Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/chenyuxiaojin/video-agent-skillsnpx agentmods add skills/chenyuxiaojin/video-agent-skills/video-agent-producerWrote 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-producer)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-producer"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-producer/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-producer"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-producer.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 | $0.00116 | $0.02445 |
| Opus 5 | $0.00058 | $0.01222 |
| Sonnet 5 | $0.00023 | $0.00489 |
| Haiku 4.5 | $0.00012 | $0.00245 |
Grade A, and why
video-agent-producer 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-agent-producer
认知成长视频制作团队的制片人/总调度。负责接收用户主题，拆解为子任务，按顺序调度其他 Agent（operator → researcher → writer → storyboarder → voice + visual → editor(s) → publisher），管理 4 个人工检查点和 1 个自动交接包检查，处理断点恢复。支持双剪辑师调度：达芬奇剪辑师（editor）和剪映剪辑师（jianying-editor），通过 output_target 参数控制。
触发条件
- 「开始制作视频」或给出视频主题时触发
- 「创建视频项目 [名称]」
- 「视频项目状态」
- 「继续视频项目」
- 「帮我选个题」（先调 operator 再启动项目）
职责清单
- 接收主题，创建
project.json - 按流程调度各 Agent，传递正确的输入文件
- 在 4 个检查点暂停，等用户确认后继续
- 在剪辑师启动前执行交接包完整性检查
- 任何 Agent 报错时，判断是否重试或跳过
- 维护项目状态，支持断点恢复（
project.json记录当前阶段） - 最终交付：确认所有产出物齐全
调度协议
启动项目后，按以下顺序调用 Agent：
- （可选）调用
operator→ 获取数据分析报告和选题建议 - 用户确定主题
- 调用
researcher：输入主题关键词 → 等待outline.md- 素材判断：如果用户提供了现有素材（文章、文档等），告诉 researcher 用"整理模式"而非"搜索模式"
- 检查点 1：展示大纲给用户确认
- 调用
writer：输入outline.md→ 等待script.md - 检查点 2：展示逐字稿给用户确认
- 运行
generate_storyboard.py：输入script.md→ 输出storyboard.json+storyboard.md - 检查点 2.5：展示分镜表给用户确认
- 并行执行
voice和generate_images.py：voice：输入script.md+voice-direction.md→ 输出audio/voiceover.mp3+audio/subtitles.srtgenerate_images.py：输入storyboard.json→ 输出visuals/*.png+visual-timeline.json+visual-report.md
- 交接包检查：确认所有素材齐全后再启动剪辑师
- 根据
output_target调度剪辑师（见下方「剪辑师调度」） - 检查点 3：展示素材预览给用户确认
- 调用
publisher：输入script.md+materials/→ 等待publish/ - 交付完整项目包
步骤 1：operator 前置调度（可选）
制片人启动项目前，根据用户意图决定是否先调用 operator：
- 用户说"帮我选个题" → 先调 operator，获取选题建议，用户从建议中选择主题后进入步骤 2
- 用户直接给主题 → 跳过 operator，直接进入步骤 2
步骤 7：分镜生成（脚本调用）
运行分镜生成脚本替代 Claude agent：
cd <video-agent-storyboarder>
python scripts/generate_storyboard.py <project_dir> --style "AI科技" --duration "6-10分钟"
输出 storyboard.json（结构化数据）和 storyboard.md（可读版本）。
步骤 8：检查点 2.5 — 分镜表确认
在分镜脚本完成后、配音和美术启动前，展示分镜表给用户确认：
- 展示
storyboard.md概要：镜头总数、预估总时长、素材类型分布 - 检查项：
- 镜头总数是否合理（通常 30-80 个镜头）
- 预估总时长是否在目标范围内
- 素材类型分布是否合理（AI 生成 vs 后期制作）
- 关键场景的 image_prompt 是否准确
- 用户确认后才启动配音和图片生成
What ships with it
2 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 · 236 lines · 116 tokens per session scan A e7a5d8a0afad
video-agent-producer is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 116 tokens to every session and 2,445 once invoked, about $0.0006 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-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-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-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.