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 redfox-data/redfox-community-dsh --skill youtube-digestgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/youtube-digest)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/youtube-digest"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/youtube-digest/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/redfox-data/redfox-community-dsh/youtube-digest"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/youtube-digest.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 | $0.00127 | $0.02679 |
| Opus 5 | $0.00063 | $0.01340 |
| Sonnet 5 | $0.00025 | $0.00536 |
| Haiku 4.5 | $0.00013 | $0.00268 |
Grade A, and why
youtube-digest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube 提文案
输入 YouTube 视频链接，一键提取视频文字稿（口播文案），终端展示 + Markdown 存档 + 可导出 Excel。
支持的链接格式（视频链接必须包含视频 ID）：
- 完整URL：
https://www.youtube.com/watch?v=dQw4w9WgXcQ - 短URL：
https://youtu.be/dQw4w9WgXcQ - 视频ID：
dQw4w9WgXcQ
默认行为（重要）：
- 默认输出不带时间戳的纯文案；需要带时间戳版本时加
--timestamp - 字幕按
zh,en,asr优先级选轨：视频有中文字幕轨时直接输出中文；没有中文轨时回退英文，脚本自动将非中文字幕翻译为中文（基于 Google Translate，批量翻译提升效率）；加--no-translate可禁用自动翻译、保留原文 - 默认自动获取视频元数据（标题/频道），无需额外参数
需先配置 API Key，通过环境变量 REDFOX_API_KEY 或 --api-key 参数传入。 文字稿来源：视频字幕轨（手动字幕 + 自动生成字幕 asr），按语言优先级选轨、中文轨优先；非中文字幕由脚本端自动翻译为中文。
使用场景
当你需要执行以下任务时，应优先使用本技能：
| 场景 | 示例 |
|---|---|
| 视频转文字稿 | 丢一个 YouTube 链接，拿到完整口播文案 |
| 学习笔记整理 | 提取教程/演讲文案后让 AI 总结成章节笔记 |
| 内容二次创作 | 提取英文视频文案 → AI 翻译改写 → 公众号文章 |
| 播客/访谈存档 | 提取访谈全文，导出 Excel 归档 |
| 竞品内容分析 | 批量提取同行视频文案，分析话术与结构 |
| 视频选题调研 | 先提文案再快速判断视频是否值得深看 |
使用方法
# 基础提取（默认：不带时间戳 + 自动获取标题等元数据）
python3 "$SKILL_PATH/scripts/extract.py" "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
# 支持短链和纯视频 ID
python3 "$SKILL_PATH/scripts/extract.py" "https://youtu.be/dQw4w9WgXcQ"
python3 "$SKILL_PATH/scripts/extract.py" "dQw4w9WgXcQ"
# 带时间戳版本（方便定位原片进度）
python3 "$SKILL_PATH/scripts/extract.py" "URL" --timestamp
# 同时导出 Excel（标题/时长/视频链接/文案内容 四列）
python3 "$SKILL_PATH/scripts/extract.py" "URL" --excel
# 带时间戳文案 + 导出 Excel（Excel 内容与当前模式一致）
python3 "$SKILL_PATH/scripts/extract.py" "URL" --timestamp --excel
# 指定语言优先级（如只要英文字幕）
python3 "$SKILL_PATH/scripts/extract.py" "URL" --language "en"
# 输出原始 JSON / 不保存文件 / 不获取元数据
python3 "$SKILL_PATH/scripts/extract.py" "URL" --json
python3 "$SKILL_PATH/scripts/extract.py" "URL" --no-save
python3 "$SKILL_PATH/scripts/extract.py" "URL" --no-metadata
终端输出：视频概要（标题/语言/片段数/总时长）+ 纯文案全文。
Markdown 存档默认保存在 ~/Downloads/QoderYoutubeDigest/，文件名 {视频ID}_{时间戳}.md，含视频信息头表 + 全文；Excel（.xlsx）同目录。
工作流程（AI 必须遵循）
- 提取：运行脚本获取文案
- 表格展示：按「返回结果展示规范」用表格呈现（标题/时长/文案内容），文案内容列展示中文译文全文（无时间戳；非中文字幕已自动翻译）
- 收尾询问：展示结束后，必须主动询问用户：
「需要带时间戳的文案版本吗（方便定位原片进度）？也可以为你导出 Excel。」
- 用户要带时间戳 → 加
--timestamp重跑并展示 - 用户要 Excel → 加
--excel重跑（如需时间戳一并加--timestamp），给出文件路径
- 用户要带时间戳 → 加
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.
- 6d ago First seen · 188 lines · 127 tokens per session scan A 7a4c04887f6d
youtube-digest is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 2,679 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
dsh-office-artifacts
Create, repair, transform, or verify XLSX, DOCX, PPTX, and PDF deliverables with format-aware tools and reopen or render checks.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
investor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
dsh-paddleocr-skills-setup
Install and configure the native PaddleOCR plugin for DeepSeek Harness (DSH) from the Settings → PaddleOCR GUI. Use for OCR and image-to-text from screenshots, scans, and PDFs; Chinese/CJK text; PDF-to-Markdown; structured document parsing with tables, formulas, layout, and reading order; or DSH endpoint, credential…
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
dsh-cowork
Read and write office documents and Jupyter notebooks (xlsx, pdf, docx, pptx, ipynb) with bounded windows and stable cell/slide addresses.