AI Call QA Scorer

Name: AI Call QA Scorer
Brand: KissMySkills
Price: 7.0 USD
Availability: InStock

AI Call QA Scorer

Turn your AI into a consistent call QA analyst that scores every call with quoted evidence, calibration and trends.

$7.00 ce skill un seul paiement à vous pour toujours

Pack skill complet téléchargement immédiatai-call-qa-scorer.md

Unlimited

Get this and 2,500+ more with Unlimited $9/mois

Celui-ci et 2,500+ autres, dans votre IA

AI CRM included

Ce skill$7

Unlimited$9/mois

See Unlimited · $9/mois → or try every skill free for 7 days, no card

Payez une fois, gardez-le pour toujoursTéléchargement immédiatSatisfait ou remboursé 30 jours

As featured onProduct Hunt Fazier KittyLaunch

Works with

Secure checkout by Shopify

Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.

Ask it something hard.

📎 ai-call-qa-scorer.md LOADED ✓

Here are 40 Five9 transcripts from last week's billing queue and our QA form. Score them, flag any compliance failures, and tell me the top 3 things costing us points.

CLAUDE · WITH THIS SKILL You get: rubric locked with assumptions -> compliance table for C1-C5 with quoted evidence -> per-call scorecards with Met/Partial/Not met and confidence -> batch summary with pass rate and compliance fail rate -> agent and team trends -> top failure drivers ranked by points lost -> calibration sheet versus your supervisors -> prioritized human review list -> one coaching point per agent.

Ou tous les skills, directement dans votre IA.

0:33 · sans son

Les 2,500+ avec Unlimited · $9/mois →

Des questions avant d’acheter ? Une personne répond, souvent le jour même : hello@kissmyskills.com

// the file itself

Read it before you buy it.

The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.

// le skill qui fait tourner votre IA

You are a contact center quality lead who scores calls on evidence, not impressions. You have been activated to score this batch of transcripts against one locked rubric, separate compliance auto-fails from soft skills, and tell supervisors exactly which calls and behaviors need attention.

You work only on what the user pastes or uploads: transcripts (TXT, VTT, SRT, JSON, CSV), call metadata exports and their existing QA form. You do not connect to Gong, Talkdesk, Five9, Genesys or any other platform, you never listen to audio, and you never send scores, emails or coaching notes to anyone. You produce a document the QA team reviews and uses. · A QA analyst or team lead has 10 to 200 call transcripts and needs them scored against the same rubric in one consistent pass. · The team has no written QA form, or an old one with vague items like "was professional", and needs a weighted, behavior-based rubric. · Compliance needs a fast sweep for auto-fail events: card numbers read aloud on a recorded line, skipped identity verification, missing mandatory disclosures, no recording notice. · Supervisors disagree on scores and need a calibration sheet that shows where and why. · A manager wants agent-level and team-level trends and the three to five behaviors that cost the most points. · Real-time monitoring or live agent assist. This is not speech analytics software; it scores finished transcripts after the fact. · Judging tone, pace, dead air, hold music or interruptions that are not visible in the text. It can flag them; it cannot hear them. · HR decisions. Scores support coaching and calibration; they are not grounds for discipline without a human review of the recording. · Coaching one agent through a behavior change with role plays - see the coach below. · Answering customer tickets or chats - see the customer service agent below. This is a focused measurement workflow: many calls, one rubric, evidence for every score, calibration and trends. · Kofi - Call Center Agent Coach AI Skill (/products/kofi-call-center-agent-coach) coaches one agent on one behavior per session with role plays and practice scripts. This QA scorer is the measurement layer that tells you which behavior to coach and for whom. Every per-agent section ends with a "Top coaching point" you can hand straight to the coach. · AI Agent for Customer Service (/products/ai-agent-for-customer-service) answers first-line tickets from your knowledge base. It does not score calls or agents.

175 lignes · .md · telechargement immediat

// what's inside

Que contient cette compétence ?

Every score backed by a quoted transcript line
Compliance auto-fails kept apart from soft skills
Agent trends, failure drivers and calibration sheet
Low-confidence audio items sent to human review

QA analysts, team leads and contact center managers who need consistent call center quality assurance across many calls.

// two ways to get it

Buy this file, or open the whole library.

Buy once

This skill as a file

$7 one payment, yours forever

Download right after checkout, keep it for good
Paste it into ChatGPT, Claude, Gemini or any AI chat, free plans included
30-day money-back guarantee

Unlimited Access

Every skill, prompt and agent, inside your chat

$9/mo cancel anytime, or $59 a year

All 2,500+ files in the library, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
Works on every Claude plan, free included · 30-day money-back guarantee on the first charge

See Unlimited Access →

Subscribers can still buy single files and keep them after they cancel.

Works with

Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.

// ask your assistant

Or let your AI set up this skill for you.

Go to kissmyskills.com/pages/for-ai-agents and set up the "AI Call QA Scorer" skill (handle: ai-call-qa-scorer) for me

Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →

What you're actually buying

AI Call QA Scorer scores a batch of call center transcripts against your QA rubric, or builds a weighted rubric if you have none, and quotes the exact transcript line behind every score. Compliance auto-fails such as card numbers read on a recorded line, skipped identity verification, missing disclosures and recording consent are kept separate from soft skills, and anything that depends on tone or pace is flagged for audio review instead of guessed.

It is built for QA analysts, team leads and contact center managers who need consistent call center quality assurance without scoring every call by hand. Paste or upload transcripts, lock the rubric, and get per-call scorecards, a batch summary, agent and team trends, top failure drivers, a supervisor calibration sheet and a list of calls a human must review. It works inside Claude or ChatGPT as a skill file and does not connect to your phone system, contact center platform or call recordings; it is not real-time speech analytics and cannot hear audio. Where Kofi - Call Center Agent Coach AI Skill coaches one agent on one behavior and AI Agent for Customer Service answers tickets, this skill is the measurement layer that tells you what to coach.

Turn a stack of transcripts into an evidence-backed call QA scorecard with calibration and trends your supervisors can act on the same day.

Compatible with: transcripts exported from Gong, Talkdesk, Five9, Genesys Cloud, Aircall, Zoom Phone and Dialpad, plus TXT, VTT, SRT, JSON or CSV files and your existing QA form.

Does it listen to the recordings? No. It scores text transcripts and marks tone, pace and silence items as low confidence for a human to check with the audio.
We have no QA form. Can it still score? Yes. It builds a weighted rubric covering opening and verification, discovery, accuracy, ownership, hold and transfer, resolution, closing and empathy, plus compliance gates.
How does it handle compliance? PCI card data, verification, disclosures and recording consent are binary pass or fail gates; a confirmed fail sets the call to zero and sends it to human review.
Can it help with calibration? Yes. Give it your supervisors' scores for the same calls and it shows item-level spreads, likely causes and rubric wording fixes.

// installation Moins de 2 minutes

Quatre étapes. N’importe quel chat AI.

01
Télécharger le fichier
Après le paiement, le lien de téléchargement arrive dans votre boîte de réception. Enregistrez le fichier où vous voulez sur votre appareil.
02
Ouvrez votre conversation AI
Claude, ChatGPT, Gemini, Grok ou Copilot — celui que vous utilisez déjà.
03
Collez le contenu du fichier
Insérez-le dans le prompt système, les instructions du projet ou le champ des instructions personnalisées.
04
Commencez à travailler
Votre AI est maintenant configurée comme spécialiste. Posez-lui n’importe quelle question relevant de son domaine.

Aucune connaissance technique requise.

Avec Unlimited, rien à télécharger. Connectez votre IA une fois, puis demandez n’importe quel skill par son nom.

Guide d’installation → Unlimited · $9/mois →

// faq

Questions concernant ce produit

What does AI Call QA Scorer do?+

It scores a batch of call transcripts against your QA rubric, or a weighted default rubric, quotes the transcript line behind every score, separates compliance auto-fails from soft skills, and produces per-call scorecards, a batch summary, agent and team trends, top failure drivers, a calibration sheet and a human review list.

Is this real-time contact center AI or speech analytics software?+

No. It is a skill file that runs inside Claude or ChatGPT and scores transcripts you paste or upload after the call. It does not connect to your phone system, cannot hear audio and flags tone or pace items for a human to check.

How is it different from Kofi - Call Center Agent Coach AI Skill?+

Kofi coaches one agent on one behavior per session with role plays. AI Call QA Scorer measures many calls consistently, with calibration and trends, and hands each agent's top coaching point to the coach.

Which transcript formats does it accept?+

Pasted text or TXT, VTT, SRT, JSON and CSV exports from tools such as Gong, Talkdesk, Five9, Genesys, Aircall, Zoom and Dialpad, as long as speakers are labelled.