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 AbyssCN/oh-my-dag --skill omd-videogit clone --depth 1 https://github.com/AbyssCN/oh-my-dagWrote 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/abysscn/oh-my-dag/omd-video)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-video"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-video/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/abysscn/oh-my-dag/omd-video"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-video.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 Data Exfiltration · line 51 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00158 | $0.02312 |
| Opus 5.5 | $0.00063 | $0.00925 |
| Sonnet 5.5 | $0.00032 | $0.00462 |
| Haiku 4.5 | $0.00016 | $0.00231 |
Grade A, and why
omd-video 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 16d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/omd-video — 视频→逐段结构化笔记 (Gemini via agy 多模态)
讲解类视频画面有大量 PPT/框架图/提示词/代码 = 音频拿不到 → 默认经
agy(Antigravity CLI,Google 订阅额度)让 Gemini 原生吃视频(画面+音频;--backend mimo走 MiMo API),非 whisper 转写。确定性五阶段管线,可重入(已产出阶段自动跳过):discover/enumerate→download→segment→fanout→aggregate。综合/蒸馏不在本管线内——产物ALL-NOTES.md交给 omd dag 引擎。
何时用
抖音/B站/YouTube 讲解视频或课程系列要提炼成知识;画面信息密集(代码/图表/PPT)、音频拿不全的内容采集。
何时不用(边界)
已有文字原文要多视角综合 → /omd-council;要 web 页面内容/多源事实 → dag_research;要设计判优 → /omd-council。本管线只做"视频→笔记语料",综合让 dag 引擎做。
入口:先定用途,再定参数(跑之前必做)
视频采集是一次性昂贵操作(下载+切段+N 段并发喂模型),fps/分辨率选错 = 糊了读不到 或 烧钱重跑。所以拿到 url/描述后先判用途再定参数——能从用户描述/URL 推断就推断,并宣告选定参数再跑;只有画面构成不明(它决定 fps/res,猜错最贵)才问一句。不逐参数确认(反 ceremonial),一次问清用途即可。
三个要素定全部参数:① 画面构成(定 fps + media_resolution)② 要提取什么(定制 prompt)③ 时长量级(分段 + 成本预警)。
| 画面构成 | --fps |
--media-resolution |
--scale |
prompt 侧重 |
|---|---|---|---|---|
| 纯口播/访谈/播客 | 1(可 0.5) | default(无字·省钱) | 640 | 口播要点 |
| PPT 幻灯讲解 | 1 | max | 960 | 屏幕文字+框架图 |
| 代码演示/live coding | 2 | max | 1280 | 逐行转录代码 |
| 动画/逐步 build/白板 | 2 | max | 960 | 抓状态变化时序 |
| UI 操作/点选演示 | 2–3 | max | 960 | 操作步骤序列 |
「要提取什么」和 fps 正交,单独定制 fanout prompt(只要提示词模板 / 只要代码 / 完整转录 → --prompt-file 或改 DEFAULT_PROMPT)。画面构成不明时问一句:「画面主要是啥——纯人讲 / PPT / 敲代码 / 动画演示?重点抓口播还是画面里的代码/提示词?」用户答完 → 宣告选定 fps/res/scale/prompt → 跑。
怎么跑
脚本自包含在本技能目录,随 omd mcp 自装到 ~/.claude/skills/omd-video/run.py。用绝对路径调(尊重 CLAUDE_CONFIG_DIR):
SKILL="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/omd-video/run.py"
# 已有 url/id 列表 (每行 <url> 或 <id>|<slug>)
python "$SKILL" --urls list.txt --workdir /tmp/<job>
# 没链接只有题目: 平台搜索找片 (yt-dlp ytsearch 默认 / bilisearchN: B站; 抖音搜索不支持)
python "$SKILL" --search "<题目>" --max 6 --workdir /tmp/<job>
# 从抖音用户主页全自动枚举 (enumerate 阶段需 browser-harness 接管真 Chrome 登录态)
python "$SKILL" --enumerate "https://www.douyin.com/user/<sec_uid>" --workdir /tmp/<job>
# 单跑/补跑某阶段 (可重入)
python "$SKILL" --workdir /tmp/<job> --only fanout
后端:默认 --backend agy(--model 默认 gemini-3.8-flash-high,并发默认 3;无 key,用 agy 自己的登录)。--backend mimo 才要 MIMO_API_KEY / MIMO_BASE_URL(os.environ 优先,否则找 CWD/.env 或 ~/.omd/.env)。依赖:yt-dlp(太旧会 403,uv tool upgrade yt-dlp)、ffmpeg/ffprobe、agy 在 PATH 内。
What ships with it
1 file 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.
- 16d ago Changed · +4 lines · +3 tokens per session f1b94bcc9ec3
- 1mo ago First seen · 78 lines · 155 tokens per session scan A f05744beae72
omd-video is a skill published in the GitHub repository AbyssCN/oh-my-dag (44 stars, last pushed 16d ago), licensed MIT. It adds 158 tokens to every session and 2,312 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ace-rsi-toolkit
Run ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published Benchmark.
release-notes
Write release notes for a tagged release — a business-impact summary of what changed for the user, plus a thanks section naming every contributor whose commits are in the release. Short by construction.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
tech-blog-expert
A specialist writing guide for technical articles, tutorials, architecture explanations, source-code analysis, and open-source project documents such as README files. It adapts the structure and detail to the intended developer audience.
poetry-prose-expert
A writing guide for creating and reviewing poetry, prose, essays, classical Chinese-style poetry, and literary criticism. It focuses on imagery, rhythm, emotion, and leaving room for the reader's interpretation.