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 Job-Yang/jobbyang-ai-skills --skill video-readergit clone --depth 1 https://github.com/Job-Yang/jobbyang-ai-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/job-yang/jobbyang-ai-skills/video-reader)<a href="https://agentmods.dev/skills/job-yang/jobbyang-ai-skills/video-reader"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/video-reader/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/job-yang/jobbyang-ai-skills/video-reader"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/video-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00384 | $0.03776 |
| Opus 5 | $0.00192 | $0.01888 |
| Sonnet 5 | $0.00077 | $0.00755 |
| Haiku 4.5 | $0.00038 | $0.00378 |
Grade A, and why
video-reader 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 12d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Reader — 给大模型配的一副"看视频的眼镜"
这个 skill 解决什么问题
你(大模型)能看图,但看不了视频。视频本质就是一串按时间排好的图片。 本 skill 的脚本帮你做两件你做不了或做不好的事:
- 初筛:用帧差(相邻帧像素差异,纯数学,不花 token)算出"哪几秒画面在动", 自动跳过静止段。用户经常从"盘古开天辟地"开始录,前面几十秒对着桌子没动—— 这些会被整段折叠,一帧都不喂给你。
- 智能抽帧:只在有动作的地方抽帧,而且支持"先粗后细"两轮下钻,既不漏关键帧, 又不会把上下文撑爆。
重要边界:这个 skill 不含任何业务逻辑。 它不懂"卡顿""面板""跟手""中间态"是什么。 它只负责把视频变成"你能消化的帧 + 时间线"。看懂画面、判断对错、定位 bug——那是你的活。
四个子命令,按需要选(别只会 scan)
本 skill 有四个能力,接到视频任务先想清楚要哪个,不要永远只用 scan:
| 子命令 | 什么时候用 | 一句话 |
|---|---|---|
scan |
默认起点;要定位"哪几秒在动/出问题" | 帧差初筛+运动时间线+稀疏抽帧 |
zoom |
已知可疑区间,要看那几秒的细节 | 指定区间高密度抽帧 |
grid |
想先要个全片概览、一张图看节奏,或视频较长先扫一眼 | 均匀取帧拼成九宫格大图,一次 Read 看全片 |
transcribe |
画面看不出、需要听(旁白/口述/报错语音/"他说了啥") | 语音转文字(带时间戳,可选,需 ffmpeg+whisper) |
常见组合:长视频/不确定从哪看 → 先 grid 看全片节奏 → scan 看运动时间线 → zoom 下钻可疑段;涉及"说了什么" → 加 transcribe 与画面时间线对齐。 用户即使没点名,你也应根据意图主动选对子命令并告诉他你用了哪个、为什么。
核心工作流:粗扫 → 下钻(由你驱动)
不要一上来就把整段视频高密度抽帧,那样既慢又炸上下文。标准打法是两步,你来决定抽哪、抽多细:
第1步 scan(粗扫)
└─ 脚本输出:运动时间线(文字) + 活动段稀疏抽的几帧
└─ 你看时间线 + 帧,判断"问题大概在 X-Y 秒"
↓
第2步 zoom(下钻)
└─ 脚本在 X-Y 秒密集抽帧
└─ 你看细节;若还不够,继续在更小区间 zoom(可多轮)
关键心法:先读时间线,再决定要不要看帧、看哪段的帧。 很多时候 scan 的运动时间线 (纯文字)就足够让你判断该往哪下钻,这是最省 token 的方式。
上传被拦怎么办(很多平台禁视频格式,务必知道)
很多平台(如 Mira 等)在上传时直接禁掉视频/音频格式,用户传 .mp4/.mov 会被提示
"不支持的文件类型",根本传不进来。这不是死路,有两个绕过办法,你必须主动告诉用户:
- 改后缀:把
xxx.mp4重命名成平台允许的后缀(如xxx.txt/xxx.bin)再上传。 你拿到后不要被后缀骗了——它本质还是视频,先把它改回.mp4(或直接用原始路径)再喂给脚本即可。 OpenCV 按文件内容解码,不认后缀,所以哪怕后缀是.txt,只要内容是视频就能读; 实在不放心就cp 那个文件 /tmp/v.mp4再处理。 - 压成 zip:把视频压成
.zip上传(zip 通常不被拦)。你收到后先解压拿到里面的视频文件, 再喂给脚本。解压是你(大模型)调用解压能力完成的,脚本本身不处理 zip。
一句话:平台拦的是"后缀/格式",不是"内容"。改后缀或套个 zip 壳就能绕过, 拿到真身后照常 scan/zoom。遇到"视频传不上去"先想到这两招,别让用户卡在上传这一步。
怎么调用
脚本路径(用绝对路径调用):
<SKILL_DIR>/scripts/video_frames.py
依赖:Python3 + opencv-python-headless + numpy(matplotlib 仅 --debug 画曲线图时用)。OpenCV 自带视频解码,不依赖系统 ffmpeg。
脚本会自动检测并安装缺失依赖(pip install --user --break-system-packages,不污染系统),无需手动准备;只有自动安装失败时才会打印一条人话提示让你手动装。
What ships with it
5 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.
- 12d ago First seen · 191 lines · 384 tokens per session scan A fdb90fe8ba22
video-reader is a skill published in the GitHub repository Job-Yang/jobbyang-ai-skills (65 stars, last pushed 8d ago), licensed MIT. It adds 384 tokens to every session and 3,776 once invoked, about $0.0019 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.