agentmods.dev

video-production

video-production is a skill for Claude Code, Codex from ZJU-REAL/Easel. It costs 199 tokens per session (2,356 once invoked), scanned A, original, Apache-2.0.

A complete video-making workflow that turns source footage into a finished, packaged video. It covers transcription, scene planning, design, implementation, checking, previewing, rendering, and delivery.

In plain words
What is it for?
Use it when you have a local source video and want a finished edit plus its delivery materials.
Why use it?
It gives each production step a checkable process and stops delivery when required quality checks or human approvals are missing.

Skill for Claude CodeCodex

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

not rated 3.8krepo +304 changed 5d ago A scan 199 tokens original Apache-2.0

Good fit Use it when you have a local source video and want a finished edit plus its delivery materials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zju-real/easel/video-production
View source ↗ ZJU-REAL/Easel zju-real.github.io
About the project

Easel is an open-source content workspace and AI agent for managing social media from trend discovery through planning, content creation, publishing, and performance analysis. It is intended for social media creators and maintains separate account profiles, content projects, platform adaptations, and publishing records. The catalogue skills support these content and publishing workflows.

ZJU-REAL/Easel · 3,795 stars · on GitHub · zju-real.github.io

Install

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.

Any agent
npx skills add ZJU-REAL/Easel --skill video-production
Clone the repo
git clone --depth 1 https://github.com/ZJU-REAL/Easel

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-production

README.md
[![agentmods](https://agentmods.dev/badge/skills/zju-real/easel/video-production/github.svg)](https://agentmods.dev/skills/zju-real/easel/video-production)
Your own site
<a href="https://agentmods.dev/skills/zju-real/easel/video-production"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-production/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-production

Your own site · 80×15
<a href="https://agentmods.dev/skills/zju-real/easel/video-production"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,356 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 $0.00199 $0.02356
Opus 5.5 $0.00080 $0.00942
Sonnet 5.5 $0.00040 $0.00471
Haiku 4.5 $0.00020 $0.00236

Measured 5d ago against content hash acd7231b78d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

video-production 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 5d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/video_pipeline.py, vendor/video-pipeline-sdk/deps/bootstrap.ps1, vendor/video-pipeline-sdk/deps/bootstrap.sh, …), 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.

skills/builtin/video-production/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

整片视频产线（video-production）

把一支原片（口播 / 独白）做成包装级成片：摸底 → 转录 → 分场 → 设计表 → 脚手架 → 写码 → 验证 → 预览 → 渲染 → 交付。质量不靠自觉，靠可执行的门。

产线 SDK 已内置在本技能 vendor/video-pipeline-sdk/（随 Easel 进仓、可复现、可在其基础上改）。 首次使用先跑一次依赖还原：bash <ROOT>/skills/builtin/video-production/vendor/video-pipeline-sdk/deps/bootstrap.sh （装 Remotion 渲染引擎，--ignore-scripts；node_modules 不入库）。

什么时候用

用户说「用视频产线做一支整片 / 把这段素材做成片 / 整片包装」时使用。

开工前检查（缺源片不要动工）

  • 源片必需：必须有可读的本地路径。用户没给 → 先向用户要（要路径，或提示他把文件拖进聊天 / 拷到内容库收件箱）；严禁用占位素材开工
  • 主题与基调（--brief）建议要一句；现成材料（转录稿 / 分场 / 设计表）有就给、没有就按流程走（流程会在需要时停下）

转录三级策略（选一个，优先级从上到下）

产线第二步要把口播里说的话转成带时间轴的文字稿。三级降级，越靠前越省：

  1. tier1 现成稿（最优）：源片自带字幕/台词就用它——start --transcript 路径。.srt/.vtt 会自动转成段级 transcript.json（保留时间轴）；.json（segments 结构）直接用。Easel 做的口播剧一般自带 SRT，走这条即可，不下模型。
  2. tier2 云端 ASR API：没现成稿但配了 SILICONFLOW_API_KEY（env）→ 自动调硅基流动（默认 XingChenAGI/XingChenGSR-V1.0，可用 SILICONFLOW_ASR_MODEL / SILICONFLOW_BASE_URL 覆盖）。key 只从环境变量读，勿写进命令/仓库。
  3. tier3 本地 whisper（兜底）：都没有才用本地 large-v3（首次下约 3GB）。需 faster-whisper。

让用户看得见（产物贴进对话 · 免上传）

对话消息直接支持图片与视频（站内媒体通道 /api/media/，零上传、零改前端）。产物落盘后，把它们贴进消息、再配卡片：

  • 图片：Markdown 图片语法（! + 方括号说明文字 + 圆括号地址），地址写 /api/media/<outputs 相对路径，逐段 URL 编码>（示例文件名：视频产线/<时间戳>/run/preview/f60.png）
  • 视频：<video src="/api/media/<outputs 相对路径>" controls style="max-width:420px"> 标签
  • 文件：Markdown 链接语法（方括号文字 + 圆括号地址）指向 /api/media/<outputs 相对路径>，或把要点直接摘进消息

三处必用：

  1. 设计表确认卡之前：先贴设计表要点摘要 + 全文链接（用户"看得见才审得动"）
  2. 预览确认卡之前：把 run/preview/*.png 逐张贴成图片，再出预览卡
  3. 交付时：成片贴成 video 标签（视频产线/<时间戳>/out/final.mp4），附门报告链接

素材怎么给（用户问"怎么把视频给你"时这样答）

  1. 首选 · 本地路径：文件放本机任意位置，对话里报路径即可（例：E:/clips/raw.mp4）。无大小限制、不复制文件
  2. 小文件可直接拖进聊天上传（进内容库收件箱）；大文件不走上传——直接报本地路径（见第 1 条）
  3. 也可先手动拷进 outputs/_inbox/ 再报路径

快速开始

python <ROOT>/skills/builtin/video-production/scripts/video_pipeline.py doctor
python <ROOT>/skills/builtin/video-production/scripts/video_pipeline.py start --source "C:/path/raw.mp4" --brief "主题一句话"

Read the full file on GitHub · 131 lines

Files

What ships with it

60 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. 5d ago Changed acd7231b78d4
  2. 27d ago Changed · +3 lines · +99 tokens per session 11c89bdc8127
  3. 1mo ago First seen · 128 lines · 100 tokens per session scan A 8b9bd228839d

Subscribe to this mod's changes

video-production is a skill published in the GitHub repository ZJU-REAL/Easel (3,795 stars, last pushed yesterday), licensed Apache-2.0. It adds 199 tokens to every session and 2,356 once invoked, about $0.0008 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 2026-09-18.

Creative and mediaagentagent-skillcontent-automationcontent-creationcontent-generationmcp
Related

Other skills, from other repositories

jacky-motion2-0

A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.

Jackywxsz/Jacky-motion · 108 tokens

p-video-2-pro-reference

Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts.

PrunaAI/pruna-skills · 63 tokens

p-video

Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p.

PrunaAI/pruna-skills · 52 tokens

interactive-explainer

Use when someone wants an educational explainer with a host and characters — history or science shorts with dialogue, not voiceover-only B-roll.

PrunaAI/pruna-skills · 33 tokens

visual-transition-reel

Use when someone wants a montage with transitions between shots — action-sequence reel or multi-scene piece where narration is optional.

PrunaAI/pruna-skills · 30 tokens

p-image-edit

Use when someone wants to edit an existing photo — change outfits or backgrounds, compose from reference images, or apply prompt-driven edits.

PrunaAI/pruna-skills · 30 tokens