Skip to main content
skill CX Codex

transcript-analyzer — Claude Code skill: setup and features

transcript-analyzer extracts decisions, action items, opinions, unresolved questions, and domain terms from meeting transcripts using Cerebras AI.

MIT 258 installs ★ 414 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add glebis/claude-skills --skill transcript-analyzer -a claude-code
Open on GitHub

What transcript-analyzer does

This skill parses raw meeting transcripts via the Cerebras API using the llama-3.3-70b model. Transcripts are split into chunks of 3000 characters by default, which you can adjust using --chunk-size. The parser classifies findings into explicit decisions, tasks assigned to people, unagreed opinions, pending questions, and terminology.

The output writes to a Markdown file with YAML frontmatter logging chunk metrics, token usage, and extraction counts. Each extraction includes the speaker name, source snippet, and confidence score. The tool can also cross-reference terms against a local JSON glossary.

The tool fails without a valid CEREBRAS_API_KEY in scripts/.env. You also need to run npm install in the scripts directory before running your first analysis.

What it helps with

  • extract action items and assignees from unformatted meeting notes
  • isolate agreed decisions from conversational debates
  • generate or update a technical glossary from discussion transcripts
  • collect open questions that were left unanswered in the meeting

Example prompts for the agent

  • Analyze meeting.md and save action items to output.md
  • Extract decisions and glossary terms from call-transcript.txt
  • Run transcript analysis on notes.md with glossary generation disabled

How to install transcript-analyzer

1Skills CLI (Vercel)

npx skills add glebis/claude-skills --skill transcript-analyzer -a claude-code

2Manually: put the files in place

~/.claude/skills/transcript-analyzer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/transcript-analyzer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about transcript-analyzer

How to install transcript-analyzer in Claude Code?

Run npx skills add glebis/claude-skills --skill transcript-analyzer -a claude-code in your terminal.

What setup is required before analyzing transcripts?

Go to ~/.claude/skills/transcript-analyzer/scripts, run npm install, and add your CEREBRAS_API_KEY to scripts/.env.

Which model powers the transcript analysis?

The tool uses llama-3.3-70b served through Cerebras AI.

Source text

SKILL.md · MIT
---
name: transcript-analyzer
description: This skill analyzes meeting transcripts to extract decisions, action items, opinions, questions, and terminology using Cerebras AI (llama-3.3-70b). Use this skill when the user asks to analyze a transcript, extract action items from meetings, find decisions in conversations, build glossaries from discussions, or summarize key points from recorded meetings.
---

# Transcript Analyzer

## Overview

Analyze meeting transcripts using AI to automatically extract and categorize:
- **Decisions** - Explicit agreements or choices made
- **Action Items** - Tasks assigned to people
- **Opinions** - Viewpoints expressed but not agreed upon
- **Questions** - Unresolved questions raised
- **Terms** - Domain-specific terminology for glossary

## Prerequisites

Before first use, install dependencies:

```bash
cd ~/.claude/skills/transcript-analyzer/scripts && npm install
```

## Usage

To analyze a transcript:

```bash
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- <transcript-file> -o <output.md> [options]
```

### Options

| Option | Description |
|--------|-------------|
| `<file>` | Transcript file to analyze (first positional arg) |
| `-o, --output <path>` | Write markdown to file instead of stdout |
| `--include-transcript` | Include full transcript in output [default: off] |
| `--no-extractions` | Exclude extractions section |
| `--no-glossary` | Exclude glossary section |
| `--glossary <path>` | Custom glossary JSON path |
| `--skip-glossary` | Don't preload glossary terms |
| `--max-terms <num>` | Limit glossary suggestions |
| `--chunk-size <num>` | Override chunk size (default: 3000) |

## Examples

### Basic Analysis

```bash
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.md
```

### Include Original Transcript

```bash
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.md --include-transcript
```

### Extractions Only (No Glossary)

```bash
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.md --no-glossary
```

### Analyze Specific Section

To analyze only part of a transcript, extract the section first:

```bash
sed -n '50,100p' /path/to/meeting.md > /tmp/section.md
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /tmp/section.md -o /path/to/section-analysis.md
```

## Output Format

The tool generates markdown with:

1. **YAML Frontmatter** - Processing metadata:
   - chunks processed
   - extractions count by type
   - new terms discovered
   - model used (llama-3.3-70b via Cerebras)
   - token usage (input/output/total)

2. **Extractions** - Categorized findings with confidence scores:
   - Each extraction includes speaker (if identified), source snippet, and related terms

3. **Glossary** - Approved terms from existing glossary + suggested new terms with definitions

## Configuration

The skill uses Cerebras API with the key stored in `scripts/.env`:

```
CEREBRAS_API_KEY=<your-key>
```

## Scripts

- `scripts/cli.ts` - Main CLI entry point
- `scripts/src/lib/extract-service.ts` - AI processing logic using Cerebras
- `scripts/src/lib/markdown.ts` - Markdown output generation
- `scripts/src/lib/term-utils.ts` - Term deduplication utilities
- `scripts/src/lib/mockExtractor.ts` - Mock mode for testing
- `scripts/src/types/index.ts` - TypeScript type definitions
- `scripts/data/glossary.json` - Default glossary storage

© glebis · MIT · glebis/claude-skills

Similar skills

All skills for Notes, tasks and projects →

From the same set51

The whole set →
doctorg doctorg is a Claude Code skill that answers health, nutrition, training and sleep questions by checking trusted sources and grading the strength of evidence for each claim. CX Codex +1 265installs tdd tdd runs test-driven development cycles with strict context separation across subagents. Useful for writing clean features and reproducing bugs. CX Codex +1 262installs youtube-transcript The youtube-transcript skill pulls subtitles and video metadata from YouTube, saves them as Markdown with YAML frontmatter into an Obsidian vault. CX Codex +1 258installs gmail Skill for searching Gmail messages via API with filters for sender, date, status and attachments. Works on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. CX Codex +1 258installs zoom Skill to create, update, and list Zoom meetings, and access cloud recordings via Zoom API. Search recordings with transcripts, summaries, and download links. CX Codex +1 252installs fathom Skill to retrieve meetings, transcripts, AI summaries, and action items directly from Fathom API. Use it to sync meeting recordings and transcripts into your coding workflow. CX Codex +1 249installs github-gist A skill to quickly publish files and notes as GitHub Gist. Use it when you need to share code, create a shareable snippet link, or upload markdown without extra steps. CX Codex +1 246installs balanced Skill for multi-perspective analysis: surfaces merits, challenges logic, suggests alternatives. Triggers on /balanced or requests for honest feedback. CX Codex +1 243installs

Project sponsors

Companies that keep this analytics open