Skip to main content
Managers listen to a handful of calls per rep per month, so coaching runs on a sample. The patterns that actually move a rep’s number — how they handle a pricing objection across ten deals, whether they talk past the close, what the top rep does that the others don’t — live across every call, not the three a manager had time for. Rep Coaching From Real Conversations surfaces coaching moments with timestamps from every call, identifies patterns across deals, and turns them into specific, evidence-based feedback.

​
Data Sources

CategoryRequiredRecommended
Calls✓
CRM✓
Email✓
Starter (required only): coaching moments pulled from a rep’s call transcripts with timestamps, plus the patterns that repeat across their deals. Full (required + recommended): the same, plus deal outcomes from CRM and follow-up behavior from email — so you can connect a habit on calls to whether deals advance or stall. Same workflow, significantly more depth. See the Customer Context Graph for how each source feeds the analysis.

​
Choose your path

PathBest forOutput is delivered
Build in ClearskiesManagers whose daily surface is SlackTo Slack DMs or channels (today)
Build in Claude or ChatGPTManagers working in Claude or ChatGPT, or enablement testing before deployIn the Claude or ChatGPT conversation

​
Build in Clearskies

For managers whose daily surface is Slack. Deploy a command that pulls a coaching readout on any rep, anytime — moments, patterns, and feedback delivered to Slack, on demand.

​
The Workflow

In the Clearskies app, open the workflow builder and describe what you want in plain language: 
When a manager types /coach [rep] in Slack, analyze that rep's recent
calls in the Clearskies Context Graph. Surface specific coaching
moments with timestamps, identify behavior patterns that repeat across
their deals, compare against what top reps do differently, and draft
two or three pieces of specific feedback. Post the readout as a private
DM to the manager who ran the command.
The app configures the trigger (Slack slash command), the data pulled (your connected sources), and the destination (a private DM, since coaching is sensitive). Review and refine before deploying.

​
Deploy to Slack

Once deployed, a manager can type /coach Daniel in Slack and see this in a DM: 
Coaching Readout — Daniel
Generated for @manager · 4:05 PM · last 30 days, 11 calls

What's working
Strong discovery. Consistently surfaces the economic buyer early —
e.g. Acme call May 12, 00:04:30, "Who else signs off besides you?"
Top reps do this; Daniel does it reliably.

Patterns to coach
• Talks past the close. In 4 of 11 calls he keeps selling after the
  buyer signals agreement (Globex May 6, 00:31:10 — buyer says "this
  makes sense" and Daniel adds two more features).
• Pricing objection handled by discounting, not reframing. 3 calls.
  Top rep Priya reframes to scope instead (see her May 8 Acme call).

Suggested feedback
1. "When the buyer agrees, stop and ask for the next step." Use the
   Globex moment — he'll recognize it.
2. Pair him with Priya on the pricing reframe before his next eval.

The one thing
The talk-past-the-close habit is costing momentum. It's specific,
it's on tape, and it's fixable in one conversation.

​
Customize the rollout

  • Keep readouts private to managers, or open a shared enablement channel for team-level patterns
  • Tailor what’s surfaced (discovery, objection handling, next-step discipline, talk ratio)
  • Set the comparison baseline — your top performers, a defined methodology, or a custom rubric
  • Adjust cadence — on demand, weekly per rep, or after every recorded call

​
Build in Claude or ChatGPT

For managers working in Claude or ChatGPT, or enablement testing the workflow before rolling it out. Output appears in your conversation.

​
The Prompt

Open Claude or ChatGPT with the Clearskies MCP connected and paste this (or modify to your needs). Replace the rep’s name with your own. 
Using the Clearskies Context Graph, analyze Daniel's recent calls and
give me a coaching readout.

Cover:
- What he's doing well, with a specific timestamped example
- Patterns to coach, with the calls and moments they show up in
- How he compares to what our top reps do differently
- Two or three pieces of specific feedback I can give him
- The one thing most worth focusing on first

Ground every point in an actual moment. Be direct.
Claude or ChatGPT returns a readout structured like the Slack example above, generated from your data. Refine the prompt to fit how you coach.

​
Make it yours

  • Add Focus only on how he handles pricing objections to coach one skill at a time.
  • Add Draft this as feedback I can paste into our 1:1 doc to make it ready to deliver.

​
The Skill (Claude)

The clearskies:rep-coaching skill in the Clearskies plugin for Claude runs the same workflow on demand: it pulls a rep’s recent calls, surfaces coaching moments with timestamps, identifies behavior patterns, and drafts specific feedback — no manual listening required, all from your Context Graph.

​
Trigger phrases

  • “Coach [rep]”
  • “What should I work on with [rep]”
  • “Show me coaching moments from [rep]‘s calls”

​
Customize it for your team

  • Match the readout to the skills your team coaches on
  • Set the comparison baseline to your top performers or your methodology
  • Layer in 1:1-prep, ramp, or PIP framing depending on context
Want this packaged for your team? Reach out and we’ll help you customize the skill to your workflow.

​
The Plugin

Ready to make this part of your team’s workflow? We’ll set up the Clearskies plugin with you — Clearskies workflows, Claude skills, all tailored to how your team works. Book 15 minutes →

​
Next steps

  1. Sign in to Clearskies
  2. Connect your data sources
  3. Get your Clearskies MCP server and try with Claude or ChatGPT