agentmods.dev

video-agent-producer

video-agent-producer is a skill for Claude Code, Codex from chenyuxiaojin/video-agent-skills. It costs 116 tokens per session (2,445 once invoked), scanned A, original, MIT.

A coordinator for a video-production team of specialized agents. It breaks a topic into research, writing, storyboarding, voice, visuals, editing, and publishing, while tracking progress and waiting for user approvals.

In plain words
What is it for?
Use it to start, continue, or check a video project, or to choose a topic. It creates project files, dispatches the relevant agents, supports DaVinci Resolve or Jianying editing, and confirms that final materials are complete.
Why use it?
It organizes a multi-stage video project and makes it possible to resume after an interruption. Checkpoints and handoff checks help catch missing work before the next stage starts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/generate_storyboard.py <project_dir> --style "AI科技" --duration "6-10分钟".

not rated 14repo +2 5mo ago A scan 116 tokens original MIT

Good fit Use it to start, continue, or check a video project, or to choose a topic. It creates project files, dispatches the relevant agents, supports DaVinci Resolve or Jianying editing, and confirms that final materials are complete.

Compare 6 skills from other repositories ↓
View source ↗ chenyuxiaojin/video-agent-skills
Install

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.

Clone the repo
git clone --depth 1 https://github.com/chenyuxiaojin/video-agent-skills
agentmods
npx agentmods add skills/chenyuxiaojin/video-agent-skills/video-agent-producer

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for video-agent-producer

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-producer/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-producer)
Your own site
<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.

agentmods 80×15 button for video-agent-producer

Your own site · 80×15
<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>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.02445
Opus 5.5 $0.00046 $0.00978
Sonnet 5.5 $0.00023 $0.00489
Haiku 4.5 $0.00012 $0.00245

Measured 2mo ago against content hash e7a5d8a0afad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/pipeline_manager.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

video-agent-producer/SKILL.md · 236 lines

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：

  1. （可选）调用 operator → 获取数据分析报告和选题建议
  2. 用户确定主题
  3. 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"
  4. 检查点 1：展示大纲给用户确认
  5. 调用 writer：输入 outline.md → 等待 script.md
  6. 检查点 2：展示逐字稿给用户确认
  7. 运行 generate_storyboard.py：输入 script.md → 输出 storyboard.json + storyboard.md
  8. 检查点 2.5：展示分镜表给用户确认
  9. 并行执行 voice 和 generate_images.py：
    • voice：输入 script.md + voice-direction.md → 输出 audio/voiceover.mp3 + audio/subtitles.srt
    • generate_images.py：输入 storyboard.json → 输出 visuals/*.png + visual-timeline.json + visual-report.md
  10. 交接包检查：确认所有素材齐全后再启动剪辑师
  11. 根据 output_target 调度剪辑师（见下方「剪辑师调度」）
  12. 检查点 3：展示素材预览给用户确认
  13. 调用 publisher：输入 script.md + materials/ → 等待 publish/
  14. 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

Read the full file on GitHub · 236 lines

Files

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.

Changes

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.

  1. 2mo ago First seen · 236 lines · 116 tokens per session scan A e7a5d8a0afad

Subscribe to this mod's changes

video-agent-producer is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (14 stars, last pushed 5mo ago), licensed MIT. It adds 116 tokens to every session and 2,445 once invoked, about $0.0005 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 2026-08-31.

Claude CodeCreative and mediaPlanningagent-skillsai-videocapcutcontent-automationdavinci-resolve
Related

video-agent-producer compared with skills from other repositories

video-agent-producer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
video-agent-producerchenyuxiaojin/video-agent-skillsSkill145mo agoMITA116Claude Code, Codex
talking-head-editpireel/pireelSkill1.4kyesterdayAGPL-3.0A79Claude Code, Codex
montage-editpireel/pireelSkill1.4kyesterdayAGPL-3.0A35Claude Code, Codex
audio-and-musicpireel/pireelSkill1.4kyesterdayAGPL-3.0A0Claude Code, Codex
suggest-sfxhassancs91/claude-faceless-shorts-creatorSkill3052mo agoMITA169Claude Code
make-ai-shorthassancs91/claude-faceless-shorts-creatorSkill3052mo agoMITA180Claude Code
make-shorthassancs91/claude-faceless-shorts-creatorSkill3052mo agoMITA183Claude Code