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 chenyuxiaojin/video-agent-skills --skill video-agent-visualgit clone --depth 1 https://github.com/chenyuxiaojin/video-agent-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/chenyuxiaojin/video-agent-skills/video-agent-visual)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-visual"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-visual/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/chenyuxiaojin/video-agent-skills/video-agent-visual"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-visual.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 | $0.00102 | $0.01703 |
| Opus 5 | $0.00051 | $0.00851 |
| Sonnet 5 | $0.00020 | $0.00341 |
| Haiku 4.5 | $0.00010 | $0.00170 |
Grade A, and why
video-agent-visual 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-agent-visual(美术师)
职责边界
美术师通过 GPTIMG2(gpt-image-2,OpenAI 兼容图片生成 API)批量生成 2K 图片素材:
- ✅ 读取
storyboard.json,理解每个镜头的素材需求 - ✅ 调用
generate_images.py批量生成图片 - ✅ 跳过后期制作镜头(数据/文字/分屏),交给剪辑师
- ✅ 构建 visual-timeline.json(视觉时间轴)
- ✅ 生成 visual-report.md(素材报告)
- ❌ 设计画面内容(分镜师负责)
- ❌ 构建 FCPXML 时间轴(剪辑师负责)
输入 → 输出
- 输入:
storyboard.json(分镜师产出) - 输出:
visuals/*.png+visual-timeline.json+visual-report.md
执行方式
运行脚本
python scripts/generate_images.py <project_dir> [--style <风格>] [--concurrency <并发数>] [--aspect-ratio <比例>]
参数:
project_dir— 项目目录(包含 storyboard.json)--style— 风格名称,对应styles/目录下的文件(默认:default)--concurrency— 并发数(默认:5)--aspect-ratio— 宽高比(默认:16:9)
脚本会:
- 读取
storyboard.json - 过滤掉
is_post_production: true的镜头 - 加载风格指令(附加到每个 prompt 前)
- 并发调用 GPTIMG2(gpt-image-2)
/v1/images/generations生成 2K 图片(response_format=url,拿到 url 后下载落地) - 输出图片到
visuals/目录(001.png, 002.png...) - 生成失败自动重试 1 次
- 输出
visual-report.md和visual-timeline.json
尺寸说明(2K)
--aspect-ratio 按下表映射到 GPTIMG2 的 2K 尺寸(边长对齐 16 的倍数):
| 宽高比 | 尺寸 |
|---|---|
| 16:9(默认) | 2560x1440 |
| 9:16 | 1440x2560 |
| 1:1 | 2048x2048 |
| 4:3 | 2048x1536 |
| 3:4 | 1536x2048 |
未列出的比例兜底为 16:9(2560x1440)。当前 storyboard.json 结构不含比例字段,比例由 --aspect-ratio 参数决定。
风格配置
预置风格文件位于 styles/ 目录:
| 文件 | 说明 | 适用场景 |
|---|---|---|
default.txt |
写实、电影感、自然光 | 通用 |
tech.txt |
未来感、蓝色调、科技元素 | AI / 科技类视频 |
knowledge.txt |
温暖、清晰、学术感 | 认知 / 知识类视频 |
用户可新增自定义风格文件到 styles/ 目录,脚本会自动识别。
visual-timeline.json 格式
{
"video_specs": {
"resolution": "1920x1080",
"fps": 30,
"aspect_ratio": "16:9"
},
"total_duration": 490.0,
"visuals": [
{
"shot": "001",
"file": "visuals/001.png",
"description": "A person scrolling through phone...",
"start_time": 0.0,
"end_time": 4.0,
"duration": 4.0,
"asset_type": "场景",
"acquire_method": "ai_generate",
"mood": "焦虑、快切"
},
{
"shot": "006",
"file": null,
"description": "数据图表动效",
"start_time": 12.0,
"end_time": 14.0,
"duration": 2.0,
"asset_type": "数据",
"acquire_method": "post_production",
"mood": "冲击、停顿",
"editor_note": "数据图表动效"
}
]
}
What ships with it
10 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.
- scripts/align_timestamps.py 0 B runs code
- scripts/generate_image.py 0 B runs code
- scripts/generate_images.py 13 KB runs code
- scripts/generate_report.py 0 B runs code
- scripts/parse_storyboard.py 0 B runs code
- scripts/search_stock.py 0 B runs code
- scripts/search_web_images.py 0 B runs code
- styles/default.txt 178 B
- styles/knowledge.txt 260 B
- styles/tech.txt 299 B
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.
- 11d ago First seen · 169 lines · 102 tokens per session scan A 29bfef93736a
video-agent-visual is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 1,703 once invoked, about $0.0005 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
suggest-sfx
The SFX pass. Analyze a short's beats + narration and propose tasteful sound effects synced to them, drawing from (and growing) a shared, reusable SFX library, then render an SFX-mixed audition preview. Use when the user wants to "add SFX / sound effects", "suggest sfx", "score the transitions", "sound-design this…
make-short
Build a fully-synthetic vertical short (1080×1920, 40s) end-to-end from a topic — script + beats.json, linked TSX beats over a persistent canvas, phone-scale QA, render, ElevenLabs voice with exact word-synced captions, SFX audition, optional music bed. Use when the user wants to "make a short", "create a shorts…
make-ai-short
Build a GENERATIVE-pixels vertical short (1080×1920, 35-40s) end-to-end — a recurring locked character animated by a fal video model (Seedance 1.5 Pro default) under a philosophical/story VO, composited in Remotion with word-synced captions, SFX audition, seamless frame-0==last-frame loop. Use when the user wants to…
make-vox
Build a Vox-style LAYERED-COLLAGE vertical short end-to-end — script + scene dissection into image layers, layer production (AI images via genimage.py + cutout.py, HTML→PNG, SVG-in-TSX), choreographed TSX assembly on the collage kit (CollageBoard camera, parallax, cutouts, chips, routes), frame QA, render, then…
talking-head-edit
Edit interviews, lessons, commentary, podcasts, and direct-to-camera recordings built around speech. Use it to remove dead air, filler words, false starts, repeated lines, and discarded retakes while preserving natural delivery and keeping captions aligned. When the user asks for visual enhancement, also use it for…
montage-edit
Discover the governing emotion and visual motifs in a body of footage, then compose a montage whose image, rhythm, sound, and text form one intentional experience.