
Transcript Analyzer
Extracts decisions, action items, opinions, questions, and terminology from meeting transcripts using Cerebras AI's llama-3.3-70b model. It chunks large transcripts, processes them through the API, and outputs structured markdown with confidence scores for each extraction. The glossary feature is interesting: it can preload existing terms and suggest new ones with definitions as it encounters domain-specific language. You'll need to install npm dependencies and add your Cerebras API key first. Output includes token usage metrics in YAML frontmatter, which is helpful for tracking costs. Good for teams that record meetings and need consistent extraction without manually reading through everything.
- skills.sh installs
- 257
- GitHub stars
- 412
- last updated
- Aug 21, 2026
Install
$ npx -y skills add glebis/claude-skills --skill transcript-analyzer --agent claude-codeInstalls into .claude/skills of the current project.
Files
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:
cd ~/.claude/skills/transcript-analyzer/scripts && npm install
Usage
To analyze a transcript:
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- <transcript-file> -o <output.md> [options]
Options
Sponsors
Details
- Repository
- github.com/glebis/claude-skills
- Category
- DevOps & CI/CD
- First seen
- Jun 3, 2026