scored output: the leads or open deals you paste in, ranked, each with its score drivers, biggest unknown, risk flags and next action.
Paste the .md file into your Claude Project Instructions (or ChatGPT's system prompt or custom instructions), then paste the activation prompt into the conversation. Zbigniew starts asking questions immediately. Takes under two minutes.
Claude, ChatGPT, Gemini, Copilot, Perplexity, or any AI chat that accepts a system prompt or custom instructions. Zbigniew is a plain text agent file, not an app or a plugin, so there is nothing to connect and no API key required.
Zbigniew still builds a working model. He asks for your best customer, the customers you regret, and who signed the last contract, then states clearly which weights are derived from your evidence and which are assumptions, and names the three data points that would replace them. He also only scores on fields you have confirmed you actually possess at the moment of decision.
Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.