Agent skill · writing content · anthropics

call-summary

Process call notes or a transcript — extract action items, draft follow-up email, generate internal summary. Use when pasting rough notes or a transcript after a discovery, demo, or negotiation call, drafting a customer follow-up, logging the activity for your CRM, or capturing objections and next steps for your team.

Why this skill is useful

Provides structured templates for summarizing calls and drafting follow-up emails that the AI wouldn't reliably generate on its own.

What it needs

About 3k tokens when loaded. Last updated 2026-08-07. 23,345 stars on the source repository.

What this skill does

/call-summary If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Process call notes or a transcript to extract action items, draft follow-up communications, and update records. Usage Process these call notes: $ARGUMENTS If a file is referenced: @$1 --- How It Works --- What I Need From You Option 1: Paste your notes Just paste whatever you have — bullet points, rough notes, stream of consciousness. I'll structure it. Option 2: Paste a transcript If you have a full transcript from your video conferencing tool (e.g. Zoom, Teams) or conversation intelligence tool (e.g. Gong, Fireflies), paste it. I'll extract the key moments. Option 3: Describe the call Tell me what happened: "Had a discovery call with Acme Corp. Met with their VP Eng and CTO. They're evaluating us vs Competitor X. Main concern is integration timeline." --- Output Internal Summary Customer Follow-Up Email --- Email Style Guidelines When drafting customer-facing emails: 1. Be concise but informative — Get to the point quickly. Customers are busy. 2. No markdown formatting — Don't use asterisks, bold, or other markdown syntax. Write in plain text that looks natural in any email client. 3. Use simple structure — Short paragraphs, line breaks between sections. No headers or bullet formatting unless the customer's email client will render it. 4. Keep it scannable — If listing items, use plain dashes or numbers, not fancy formatting. Good: Bad: --- If Connectors Available Transcripts connected (e.g. Gong, Fireflies): I'll search for the call automatically Pull the full transcript Extract key moments flagged by the platform CRM connected: I'll offer to update the opportunity stage Log the call as an activity Create tasks for action items Update next steps field Email connected: I'll offer to create a draft in ~~email Or send directly if you approve --- Tips 1. More detail = better output — Even rough notes help. "They seemed concerned about X" is useful context. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills anthropics/call-summary

View the source on GitHub

Browse the @skills marketplace