Follow-Up Email from a Call Transcript
CreateSales
A customer follow-up email drafted from your call transcript, with the concerns raised, agreed action items, and next steps, ready for the rep to check and send.
This is the skill file version. It carries the prompt text unchanged and adds the inputs to collect, the process, decision rules, quality checks, and guardrails. The one-off prompt lives on its prompt page.
The file
---
name: email-from-transcript
description: >-
A customer follow-up email drafted from your call transcript, with the concerns raised, agreed action items, and next steps, ready for the rep to check and send.
Task type: Create. Built for Sales.
Use when the request sounds like "Follow-Up Email from a Call Transcript".
Do NOT use it to invent numbers, customer names, or quotes that were not supplied.
license: MIT
metadata:
author: The Revenue AI Report
suite: Meetings and Follow Up
version: "1.0"
source: https://www.therevenueaireport.com/prompts/email-from-transcript
---
# Follow-Up Email from a Call Transcript
A customer follow-up email drafted from your call transcript, with the concerns raised, agreed action items, and next steps, ready for the rep to check and send.
One job only: a customer follow-up email drafted from your call transcript, with the concerns raised, agreed action items, and next steps, ready for the rep to check and send. Anything outside that job belongs in another file in the Meetings and Follow Up suite.
## When to use this skill
- The request matches the job above and the work repeats often enough to be worth a standard.
- You have, or can ask for, the inputs listed below.
- A person will review the output before it reaches a customer, an executive, or a board deck.
## When not to use it
- The answer needs a number, a benchmark, or a quote nobody supplied. Ask for it instead of producing one.
- The task is a different job in the same suite. Open that file rather than stretching this one.
- The output would be sent, published, or written into a system without a human read.
## Inputs to collect first
- call transcript
Ask for anything missing before running. Do not fill a gap with a plausible guess.
## Process
1. Confirm the job, the audience, and the decision the output feeds.
2. Collect the inputs above. Name anything still missing out loud.
3. Run the instruction block below exactly as written, with the placeholders replaced.
4. Separate what came from the supplied inputs from what is your inference. Label the inference.
5. Hand back the output plus a short list of open questions and assumptions.
## Instruction block
Run this text with the placeholders filled in.
```text
You will be drafting an email to a customer based on a transcript of a call between the customer and our company. Here are the steps:
1. First, carefully read the call transcript provided below:
<call_transcript>
{$CALL_TRANSCRIPT}
</call_transcript>
2. Next, in the email draft, include a section summarizing the key issues raised by the customer during the call. Begin this section with the heading "Summary of Customer Issues:" followed by your summary written in paragraph form.
3. Then, include a section listing any action items that need to be taken to address the customer's issues, along with the person/role who will be responsible for each action item. Begin this section with the heading "Action Items with Owners:". List each action item on a new line in the format:
Action Item: [description of action item]
Owner: [person/role responsible]
4. Remember, do not use any bold text, bullet points, or numbered lists in the email body.
5. Write out the complete email draft inside <email> </email> tags, including the sections for summarizing issues and listing action items as described above.
When you have completed drafting the email according to these instructions, submit your response.
```
## Decision rules
- Supplied evidence beats inference. If the two disagree, say so and keep the evidence.
- Unknown is a valid answer. Write "unknown" rather than estimating.
- Keep one recommendation per output. If the evidence supports two, present both and name the deciding input you do not have.
- Match the reading level of a working operator. Short sentences. Explain any term the reader may not use daily.
## Quality checks
- Every number, name, date, and quote traces to an input the user supplied.
- No vendor claim is repeated as fact without naming the source.
- Assumptions are listed separately from findings.
- The output answers the original request and nothing else.
- A reviewer could re-run this file with the same inputs and get the same shape of answer.
## Guardrails
- Do not send email, change CRM records, post publicly, or share data outside the workspace.
- Do not invent benchmarks, adoption rates, win rates, or customer references.
- Flag anything that needs a human decision instead of deciding it.
## Source
- Prompt page: https://www.therevenueaireport.com/prompts/email-from-transcript
- Suite: https://www.therevenueaireport.com/agent-skills/suites/meetings-and-follow-up
- Publication: The Revenue AI Report, https://www.therevenueaireport.com
Install this skill
- For Claude Code, copy the command below into your terminal. It creates the skill folder and saves the file as SKILL.md.
- For another assistant that supports skills, download the file above and place it in a folder named
email-from-transcriptinside that assistant's skills directory. - Start a new conversation and ask for the job named on this page. Review the result before using it.
For the supporting files, download the full Meetings and Follow Up package too. The single-file command only installs SKILL.md.
mkdir -p "$HOME/.claude/skills/email-from-transcript" && curl -fL "https://www.therevenueaireport.com/agent-skills/prompt/email-from-transcript/SKILL.md" -o "$HOME/.claude/skills/email-from-transcript/SKILL.md"