Prioritize a supplied prospect set using bounded evidence
Use only information supplied in the conversation and this skill text. Do not browse, call tools, inspect files, execute code, create artifacts, or take external actions. Return the work directly in chat. Attribute material claims to supplied source labels or quotations; a pasted URL is a source label, not evidence that its contents were checked. Distinguish supplied facts, reasonable interpretations, proposals, and unknowns.
Inputs and scope: Obtain the complete prospect set to evaluate, the user's offer and fit criteria, supplied company facts, evidence dates, disqualifiers, capacity, and prioritization objective. Unknown fields remain unknown. If a decision-changing input is absent, ask the smallest useful question and complete the portions supported by available material. State assumptions explicitly; do not manufacture facts, approvals, dates, or completion evidence.
Method 1. Define fit, possible need, access, timing, and disqualification separately. Clarify what makes an account worth attention for this offer instead of importing a particular company's scoring rules. 2. Review every supplied prospect and record evidence coverage. Distinguish observed facts from inferred demand: hiring can indicate growth or replacement, and website shortcomings do not establish urgency or budget. 3. Assess existing vendor or agency involvement neutrally. Presence alone does not prove overpayment, dependence, poor results, or willingness to switch; economic claims need supplied evidence. 4. Prioritize using criteria suited to the decision, with transparent qualitative reasoning or explicitly agreed weights. Separate strong fit with little evidence from poor fit with abundant information; do not reward verbosity as intent. 5. Identify the next question that would most change each account's priority, including a no-fit or defer outcome. Do not invent contacts, authority, purchase intent, or missing firmographics. 6. Report ranked accounts and coverage using clearly defined stages and denominators. If describing a funnel, name each stage, its inclusion rule, count, and denominator so a change in stage definition cannot masquerade as conversion.
Output: Return the criteria, ranked prospect table with facts and hypotheses separated, disqualifications or deferrals, coverage summary, and next discovery questions.
Quality checks: Confirm all supplied accounts were considered, weights are assumptions when not provided, counts reconcile, and inferred pain is not stated as fact. No CRM writes, list discovery, contact enrichment, or outreach execution occurs.
Worked example: Three supplied prospects include a growing shop hiring an administrator, an established shop with an agency-built site, and a business outside the user's target geography. Prioritize the first for a question about administrative workload if fit is otherwise strong, treat the agency fact as neutral, and exclude the third under the explicit geography rule. None is labeled ready to buy.