Call Coaching
Coach a rep on a specific call with candid feedback on discovery quality, objection handling, and talk dynamics, grounded in moments from the call.
Overview
Call Coaching gives a rep specific, actionable feedback on a single call: what worked, what to improve, and what to focus on next time. It reads how the conversation actually went using conversation intelligence, then assesses it against solid discovery and objection-handling fundamentals. Every point is grounded in a real moment from the call, with the words that were said.
The skill is built for reps who want to sharpen their own calls and for managers who coach a team. You can name the call by account or date, or let the skill pull recent meetings and confirm the most likely candidate before spending credits. An optional focus, such as discovery, the pricing objection, or whether the rep talked too much, targets the coaching where the rep wants it.
Feedback is candid and useful rather than generic. The skill judges the call against good practice: open questions over pitching, listening over talking, surfacing next steps, and addressing concerns directly. It analyzes one call at a time and keeps the read scoped to that engagement. When the transcript is too thin to judge something, it says so instead of inventing a critique, and when a call has no transcript at all it offers to coach from notes the rep provides.
What It Does
- Strength callouts: Names two to three things the rep did well, each tied to a specific moment in the conversation.
- Improvement areas: Identifies the two to three highest-impact changes and pairs each with a concrete alternative to try next time.
- Talk dynamics: Reads the balance of the call, including who drove, listening versus pitching, and the questions asked, when the data supports it.
- Next-call focus: Recommends one or two things to do differently, tied to where the deal now stands.
- Targeted coaching: Narrows the feedback to a chosen area such as discovery or a specific objection when the rep asks for it.
- Grounded assessment: Cites what was said for every point and declines to critique what the transcript cannot show.
Use Cases
Self-Review After Discovery
A rep finishes a discovery call and wants to know how it went before the follow-up. The skill reads the conversation and returns what landed and where discovery fell short. For the weak spots it offers a concrete alternative, such as anchoring on an earlier value point instead of discounting when price came up. The rep walks into the next call with a clear focus.
Manager Coaching a Rep
A sales manager wants to coach a team member on a recorded call without listening to the whole thing. Running Call Coaching produces strengths, the highest-impact improvements, and a talk-dynamics read, each tied to a moment in the transcript. The manager can point to specific exchanges rather than offering vague encouragement.
Diagnosing a Stalled Deal
A rep senses a deal lost momentum on the last call but cannot pinpoint where. With a focus on where the conversation stalled, the skill traces the moment the customer disengaged and what preceded it, then suggests how to re-approach on the next call. The read stays honest about what the transcript can and cannot confirm.
Skill Definition
The raw markdown Claude uses when this skill is invoked.
---
name: call-coaching
description: Coach a rep on how they handled a specific call — discovery quality, objection handling, talk dynamics, and next-call focus. Name the call if you know it, or let the skill pull recent calls and identify the most likely candidate to confirm. Uses conversation_intelligence to read how the conversation actually went. Use when someone asks "how did I do on the Acme call", "coach me on my last discovery call", "where did I lose them", or wants actionable feedback before the next conversation. Analyzes one call at a time.
---
# Call Coaching
Give a rep specific, actionable feedback on a single call: what worked, what to improve, and what to focus on next time.
## Prerequisites
`browse_engagements` (to find the call) is free but requires an active calendar/meeting integration; `conversation_intelligence` (to analyze it) requires at least one connected meeting source and consumes AI credits. If the call has no transcript to analyze, say so rather than coaching from assumption.
## Input
Provided via `$ARGUMENTS`:
- **Which call** (optional) — an account and/or date. If omitted, the skill identifies the most likely recent call and confirms before analyzing.
- **Focus** (optional) — e.g. "discovery", "the pricing objection", "did I talk too much". Targets the coaching.
## Workflow
1. **Identify the call.** `browse_engagements` filters by date and by company/contact ID, not by call name, so resolve any named account or contact first via `search_companies` / `search_contacts`, then call `browse_engagements` (`engagementType: MEETINGS`, `sort: -chronological`) scoped to that ID and date window and pick the matching meeting from the results. If nothing was named, call `browse_engagements` for the user's recent meetings, propose the most likely candidate, and confirm it before spending credits. If more than one meeting plausibly matches, ask. Keep the chosen engagement ID.
2. **Analyze how it went.** Run `conversation_intelligence` scoped to that engagement ID. Ask how the rep handled discovery (did they uncover pain, budget, timeline, decision process), how objections were handled, what the customer's reactions and sentiment were, and where the conversation stalled or advanced. Keep the query scoped to this one call.
3. **Coach against good practice.** Assess the call against solid discovery and objection-handling fundamentals — open questions over pitching, listening over talking, surfacing next steps, addressing concerns directly. Ground every point in a specific moment from the call; cite what was said. Be candid and useful, not generic. If the transcript is too thin to judge something, say so rather than inventing a critique.
## Output Format
### Call coaching — [Call title, date]
**What went well** (2-3) — specific strengths, each tied to a moment in the call.
**What to improve** (2-3) — the highest-leverage changes, each with the moment that shows it and a concrete alternative ("when they raised price, you discounted; instead anchor on the value point from earlier").
**Talk dynamics** — a quick read on balance (who drove, listening vs pitching, questions asked) if the data supports it.
**Focus for the next call** — one or two things to do differently next time, tied to where this deal now stands.
### When there is no data
If the call cannot be found or has no transcript, tell the user and offer to coach from notes they provide, rather than fabricating an assessment.
Created by
Rowan Bailey
Senior Director, Product
Provided by
ZoomInfo ↗Capabilities
- Two to three specific strengths, each tied to a moment in the call
- Two to three highest-impact improvements with a concrete alternative
- Talk dynamics read on who drove and listening versus pitching
- Focus for the next call tied to where the deal now stands
- Optional focus input to target discovery, an objection, or talk time
- Honest fallback when the transcript is too thin to judge