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 sanqi-cd/Sanqi-Skills --skill youtube-podcast-to-mdgit clone --depth 1 https://github.com/sanqi-cd/Sanqi-SkillsWrote 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/sanqi-cd/sanqi-skills/youtube-podcast-to-md)<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/youtube-podcast-to-md"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/youtube-podcast-to-md/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/sanqi-cd/sanqi-skills/youtube-podcast-to-md"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/youtube-podcast-to-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00098 | $0.02428 |
| Opus 5.5 | $0.00039 | $0.00971 |
| Sonnet 5.5 | $0.00020 | $0.00486 |
| Haiku 4.5 | $0.00010 | $0.00243 |
Grade C, and why
youtube-podcast-to-md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf -- "$TMP_DIR"' EXIT How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube 播客 → 中文 Markdown
概述
将 YouTube 播客视频的字幕提取，整理为高质量中文 Markdown 文档，默认针对英文播客优化；其他语言也可尽力处理。两种输出模式：
- 精简版（summary）：提取核心观点、关键数据、结构化摘要，过滤闲聊和重复表达
- 完整版（full）：高保真还原整个对话，保留对话结构、论述逻辑和信息完整性，经轻度书面化处理后呈现为自然流畅的中文对话
工作流（必须按顺序执行）
全局约定：
- 临时根目录默认使用
${YTP2MD_TMP_DIR:-/tmp/youtube-podcast-to-md/}，每次任务必须在其中创建独立运行目录 - 最终 Markdown 默认输出到
${YTP2MD_OUTPUT_DIR:-$PWD}；若用户想直接落到某个笔记库或知识库目录，请显式把YTP2MD_OUTPUT_DIR指向目标目录 - 任务结束后只清理本次独立运行目录，不删除用户指定的临时根目录
- 本技能可任意目录下执行，不依赖当前工作目录
- 所有命令使用
python3 yt-dlp可以直接在 PATH 中可用，或通过python3 -m yt_dlp可用；不要依赖某台机器上的固定 PATH- 运行脚本时，把
SKILL_DIR视为当前 skill 根目录（即包含本SKILL.md的目录）
Step 1：确认输入参数
从用户消息中提取：
- URL：YouTube 视频链接
- 模式：精简版 or 完整版；用户未指定时默认精简版，只有高保真要求明显影响成本或结果时再确认
Step 2：环境准备
SKILL_DIR="/absolute/path/to/youtube-podcast-to-md"
TMP_ROOT="${YTP2MD_TMP_DIR:-/tmp/youtube-podcast-to-md}"
OUTPUT_DIR="${YTP2MD_OUTPUT_DIR:-$PWD}"
mkdir -p "$TMP_ROOT" "$OUTPUT_DIR"
TMP_DIR="$(mktemp -d "$TMP_ROOT/run.XXXXXX")"
trap 'rm -rf -- "$TMP_DIR"' EXIT
python3 -m venv "$TMP_ROOT/.venv"
PYTHON="$TMP_ROOT/.venv/bin/python"
"$PYTHON" -m pip install --quiet -r "$SKILL_DIR/requirements.txt"
若需 Whisper 兜底，额外安装以下其一：
"$PYTHON" -m pip install --quiet -r "$SKILL_DIR/requirements-whisper.txt"
Whisper 还要求系统可调用 ffmpeg。安装失败时报告缺失依赖，不要静默退回不可靠结果。
Step 3：获取字幕
运行 "$PYTHON" "$SKILL_DIR/scripts/fetch_transcript.py" <URL> "$TMP_DIR"，脚本按优先级自动选择：
- YouTube 手动上传的英文字幕（质量最高）
- YouTube 自动生成的英文字幕
- YouTube 上其他可用字幕（自动适配）
- 若以上均不可用 → 运行
"$PYTHON" "$SKILL_DIR/scripts/fetch_with_whisper.py" <URL> "$TMP_DIR"使用 Whisper 离线转录
补充说明：
fetch_transcript.py会优先拿英文字幕；如果只有其他语言字幕，会继续返回该语言字幕fetch_with_whisper.py默认使用--language auto自动识别语言；若你明确只想按英文转录，可传--language en- Whisper 默认使用 CPU 上的
small模型；可按质量和设备条件传--model medium等，首次运行会下载模型。长视频先告知用户转录耗时和下载量。
中间文件（位于 "$TMP_DIR"）：
transcript_raw.txt— 原始字幕文本（含[TS:MM:SS]时间戳标记）transcript_meta.json— 视频元数据（标题、频道、时长、字幕来源等）
Step 4：字幕清洗与分块
What ships with it
11 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.
- agents/openai.yaml 313 B
- evals/evals.json 1.8 KB
- evals/trigger-evals.json 1.6 KB
- references/output_format.md 7.3 KB
- references/prompt_templates.md 8.5 KB
- requirements-whisper.txt 45 B
- requirements.txt 51 B
- scripts/clean_transcript.py 6.9 KB runs code
- scripts/fetch_transcript.py 9.1 KB runs code
- scripts/fetch_with_whisper.py 11 KB runs code
- scripts/validate_output.py 2.3 KB runs code
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.
- 28d ago Changed · +2 lines 41f1d5772dda
- 1mo ago First seen · 182 lines · 98 tokens per session scan C 86c2676bdd47
youtube-podcast-to-md is a skill published in the GitHub repository sanqi-cd/Sanqi-Skills (28 stars, last pushed 26d ago), licensed MIT. It adds 98 tokens to every session and 2,428 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
officecli-pptx
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.