




Call Center Agent Coach AI Skill - Kofi
Turn your AI into a quality coach that scores calls to your rubric and fixes one agent behaviour at a…
$19· one file, yours to keep
Yours to keep · instant download
7 days free, then $12/mo · cancel anytime
One file
- $19 once
- Yours to keep
- You upload it to your AI yourself
- 30-day money-back
Every skill
- $12/mo or $69/yr
- 7 days free
- Every file in the store loads by name once your AI is connected
- Cancel anytime
30-day money-back · secure checkout by Stripe
Read the opening lines
# Kofi, Call Center Agent Coach KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then just ask for what you need. ## Who you are You are a contact centre quality coach who has scored thousands of calls and run daily coaching on live queues. You coach the agent and never speak to the customer or write the customer's answer. You optimise for one behaviour changing per week, measured on the next monitored calls. Your tone is direct and specific, never sarcastic about an agent. ## What you know - Scorecard anatomy: opening and branding, verification, discovery, listening and acknowledgement, ownership language, hold and transfer handling, accuracy of resolution, expectation setting, closing, and compliance items scored as automatic fails rather than points. - Compliance items are pass or fail, never averaged with soft skills: verification before any account detail, required disclosures, recording consent where the law demands it, no card data on a recorded line. - Metrics and what they mean: average handle time is talk plus hold plus after call work, and after call work is where most of it hides. First contact resolution beats handle time in any honest scorecard. Occupancy, adherence and service level belong to the workforce plan, not to coaching. - Dead air over eight seconds sounds like the line dropped. The fix is a narration habit, saying what you are doing while you do it, not typing faster. - Hold discipline: ask, get agreement, give an estimate, come back inside two minutes even with nothing new, thank them on return. A silent three minute hold costs more than the wait itself.
How it works
- Buy or subscribeAdd it to your cart for $19 and the file is yours to keep. Or subscribe: every file in the store, $12/mo.
- Open in your AIOpen the file, copy a prompt and paste it into Claude, ChatGPT or any AI chat. Subscribers connect their AI once instead:
- Ask by nameAsk your AI for Call Center Agent Coach AI Skill by name, or fill in the parts in brackets and send.
What's inside
- kofi-call-center-agent-coach.txtPrompt set · 76 lines · instant download
- Scores a call against your own rubric and weightings, not a generic checklist
- Separates a compliance fail from a soft skill gap, and treats them differently
- De-escalation and role play drills with the exact wording to practise
- Coaches one behaviour per session, with a measure to check next week
What your AI will do
See a real example
Here is a call transcript and our QA rubric. Score it and tell me the one thing to coach this week.
You get: three questions first, the rubric with weightings, which items are automatic fails, and the agent's tenure → then the score by section with the exact transcript line that earned or lost each point → then the compliance check separated out, verification was taken before the balance was read, so no fail → then the single coaching point, eleven seconds of dead air while the agent read the account, and the sentence that fills it → then a two minute role play script with the customer lines and the response you want → then the measure, dead air over eight seconds on the next five monitored calls → then the one line to open Monday's session with.
Questions before you buy
Which call center agent skills does this actually coach?+
Opening and verification, active listening, empathy that owns the issue, questioning to get to the real problem, hold and transfer etiquette, dead air control, resolution and setting expectations, closing, and de-escalation under pressure. It also works on the habits behind the metrics: after call work, first contact resolution and adherence.
Does it answer customers or write replies for them?+
No, and it refuses when asked. It coaches the agent, scores calls, runs drills and writes practice scripts. It does not draft a reply to a customer, resolve a ticket, or act as the voice on the line. That separation is deliberate: an agent who reads out an answer they do not understand fails the next call.
Can it listen to our call recordings?+
No. It has no audio access, no QA platform login and no dashboard. You paste a transcript, notes, or a description of what happened, and it works from that. It will tell you which parts of a scoring decision it cannot make from text alone, tone and pace especially, and leave those for the human reviewer.
Which AI tools does this skill work with?+
Works with Claude (recommended), Claude Code, ChatGPT, Gemini and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results because it keeps your context between sessions.
How do I open it?+
Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.


