transcript-analyzer
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.
Security Assessment
Detected risks:
About transcript-analyzer
The 'transcript-analyzer' skill is designed to help users analyze meeting transcripts, automatically extracting and categorizing crucial information such as decisions, action items, opinions, questions, and domain-specific terminology. This tool uses Cerebras AI with the Llama-3.3-70b model to quickly process transcript data and provide insights for better understanding and documentation of meetings. It simplifies the process of identifying key points and organizing information, which can be time-consuming if done manually.
FAQ
How do I analyze a transcript with the transcript-analyzer skill?
To analyze a transcript, use the command `npm run cli -- <transcript-file> -o <output.md> [options]` in the script directory. You can specify options like including the full transcript or excluding certain sections like the glossary.
What is required before using this skill for the first time?
Before using the skill, you must install the necessary dependencies by running `npm install` in the `~/.claude/skills/transcript-analyzer/scripts` directory.
Can I customize the glossary used by the transcript-analyzer?
Yes, you can customize the glossary by providing a custom JSON path with the `--glossary <path>` option. Additionally, you can disable glossary preloading with the `--skip-glossary` option.
What is the default chunk size used for transcript analysis?
The default chunk size for processing transcripts is 3000 tokens, but this can be modified using the `--chunk-size <num>` option.
Install transcript-analyzer
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
glebis/claude-skills