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 agentmods add skills/dddfxyqiming/agent_extensions/video-notes-generatornpx skills add DDDFXYqiming/Agent_Extensions --skill video-notes-generatorgit clone --depth 1 https://github.com/DDDFXYqiming/Agent_ExtensionsWrote 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/dddfxyqiming/agent_extensions/video-notes-generator)<a href="https://agentmods.dev/skills/dddfxyqiming/agent_extensions/video-notes-generator"><img src="https://agentmods.dev/badge/skills/dddfxyqiming/agent_extensions/video-notes-generator.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.02266 |
| Opus 5 | $0.00033 | $0.01133 |
| Sonnet 5 | $0.00013 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
video-notes-generator 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 today.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-notes-generator
把视频 URL 或本地视频加工成结构化笔记素材：下载 → 字幕/转写 → 抽帧 → 五类产物；最终笔记由 Agent 基于产物综合生成。脚本零 pip 设计，只依赖 yt-dlp 与 ffmpeg 二进制。
触发场景
- 用户说"视频笔记 / 视频总结 / video notes / summarize video"
- 分享 Bilibili / YouTube / 抖音 / 快手 URL 并要求笔记或总结
- 要求转写或总结本地视频文件
Quick Start
# B站视频（无字幕时自动转写）
python3 <skill>/scripts/video_to_notes.py "https://www.bilibili.com/video/BV1xxxxx"
# YouTube + 自定义输出目录
python3 <skill>/scripts/video_to_notes.py "https://www.youtube.com/watch?v=xxxxx" -o ./my_notes
# 本地文件（默认抽帧做多模态分析）
python3 <skill>/scripts/video_to_notes.py "/path/to/video.mp4" --frame-interval 30 --max-frames 3
# 紧急纯文本模式（仅当下载/抽帧失败或用户明确不要图）
python3 <skill>/scripts/video_to_notes.py "<url>" --no-frames
流水线
- 依赖预检 → 2. 平台检测（bilibili/youtube/douyin/kuaishou/local）→ 3. 元数据（yt-dlp --dump-json，B站失败走公开 API fallback）→ 4. 字幕优先（B站/YouTube）→ 5. 无字幕则音频下载 + faster-whisper / whisper.cpp 转写 → 6. 下载 ≤720p H.264 视频抽代表帧（20%/50%/80%）→ 7. 输出产物。
产物五件套
| 文件 | 用途 |
|---|---|
*_final_notes.md |
用户可见笔记（先读这个） |
*_chunk_summaries.md |
分块摘要（第二顺位读） |
*_transcript.json |
完整转写档案（仅在用户要求原始细节时读） |
*_visual_manifest.json |
帧索引：timestamp / image_path / nearby_transcript |
*_frames/ |
关键帧图片 |
配置
环境变量（可放 <runtime>/.env，runtime 默认 ~/.cache/video-notes-generator）：
| 变量 | 默认 | 说明 |
|---|---|---|
YTDLP / FFMPEG |
自动探测 | 二进制路径 |
TRANSCRIBER_TYPE |
faster-whisper |
转写引擎；whisper.cpp 可选（有 git/编译器时自动编译） |
WHISPER_MODEL |
base |
转写模型。嘈杂音频建议 large-v3-turbo（首次需下载模型）；内置别名 tiny/base/small/medium/large-v1/v2/v3/v3-turbo |
WHISPER_DEVICE / WHISPER_COMPUTE_TYPE |
留空 = 自动探测 | 显式设值最优先；取值与降级行为见「转写算力」小节 |
VIDEO_NOTES_CUDA_BIN |
自动搜索 | 含 cublas64_12.dll 的目录，供借用 CUDA 运行库时指定 |
VIDEO_NOTES_PROXY |
标准 proxy env | yt-dlp/网络代理；也可用 <runtime>/config/proxy.json {"enabled":true,"url":"..."} |
VIDEO_NOTES_MAX_AGENT_FRAMES |
3 |
默认最大抽帧数 |
VIDEO_NOTES_FRAME_MAX_WIDTH |
640 |
帧宽上限 |
CLI 参数：位置参数 url 必填；-o/--output（默认 ./notes）；--no-subtitle、--transcribe、--model、--frame-interval、--max-frames、--no-frames、--print-full-json（勿在 Agent 场景使用）。已废弃：--url/--file/--style/--format/--quality。
What ships with it
13 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.
- CHANGELOG.md 1.5 KB
- references/bilibili-412-api-fallback.md 2.1 KB
- references/bilibili-uploader-discovery.md 4.0 KB
- references/bilibili-uploader-exact-space-api.md 3.5 KB
- references/bilibili-windows-ssl-and-long-audio.md 2.6 KB
- references/bulk-visual-enrichment.md 4.4 KB
- references/platform-support.md 4.1 KB
- references/prompt-templates.md 4.9 KB
- references/style-guide.md 3.6 KB
- scripts/install_deps.sh 2.7 KB runs code
- scripts/video_to_notes.py 68 KB runs code
- templates/.env.example 1.1 KB
- templates/config.yaml 1.7 KB
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.
- today Changed · +6 lines 971e3937b6af
- 4d ago First seen · 121 lines · 66 tokens per session scan A e4eeaaae1411
video-notes-generator is a skill published in the GitHub repository DDDFXYqiming/Agent_Extensions (7 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,266 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
tidyfactor-styler
Production framework styler and surgical RTL UI polish engine with Contextual Decision Layer (CDL). Operates directly inside existing codebases across React/Next.js, PHP, WordPress, and Vanilla HTML/CSS/JS. Trigger on commands 'brief', 'component', 'section', 'page', 'redesign', 'typography', 'palette', 'layout'…
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.
scaffold-exercises
创建包含 section、problem、solution 和 explainer 的练习目录结构，且能通过 lint 检查。当用户想要搭建练习框架、创建练习模板或设置新的课程章节时使用。.
migrate-to-shoehorn
将测试文件从 as 类型断言迁移到 @total-typescript/shoehorn。当用户提到 shoehorn、想要在测试中替换 as、或需要部分测试数据时使用。.
writing-for-agents
为智能体编写文档。当你正在创建或编辑技能，或者修改 AGENTS.md / CLAUDE.md 时使用。.
diagnosing-bugs
针对棘手 bug 和性能回归的诊断循环。当用户说"诊断"/"调试这个"，或报告某处崩溃/报错/不正常/缓慢时使用。.