Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chubbyguan/chubbyskills --skill podcast-transcribegit clone --depth 1 https://github.com/chubbyguan/chubbyskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chubbyguan/chubbyskills/podcast-transcribe)<a href="https://agentmods.dev/skills/chubbyguan/chubbyskills/podcast-transcribe"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/podcast-transcribe/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chubbyguan/chubbyskills/podcast-transcribe"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/podcast-transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 32 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00788 |
| Opus 5 | $0.00020 | $0.00394 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade B, and why
podcast-transcribe scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# Ubuntu: sudo apt install ffmpeg What it actually says
播客转录 Skill
将播客音频下载并转录为文字，存为 Markdown 文件。支持小宇宙、喜马拉雅等平台。
环境要求
# Python 3.9+
python -m venv .venv
source .venv/bin/activate
# 依赖
pip install faster-whisper
# 系统依赖
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
使用方法
单集转录
python scripts/transcribe.py "https://www.xiaoyuzhoufm.com/episode/xxxxx"
批量转录（RSS）
python scripts/batch_transcribe.py --rss-url "http://www.ximalaya.com/album/xxxxx.xml" --count 10
流程
Step 1: 下载音频
支持多种来源：
- 小宇宙单集链接（自动从页面提取音频 URL）
- 喜马拉雅链接
- 直接音频 URL（.mp3/.m4a/.wav）
- RSS feed 中的音频链接
注意：小宇宙/喜马拉雅等平台会从页面 HTML 中自动解析 og:audio、<audio> 标签或内嵌 JSON 获取真实音频地址，无需手动提取。
Step 2: faster-whisper 转录
from faster_whisper import WhisperModel
model = WhisperModel('small', device='cpu', compute_type='int8')
segments, info = model.transcribe(
audio_path,
language='zh',
beam_size=5,
vad_filter=True,
)
Step 3: 生成 Markdown
自动创建带 frontmatter 的 Markdown 文件。
性能数据
| 模型 | 速度 (CPU) | 中文准确率 |
|---|---|---|
| faster-whisper tiny | ~149s/1h | 一般 |
| faster-whisper small | ~10min/h | 良好 (~85-90%) |
| faster-whisper large-v3 | ~30-60min/h | 最佳 |
已知限制
- CPU 推理较慢，长播客需要较长时间
- 中文准确率约 85-90%，需要人工校对
- 首次运行会下载模型（small: ~461MB）
- 不支持说话人分离
参考项目
- SYSTRAN/faster-whisper - Whisper 的 CTranslate2 实现
- OpenAI Whisper - 原始 Whisper 模型
⚖️ 合规声明
仅供个人学习与研究使用。请遵守目标平台的服务条款（ToS）与 robots 规则，控制请求频率，不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 102 lines · 41 tokens per session scan B cc35a5097174
podcast-transcribe is a skill published in the GitHub repository chubbyguan/chubbyskills (667 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 788 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
audio-transcriber
Speech-to-text transcription using Whisper API or local engine.
faster-whisper
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.