Skip to content
Get packs

Review Rep Call Trends

Analyzes a sales rep's call recordings over time to show improvements, regressions and coaching actions.

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
4 files

What it does

This skill teaches an AI agent to review a sales or customer-facing representative's meeting call summaries across older and newer time periods, then produce an evidence-based readout of what got better, what got worse, and what stayed the same. It splits the last 90 days into three slices, compares the same behavior categories across them, and checks a few full calls to confirm patterns. It ends with three concrete coaching actions for the next two weeks. It is designed to read data from connected meeting transcript and file sources rather than run code, and it does not create trackers, send messages, or save files.

Great for

  • Sales managers who want objective, evidence-based coaching notes for a rep
  • Reps who want to see how their discovery, objection handling or next-step habits are changing
  • Enablement or coaching teams reviewing call quality over a quarter

Skip it if

  • Judging a rep's performance from sales outcomes or CRM data alone, because the skill requires call summaries or transcripts as evidence and treats outcomes as insufficient
  • Small samples of only a few calls, where the skill itself warns it will return only a limited readout; using it for formal performance decisions could be unfair to the rep
  • Reviewing calls without consent or outside the company's policies, since it pulls recordings and transcripts of other people's conversations

Try asking

  • “Review how my calls have changed over the last 90 days and give me coaching actions.”
  • “Compare Jordan Lee's discovery and objection handling in the older vs newer call sets I've uploaded.”
  • “Show me improvements, regressions and calls I should re-listen to for Sam Patel's demos this quarter.”
Step-by-step guide: how to use Review Rep Call TrendsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    review-rep-call-trends.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip review-rep-call-trends.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip review-rep-call-trends.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the rep's exact display name or email and pick a clear comparison basis (default 90 days or your own older/newer sets) so the agent does not guess.
  • Supply call summaries or transcripts directly if you do not have a live meeting transcript connection; trend claims need call evidence.
  • Treat the output as coaching input to verify by listening to the flagged calls, not as a final performance rating.

What's inside

  • agents/openai.yaml
  • references/request-schema.yaml
  • references/rubric.md
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.