transcript-analyzer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited transcript-analyzer (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- Adapted from github.com/glebis/claude-skills/transcript-analyzer (no LICENSE declared in source repo, personal use only — do not redistribute). Local adaptations by the author 2026-05-07: expanded YAML description with the user-specific triggers, Cerebras key acquisition note, pointer to local DaytradeWarrior transcript corpus. -->
Analyze meeting / podcast / interview / YouTube transcripts using Cerebras llama-3.3-70b to automatically extract and categorize:
cd ~/.claude/skills/transcript-analyzer/scripts && npm installSign up at https://cloud.cerebras.ai — there is a free tier with generous limits (this is what makes llama-3.3-70b extraction effectively free for personal use). Create a key in the dashboard, then put it in scripts/.env:
CEREBRAS_API_KEY=csk-...Reference doc: https://inference-docs.cerebras.ai/
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- <transcript-file> -o <output.md> [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) |
cd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.mdcd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.md --include-transcriptcd ~/.claude/skills/transcript-analyzer/scripts && npm run cli -- /path/to/meeting.md -o /path/to/analysis.md --no-glossarysed -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.mdExisting transcript corpora on this machine (point the CLI at any of these or your own paths):
C:\Users\A\Desktop\YouTube\... (point at the actual transcript files when invoking).C:\Users\A\Desktop\МИФ\_knowledge_bases\. Useful for opinion / decision extraction across long-form content.When running against the DaytradeWarrior corpus, prefer --no-glossary per-file then merge glossaries at the end (the default data/glossary.json is incremental).
The tool generates markdown with:
scripts/cli.ts — main CLI entry pointscripts/src/lib/extract-service.ts — AI processing logic using Cerebrasscripts/src/lib/markdown.ts — markdown output generationscripts/src/lib/term-utils.ts — term deduplication utilitiesscripts/src/lib/mockExtractor.ts — mock mode for offline testingscripts/src/lib/utils.ts — shared helpersscripts/src/types/index.ts — TypeScript type definitionsscripts/data/glossary.json — default incremental glossary storescripts/package.json, scripts/tsconfig.json — Node/TS configAdapted from https://github.com/glebis/claude-skills/tree/main/transcript-analyzer (no license declared — personal use only, do not redistribute).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.