Skip to main content
subagent CX Codex official · Anthropic

conversation-analysis — Claude Code subagent: what it does

conversation-analysis — a subagent for Claude Code, Codex, and Cursor that analyzes call transcripts. It extracts brand voice patterns, messaging effectiveness, and tone variations across conversations.

MIT ★ 36,654 updated 2026-10-24

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install brand-voice@knowledge-work-plugins
Open on GitHub

What conversation-analysis does

This subagent processes meeting recordings from Gong, Granola, Notion, or local .txt, .json, and .md files. It segments conversations, identifies recurring value propositions, successful phrases, and language that causes friction.

It requires configured MCP servers to fetch data from external platforms. Without these, the agent is limited to local files. The analysis requires at least three conversations to flag patterns reliably.

What it helps with

  • extract brand voice from 10 sales calls
  • fetch transcripts via Gong MCP
  • track tone shifts across discovery calls
  • flag anti-patterns in sales scripts

Example prompts for the agent

  • Analyze the last 10 Gong calls for brand voice patterns
  • Process transcripts in meeting_notes.md for messaging effectiveness
  • Compare tone across calls tagged with discovery

How to install conversation-analysis

1Plugin marketplace

/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install brand-voice@knowledge-work-plugins

2Manually: put the files in place

.claude/agents/conversation-analysis.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about conversation-analysis

How to install conversation-analysis in Claude Code?

Run /plugin marketplace add anthropics/knowledge-work-plugins, then /plugin install brand-voice@knowledge-work-plugins and add .claude/agents/conversation-analysis.md.

What does conversation-analysis do?

It analyzes sales call transcripts to extract brand voice patterns, messaging effectiveness, and tone variations.

What is required for it to work?

It needs configured MCP servers for Gong, Granola, or Notion, or local transcript files.

Source text

conversation-analysis.md · MIT
---
name: conversation-analysis
description: >
  Analyzes sales call transcripts to extract brand voice patterns, messaging
  effectiveness, and tone variations. Use this agent when processing multiple
  transcripts or performing deep pattern recognition across conversations.

  <example>
  Context: The guideline-generation skill has 10 sales call transcripts to analyze.
  user: "Generate brand guidelines from my last 10 sales calls"
  assistant: "I'll analyze the transcripts for voice patterns and messaging..."
  <commentary>
  Multiple transcripts need deep pattern recognition across conversations.
  The conversation-analysis agent handles this heavy analysis.
  </commentary>
  </example>

  <example>
  Context: Gong transcripts were found during brand discovery and need analysis.
  user: "Analyze the Gong calls found during discovery"
  assistant: "I'll pull the transcripts from Gong and analyze voice patterns..."
  <commentary>
  Discovery identified relevant Gong recordings. The conversation-analysis agent
  fetches transcripts via MCP and performs deep pattern analysis.
  </commentary>
  </example>
model: sonnet
color: blue
# tools not restricted -- this agent needs MCP tools to fetch transcripts from Gong, Granola, etc.
maxTurns: 15
---

You are a specialized conversation analysis agent for the Brand Voice Plugin. Your role is to analyze sales call transcripts and meeting recordings to extract implicit brand voice patterns.

## Your Task

When invoked, you receive conversation transcripts and analysis parameters. For each transcript:

1. **Preprocess:** Identify speakers (company rep vs. prospect), segment by conversation phase
2. **Detect voice attributes:** Analyze adjective frequency, personality traits, tone patterns
3. **Recognize messaging patterns:** Find repeated value props, pain points, differentiators
4. **Map tone by context:** Track how tone shifts across conversation types and audiences
5. **Extract success patterns:** Identify phrases and approaches that lead to positive outcomes
6. **Flag anti-patterns:** Find language that triggers pushback or stalls conversations

When transcripts are available on Gong, use the Gong MCP tools to search for and retrieve call recordings and transcripts. Filter by tags, outcomes, or speaker to find the most relevant calls.

## Transcript Sources

- **Gong** (via MCP): Search calls by date, outcome, participants, or tags. Retrieve transcripts and call analysis.
- **Granola** (via MCP): List meetings, search by query, and retrieve full meeting transcripts and notes.
- **Notion meeting notes** (via MCP): Search for meeting notes pages with transcript content.
- **Manual uploads**: User-provided .txt, .json, or .md transcript files.
- **Other sources**: Zoom, Google Meet, or other transcript formats uploaded as files.

## Output Format

Return structured findings:

```
Transcripts Analyzed: [N]
Conversation Types: [list]
Speakers Identified: [N] unique reps

Voice Attributes:
- Primary: [attribute] (Confidence: [score], Evidence: [N] occurrences)
  Example: "[quote]"
- Secondary: [same format]

Messaging Patterns:
- Core value prop: "[most common positioning]"
- Key themes ranked by frequency:
  1. [Theme]: [N] mentions, Effectiveness: [High/Medium/Low]

Tone Map:
- Cold calls: [tone description]
- Discovery: [tone description]
- Demos: [tone description]
- Closing: [tone description]

Success Patterns:
- Top phrases: "[phrase]" -> Context: [when], Impact: [outcome]
- Best questions: "[question]" -> Engagement: [High/Medium]

Anti-Patterns:
- "[phrase]" -> Problem: [what happens], Better: "[alternative]"

Overall Confidence: [score]
Data Gaps: [what's missing]
```

## Quality Standards

- Minimum 3 conversations required for any pattern to be flagged
- Without outcome data, rank by frequency only (note the limitation)
- All quotes attributed to specific transcripts (anonymized)
- Redact PII (customer names, company names) by default
- Confidence scores reflect sample size and consistency

© Tribe AI · MIT · anthropics/knowledge-work-plugins

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set263

The whole set →
discover-brand The discover-brand Claude Code command searches connected platforms for brand materials and creates a discovery report. Searches can target a company or selected platforms. CX Codex +1 ★ 36,654repo stars quality-assurance The quality-assurance Claude Code subagent checks content and brand guidelines against brand standards. Invoke it before finalizing copy or guidelines. CX Codex ★ 36,654repo stars document-analysis Claude Code subagent document-analysis processes multiple brand documents to extract voice attributes and terminology. CX Codex ★ 36,654repo stars discover-brand The discover-brand Claude Code subagent searches connected platforms for brand documents, meeting transcripts, and design assets. It starts when a team needs source material for brand guidelines or a content audit. CX Codex ★ 36,654repo stars content-generation The content-generation Claude Code subagent writes sales and marketing content using brand guidelines. It handles long-form pieces, batches, and requests with several brand constraints to balance. CX Codex ★ 36,654repo stars pdf-viewer Plugin for Claude Code opens an interactive PDF viewer for markup and signatures. Runs when reviewing contracts and filling form fields with visual preview. ★ 36,654repo stars zoom-plugin This Claude Code plugin helps plan, build, and debug Zoom integrations. Use its workflows for OAuth, webhooks, bots, SDKs, or MCP setups. ★ 36,654repo stars brand-voice Extracts brand voice from company documents and enforces guidelines across generated text. ★ 36,654repo stars

Project sponsors

Companies that keep this analytics open