Outbound Campaign Performance Optimizer
Analyze outbound call data to optimize scripts, agent performance, and conversion rates
What You Can Do
You can upload call campaign data—including conversion rates, handle times, objection patterns, and agent metrics—and receive quantified analysis of performance drivers. The skill diagnoses whether underperformance stems from script ineffectiveness, agent skill gaps, or process inefficiencies, then recommends specific script refinements, coaching interventions, and training priorities tailored to individual agent cohorts or campaign variations.
Features
Compare conversion rates across script variations and identify which messaging elements, objection responses, or call flow sequences drive higher close rates
Detect performance variance within teams (30%+ gaps) and isolate whether differences are coaching-related, script-related, or selection-related
Analyze which objections cause call terminations most frequently and evaluate agent success rates by objection type
Identify time allocation inefficiencies and pinpoint whether longer calls correlate with higher conversions or wasted cycles
Quantify which metrics (script version, agent tenure, time-of-day, call sequence) most strongly predict conversion outcomes
Generate targeted coaching priorities for individual agents or teams based on performance data gaps
Structure evidence-based tests for script or process changes with sample size and duration guidance
Example Output
Example 1: Script Optimization
Input: Campaign data showing Agent Group A (Script V2) converting at 18% vs. Agent Group B (Script V1) at 12%.
Output:
- Script V2 outperforms by 6 percentage points (50% lift)
- Primary driver: Modified objection response on budget concerns (73% override rate vs. 41%)
- Recommendation: Adopt Script V2 format across all agents; coach Script V1 group on specific override language
- Revenue impact: $45K additional monthly pipeline at current call volume
Example 2: Agent Performance Diagnosis
Input: Three agents in same team; conversion rates 22%, 16%, 14% despite identical scripts and call volume.
Output:
- Agent 1 (22%): Higher discovery questions (8 vs. 5 avg), longer average calls (6:20 vs. 4:50)
- Agent 2 (16%): Shorter calls, fewer objections overcome, weaker closing attempts
- Agent 3 (14%): Highest objection frequency but lowest override rate (34%)
- Coaching priorities: Agent 2 needs closing technique training; Agent 3 needs objection-handling coaching; Agent 1 model for discovery depth
Example 3: Handle Time vs. Revenue Trade-off
Input: Monthly data showing average handle time increased from 4:20 to 5:10 over quarter.
Output:
- Conversion rate actually improved +2% during same period
- Additional time spent on discovery questions (avg +45 sec)
- Efficiency analysis: Throughput declined 14% but revenue per call increased 18%
- Recommendation: Retain longer handle time; focus coaching on closing efficiency within extended calls rather than reducing talk time
What's Included
- SKILL.md instruction file: Complete framework for analyzing campaign data and structuring performance diagnostics
- Campaign Performance Template: Structured format for input data (conversion rates, handle times, objection logs, agent metrics)
- Script Variation Comparison Worksheet: Side-by-side analysis template for A/B testing script versions
- Agent Cohort Benchmarking Checklist: Variables to track for accurate performance attribution (tenure, training date, script version, time-of-day patterns)
- Coaching Recommendation Framework: Evidence-based format for translating metrics into targeted development priorities
Who It's For
- Call Center Managers — Diagnose team performance issues and allocate coaching resources to highest-impact priorities
- Sales Operations Leaders — Evaluate script effectiveness and campaign optimization across multiple teams or regions
- Quality Assurance Directors — Correlate QA scores with conversion outcomes and identify coaching gaps
- Training Coordinators — Measure training effectiveness by cohort and personalize development based on performance data
- Revenue Leaders — Identify conversion rate drivers and forecast revenue impact of script or coaching changes
Best For
- Analyzing campaign conversion rate declines or plateaus with inconsistent agent performance
- Evaluating the impact of script changes or new call flow variations on agent outcomes
- Diagnosing why individual agents significantly outperform or underperform team benchmarks
- Planning targeted coaching interventions based on objection-handling gaps or closing technique weaknesses
- Structuring A/B tests of script variations and forecasting expected lift before full rollout
You might also like
You can generate multi-week shift schedules optimized across competing business priorities: staffing customer demand patterns, respecting employee availability and preferences, meeting regulatory and contractual requirements, and controlling labor costs. Claude analyzes trade-offs between schedule fairness, service coverage, and budget impact, giving you strategic recommendations with constraint validation before deployment.
You systematically investigate escalated support tickets by mapping customer symptoms to root causes, eliminating troubleshooting dead-ends, and applying technical frameworks that work across billing, account, and system-level issues. This skill guides you through decision trees that determine whether cases need engineering escalation, policy exceptions, or technical remediation—then helps you communicate the resolution in ways that rebuild customer trust and prevent churn.
You can systematically analyze your support operation's historical ticket volume, agent productivity metrics, and availability constraints to generate evidence-based shift schedules. The skill identifies optimal coverage windows, balances workload distribution across your team, and recommends scheduling adjustments that simultaneously improve operational metrics and reduce agent burnout.
You can quickly categorize incoming support tickets by issue type, severity, and resolution path. The framework helps you apply standardized solutions from your knowledge base, identify when escalation to Tier 2/3 is necessary, and maintain consistent response quality across your team. This reduces average handle time while improving first-contact resolution rates and customer satisfaction scores.
You can systematically analyze weeks or months of historical contact volume data to identify trends, seasonality, and anomalies. The skill applies multiple forecasting methodologies (time-series decomposition, trend analysis, comparative methods) and produces forecasts with documented assumptions, error bounds, and actionable staffing recommendations backed by statistical confidence intervals.
Transform historical contact volume data and business constraints into data-driven shift schedules that balance operational efficiency with cost control. You can model multiple scheduling scenarios—comparing different shift lengths, patterns, and staffing levels—to quantify the trade-offs between service quality and labor spend. Claude helps you identify staffing gaps, calculate precise interval-by-interval requirements, and generate compliant schedules that respect labor regulations and company policies.
You can rapidly assess enterprise account criticality, activate appropriate resolution teams, classify issue severity, and maintain coordinated stakeholder communication throughout resolution. The protocol ensures mission-critical issues receive immediate attention with documented accountability, preventing contract renewal risk and executive escalation.
You can architect complete outbound campaign strategies from prospect segmentation through performance analysis. Claude helps you design data-driven targeting strategies, generate compliant agent scripts tailored to specific lead segments, plan optimal call sequences with strategic timing, establish measurable KPIs, and identify compliance risks—reducing planning time from days to hours while improving conversion rates by 15-25%.