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 zhiliyouxian/claude-novel-writer --skill video-assemblergit clone --depth 1 https://github.com/zhiliyouxian/claude-novel-writerWrote 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/zhiliyouxian/claude-novel-writer/video-assembler)<a href="https://agentmods.dev/skills/zhiliyouxian/claude-novel-writer/video-assembler"><img src="https://agentmods.dev/badge/skills/zhiliyouxian/claude-novel-writer/video-assembler/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/zhiliyouxian/claude-novel-writer/video-assembler"><img src="https://agentmods.dev/badge/skills/zhiliyouxian/claude-novel-writer/video-assembler.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 | $0.00056 | $0.03237 |
| Opus 5 | $0.00028 | $0.01618 |
| Sonnet 5 | $0.00011 | $0.00647 |
| Haiku 4.5 | $0.00006 | $0.00324 |
Grade D, and why
video-assembler scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Ubuntu: `sudo apt install ffmpeg` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf releases/{project_id}/video/temp How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频合成器
根据分镜文件中的参数,将镜头图片合成为带动画、音频、字幕的完整视频。
目录结构规范:
specs/directory-structure.md
输入文件
-
分镜文件 — 包含镜头参数
releases/{project_id}/video/storyboard/chapter-{NNNN}.yaml -
镜头图片 — 每个镜头对应一张图(按章节分目录)
releases/{project_id}/video/images/shots/chapter-{NNNN}/shot-{NNN}.png -
音频文件
releases/{project_id}/tts/audio/{NNNN}.mp3 -
字幕文件
releases/{project_id}/tts/subtitles/{NNNN}.srt
文件命名规范
| 文件类型 | 命名格式 | 示例 |
|---|---|---|
| 分镜文件 | chapter-{NNNN}.yaml |
chapter-0001.yaml |
| 镜头图片目录 | chapter-{NNNN}/ |
chapter-0001/ |
| 镜头图片 | shot-{NNN}.png |
shot-001.png |
| 动画片段 | shot-{NNN}.mp4 |
shot-001.mp4 |
| 输出视频 | chapter-{NNNN}.mp4 |
chapter-0001.mp4 |
说明:
- 章节号
{NNNN}使用四位数补零 - 镜头号
{NNN}使用三位数补零,每章从 001 开始
工作流程
1. 读取分镜文件
↓
2. 检查图片是否齐全
↓
3. 为每个镜头生成 Ken Burns 动画
↓
4. 拼接所有视频片段
↓
5. 添加音频
↓
6. 烧录字幕
↓
7. 输出最终视频
依赖检查
执行前必须检查 ffmpeg:
which ffmpeg || echo "❌ ffmpeg 未安装"
如未安装,提示用户:
- macOS:
brew install ffmpeg - Ubuntu:
sudo apt install ffmpeg
步骤1: 读取分镜文件
从 YAML 文件中读取每个镜头的参数:
shots:
- id: "001"
duration: 32.5
camera:
type: "push_in"
start_scale: 1.0
end_scale: 1.3
start_position: [0.5, 0.5]
end_position: [0.5, 0.45]
步骤2: 检查图片
# 检查所有镜头图片是否存在
for shot in 001 002 003 ...; do
[ -f "releases/{project_id}/video/images/shots/shot-${shot}.png" ] || echo "缺少 shot-${shot}.png"
done
步骤3: 生成 Ken Burns 动画
ffmpeg zoompan 滤镜
Ken Burns 效果通过 ffmpeg 的 zoompan 滤镜实现。
命令模板:
ffmpeg -y -loop 1 -i {input_image} \
-vf "zoompan=z='min(max({start_scale}+{scale_delta}*(on-1),1),10)':x='(iw-iw/zoom)*({start_x}+{x_delta}*(on-1))':y='(ih-ih/zoom)*({start_y}+{y_delta}*(on-1))':d={total_frames}:s=1920x1080:fps=30" \
-t {duration} \
-c:v libx264 -pix_fmt yuv420p -preset medium -crf 23 \
{output_video}
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 · 374 lines · 56 tokens per session scan D 15a2eda41db8
video-assembler is a skill published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 56 tokens to every session and 3,237 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.