← All skills
podcast-transcript-fetcher
57 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.
By Varnan-Tech/opendirectory (GitHub) · media · 705 stars · scanned at commit caac7cd
Use when fetching, searching, or analyzing transcripts from Lenny's Podcast, Dwarkesh Podcast, Cheeky Pint, 20VC, or A16z Podcast. Tier 2 (RSS+Groq Whisper) is the recommended approach -- fast, free, and most reliable. Also use when asked to "get transcript", "find episode", "summarize podcast", or "search podcast content". Do not use for general web scraping or non-podcast audio transcription.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 17 places.
Show 14 more
- skills/podcast-transcript-fetcher/README.md, line 103
| Local faster-whisper | $0 (compute) | ~1.5x realtime | 2.7% WER | `pip install faster-whisper` | Offline alternative | - skills/podcast-transcript-fetcher/README.md, line 111
- macOS: `brew install ffmpeg` - skills/podcast-transcript-fetcher/README.md, line 112
- Linux: `apt install ffmpeg` - skills/podcast-transcript-fetcher/SKILL.md, line 49
pip install requests - skills/podcast-transcript-fetcher/SKILL.md, line 52
pip install groq - skills/podcast-transcript-fetcher/SKILL.md, line 56
pip install faster-whisper - skills/podcast-transcript-fetcher/SKILL.md, line 178
| Audio > 25 MB for Groq | Install ffmpeg: `winget install ffmpeg` (Windows) or `brew install ffmpeg` (macOS) | - skills/podcast-transcript-fetcher/references/podcasts.md, line 174
pip install faster-whisper - skills/podcast-transcript-fetcher/references/podcasts.md, line 186
pip install groq - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 993
print(f" [WARN] No PDF parser installed. pip install PyPDF2 or pdfminer.six") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 1108
print(" Cloud (recommended): pip install groq && export GROQ_API_KEY=...") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 1109
print(" Local: pip install faster-whisper") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 1203
print(" [ERROR] GROQ_API_KEY is not set. Export GROQ_API_KEY or use local Whisper (pip install faster-whisper).") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 1232
print(" Install: pip install faster-whisper")
Runs commands on your computer
The author does not mention this.
Found in 3 places.
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.
Found in 26 places.
Show 17 more
- skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 249
resp = urllib.request.urlopen(req, timeout=30) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 671
req = urllib.request.Request( - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 674
with urllib.request.urlopen(req, timeout=300) as resp: - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 725
req = urllib.request.Request( - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 729
raw = urllib.request.urlopen(req, timeout=30).read() - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 753
req = urllib.request.Request(trans_url, headers={"User-Agent": "Mozilla/5.0"}) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 754
content = urllib.request.urlopen(req, timeout=30).read().decode("utf-8", errors="replace") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 781
req = urllib.request.Request(api_url, headers={"User-Agent": "Mozilla/5.0", "Accept": "application/json"}) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 782
resp = urllib.request.urlopen(req, timeout=15) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 825
req = urllib.request.Request( - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 829
html_content = urllib.request.urlopen(req, timeout=30).read().decode("utf-8", errors="replace") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 877
req = urllib.request.Request(dl_url, headers={"User-Agent": "Mozilla/5.0"}) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 878
resp = urllib.request.urlopen(req, timeout=30) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 905
req = urllib.request.Request(raw_url, headers={"User-Agent": "Mozilla/5.0"}) - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 906
content = urllib.request.urlopen(req, timeout=15).read().decode("utf-8", errors="replace") - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 937
req = urllib.request.Request( - skills/podcast-transcript-fetcher/scripts/get_transcript.py, line 941
html_content = urllib.request.urlopen(req, timeout=30).read().decode("utf-8", errors="replace")
and 6 more places
Reads your saved credentials, such as SSH keys or .env files
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (media) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'podcast-transcript-fetcher' ] || [ -L ~/.agents/skills/'podcast-transcript-fetcher' ]; then echo 'A skill folder named podcast-transcript-fetcher already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Varnan-Tech/opendirectory' "$d" && git -C "$d" checkout --quiet 'caac7cda5621e289591e4e74b400e66ac72ad25b' -- 'skills/podcast-transcript-fetcher' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/podcast-transcript-fetcher' ~/.agents/skills/'podcast-transcript-fetcher' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'podcast-transcript-fetcher' ~/.claude/skills/'podcast-transcript-fetcher' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for Varnan-Tech/opendirectory shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Varnan-Tech/opendirectory/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | caac7cd | 57 |
| 2026-11-07 | caac7cd | 57 |