agentkit-multimedia-shopping

agentkit-multimedia-shopping is a skill for Claude Code, Codex from ufy2024/AuC. It costs 88 tokens per session (2,241 once invoked), scanned A, original, MIT.

A workflow for making a vertical product-promotion video with a digital sales-presenter character, using ByteDance AgentKit sample tools. It combines generated images, speech, music, and video.

In plain words
What is it for?
Use it to create a 9:16 phone-format shopping video: generate the presenter and background, synthesize a voice from sales copy, and combine the parts into a finished video.
Why use it?
It organizes several media-making steps so the character, setting, voice, and finished video can be produced as one sequence.

Skill for Claude CodeCodex

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

Good fit Use it to create a 9:16 phone-format shopping video: generate the presenter and background, synthesize a voice from sales copy, and combine the parts into a finished video.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ufy2024/auc/agentkit-multimedia-shopping
View source ↗ ufy2024/AuC
About the project

AuC is a Python framework for running a single AI agent with an asynchronous, pluggable reasoning loop, language-model adapters, permission levels, and observable events. It is used to build coding and conversational agents with tools, security checks, web interfaces, background jobs, evaluations, and isolated execution. The catalogue entries are skills for extending its agent workflow.

ufy2024/AuC · 1,090 stars · on GitHub

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 ufy2024/AuC --skill agentkit-multimedia-shopping
Clone the repo
git clone --depth 1 https://github.com/ufy2024/AuC

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 agentkit-multimedia-shopping

README.md
[![agentmods](https://agentmods.dev/badge/skills/ufy2024/auc/agentkit-multimedia-shopping/github.svg)](https://agentmods.dev/skills/ufy2024/auc/agentkit-multimedia-shopping)
Your own site
<a href="https://agentmods.dev/skills/ufy2024/auc/agentkit-multimedia-shopping"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/agentkit-multimedia-shopping/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 agentkit-multimedia-shopping

Your own site · 80×15
<a href="https://agentmods.dev/skills/ufy2024/auc/agentkit-multimedia-shopping"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/agentkit-multimedia-shopping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,241 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.02241
Opus 5 $0.00044 $0.01120
Sonnet 5 $0.00018 $0.00448
Haiku 4.5 $0.00009 $0.00224

Measured 10d ago against content hash ba28c2089c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentkit-multimedia-shopping 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 10d 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.

auc/skill_library/bundled/agentkit-multimedia-shopping/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKit多媒体小省导购员数字人带货

任务目标

  • 本技能用于:基于ByteDance agentkit-samples多媒体用例,生成小省导购员数字人带货视频的多模态内容
  • 能力包含:
    • AI绘画生成(小省导购员角色形象、场景背景)
    • 语音合成(导购员语音、背景音乐)
    • 视频生成(多模态组合)
    • 工作流编排(图像→音频→视频→成片)
  • 触发条件:用户需要生成小省导购员数字人带货视频,使用agentkit-samples的多媒体能力

前置准备

依赖说明

本技能依赖以下Python包:

Pillow>=10.0.0
requests>=2.28.0
numpy>=1.24.0

环境准备

  1. 安装agentkit-samples(如需要)
  2. 准备API凭证(如涉及第三方服务调用)
  3. 准备小省导购员角色固定特征描述

前置知识

  • 了解ByteDance agentkit-samples多媒体用例的基本功能
  • 了解AI绘画、语音合成、视频生成的基本原理
  • 了解9:16竖屏视频规格

操作步骤

标准流程

1. 角色形象生成

使用AI绘画生成小省导购员角色形象:

输入信息

  • 角色固定特征(脸型、发型、服饰、气质)
  • 场景类型(商务场景)
  • 情绪基调(热情、专业、亲切)

生成流程

  1. 读取 references/character-profile.md,获取小省导购员角色固定特征
  2. 调用 scripts/generate_character.py 生成角色形象
  3. 裁剪为9:16比例,分辨率≥1080×1920
  4. 保存参考图(供InfiniteTalk使用)

输出:角色参考图(9:16竖屏)

2. 场景背景生成

使用AI绘画生成场景背景:

输入信息

  • 场景类型(商务会议室、书房、洽谈室、大厅、办公室)
  • 情绪基调(冷调、暖调、中性)
  • 光影描述(侧光、顺光、顶光、逆光)

生成流程

  1. 读取场景模板,选择对应场景类型
  2. 调用 scripts/generate_scene.py 生成场景背景
  3. 裁剪为9:16比例,分辨率≥1080×1920
  4. 保存场景参考图

输出:场景参考图(9:16竖屏)

3. 语音合成

使用TTS生成导购员语音:

输入信息

  • 话术内容(带货文案)
  • 语音类型(语速、语气)
  • 情绪基调(热情、专业、亲切)

生成流程

  1. 准备话术内容(符合小省导购员人设)
  2. 调用 scripts/generate_voice.py 合成语音
  3. 导出为16kHz单声道wav格式
  4. 保存语音文件(供InfiniteTalk使用)

输出:语音文件(16kHz单声道wav)

4. 背景音乐生成

使用音乐生成工具生成背景音乐:

输入信息

  • 情绪基调(热情、专业、紧迫、亲切)
  • 音乐风格(管弦乐、钢琴、弦乐)
  • 时长(5秒/幕)

生成流程

  1. 根据情绪基调选择音乐风格
  2. 调用 scripts/generate_music.py 生成音乐
  3. 导出为16kHz单声道wav格式
  4. 保存音乐文件(供InfiniteTalk使用)

输出:音乐文件(16kHz单声道wav)

5. 视频生成

使用多模态组合生成视频:

输入信息

  • 角色参考图(9:16竖屏)
  • 场景参考图(9:16竖屏)
  • 语音文件(16kHz单声道wav)
  • 音乐文件(16kHz单声道wav)
  • 提示词(InfiniteTalk专用)

生成流程

  1. 读取InfiniteTalk专用提示词(使用infinitetalk-shopping-avatar Skill生成)
  2. 调用 scripts/generate_video.py 生成视频
  3. 生成5幕视频(每幕5秒)
  4. 拼接完整视频(总时长25秒)

输出:完整视频(25秒,9:16竖屏)

可选分支

  • 当仅需生成角色形象:执行步骤1
  • 当仅需生成场景背景:执行步骤2
  • 当仅需生成语音:执行步骤3
  • 当仅需生成背景音乐:执行步骤4
  • 当仅需生成视频:执行步骤1-5

Read the full file on GitHub · 229 lines

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. 10d ago First seen · 229 lines · 88 tokens per session scan A ba28c2089c66

Subscribe to this mod's changes

agentkit-multimedia-shopping is a skill published in the GitHub repository ufy2024/AuC (1,090 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 2,241 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

beat-sync-reel

Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.

gooseworks-ai/goose-skills · 68 tokens

byted-livesaas-master

A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.

bytedance/agentkit-samples · 160 tokens

byted-ind-ecom-product-video-prompt

A structured prompt-writing guide for creating e-commerce product videos with Seedance 2.0. It turns one or more product images into a product showcase script using scene settings, timed shots, and output constraints.

bytedance/agentkit-samples · 79 tokens

tiktok-shop-branding

Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.

nexscope-ai/eCommerce-Skills · 55 tokens

tiktok-shop-content-strategy

TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok marketing, or content planning.

nexscope-ai/eCommerce-Skills · 56 tokens

amazon-listing-images

Amazon product listing image strategy and optimization. Comprehensive shot planning, infographic design, lifestyle photography, mobile optimization, and conversion-focused visual content. Use when the user asks about Amazon images, product photography, visual optimization, or listing conversion.

nexscope-ai/Amazon-Skills · 51 tokens