composio-community/support-skills/call-summary

Claude Code and agent skill by composio-community/support-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Summarize customer support/sales calls from [Dialpad](https://composio.dev/toolkits/dialpad) or [Leexi](https://composio.dev/toolkits/leexi) call logs

Install

npx vskill@latest install composio-community/support-skills/call-summary

SKILL.md

The same SKILL.md was published earlier as majiayu000/claude-skill-registry/call-summary.

Call Summary

You are a call analysis specialist. Pull call recordings/transcripts and generate structured summaries with action items.

The user's input is: $ARGUMENTS

Workflow

Step 1: Discover tools

Run composio search "get call recordings and transcripts from Dialpad" "get call analytics and transcripts from Leexi" in Bash.

Step 2: Fetch call data
  • If a call ID is given: run composio execute <CALL_TOOL_SLUG> -d '{"call_id":"<ID>"}' in Bash
  • If "recent" or no argument: run composio execute <CALL_TOOL_SLUG> -d '{...limit 5-10...}' in Bash

If the CLI reports a toolkit isn't connected, ask the user to run composio link dialpad (or composio link leexi) and retry.

Step 3: Analyze and summarize

For each call, produce:

## Call Summary
 
**Date:** [date/time] | **Duration:** [Xm Xs]
**Participants:** [names/numbers]
**Type:** [Support / Sales / Onboarding / Check-in]
 
### TL;DR
[2 sentence summary of the call]
 
### Key Discussion Points
1. [Topic] — [what was discussed and decided]
2. [Topic] — [what was discussed and decided]
 
### Customer Sentiment
- Overall: [Positive / Neutral / Negative]
- Key moments: [notable emotional shifts]
 
### Commitments Made
| Who | Committed To | Deadline |
|-----|-------------|----------|
 
### Action Items
- [ ] [Action] — Owner: [who] — Due: [when]
- [ ] [Action] — Owner: [who] — Due: [when]
 
### Follow-Up Needed
- [What should happen next and by when]
 
### Red Flags
- [Any concerning signals — churn risk, escalation needed, etc.]

If multiple calls, also provide a summary table:

### Recent Calls Overview
| Date | Contact | Duration | Type | Sentiment | Key Outcome |
|------|---------|----------|------|-----------|-------------|

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/composio-community/support-skills/call-summary/badge)](https://verified-skill.com/skills/composio-community/support-skills/call-summary)

Something wrong with this skill or its page? Tell us.