Agent skill

AgentKit Shopping Avatar Video

by anbeime in anbeime/skill

Chinese-language skill that produces a 25-second vertical video of a digital shopping-guide avatar for e-commerce, chaining AI image, voice and video generation.

No licenceAuto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install AgentKit Shopping Avatar Video

skills CLI
$ npx skills add anbeime/skill --skill agentkit-multimedia-shopping -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anbeime/skill agentkit-multimedia-shopping --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping .claude/skills/agentkit-multimedia-shopping && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agentkit-multimedia-shopping
GitHub stars
7.8k
Token cost
~1k tokens
SKILL.md length
190 words
Files
16 (incl. scripts, references, assets)
Skills in repo
62
Repo updated
First seen
Licence
None found

At a glance

Chinese-language skill that produces a 25-second vertical video of a digital shopping-guide avatar for e-commerce, chaining AI image, voice and video generation.

  • Works in 5 steps: 角色形象生成 → 场景背景生成 → 语音合成 → …
  • Generating a digital shopping-guide avatar for a livestream or short video
  • SKILL.md covers 任务目标, 前置准备, 操作步骤 and 资源索引, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Written in Chinese, the skill orchestrates ByteDance's agentkit-samples multimedia tools to build a nine-by-sixteen vertical video of a fixed shopping-guide character recommending a product. It generates the character's portrait and a scene background with AI image generation at a resolution of at least 1080 by 1920, cropped to the vertical ratio, synthesizes the sales script as sixteen-kilohertz mono speech and a matching background music track, then feeds the character image, scene image, voice file, music file and prompts into a video generator that produces five five-second scenes stitched into one 25-second clip.

Each step can also run alone when only the avatar, the background, the voice or the music is needed. The skill depends on Pillow, requests and numpy, and needs agentkit-samples installed plus credentials for any third-party services it calls. Reference files hold the character's fixed appearance, scene templates and tool usage notes, and the character's look must stay consistent across every generated asset.

When your agent uses it

  • Generating a digital shopping-guide avatar for a livestream or short video
  • Turning a finished sales script into a full product video
  • Generating only the character portrait or only the scene background
  • Preparing a reference image and audio for a companion video-generation skill

Example prompts

  • “Generate a reference portrait of the shopping-guide avatar in a business-meeting scene.”
  • “Synthesize this sales script into the avatar's voice.”
  • “Generate the full 25-second product video using the avatar and voice from before.”

Requirements

  • Python with Pillow, requests and numpy
  • ByteDance agentkit-samples installed
  • API credentials for the image, voice and video services it calls

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 角色形象生成
  2. 场景背景生成
  3. 语音合成
  4. 背景音乐生成
  5. 视频生成

What it can do on your machine

Read from SKILL.md and the folder at commit e92662c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 7 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AgentKit Shopping Avatar Video loads about 1k tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 31 tokens; SKILL.md has 190 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 190 words (~1,019 tokens).

name
agentkit-multimedia-shopping
dependency.python
Pillow>=10.0.0, requests>=2.28.0, numpy>=1.24.0
dependency.system
echo "Skill已加载"

Read the full SKILL.md on GitHub

Files

SKILL.md and 15 other files (scripts, references, assets) in skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping of anbeime/skill.

  • SKILL.md
  • assets/examples/sample-output.md
  • assets/templates/avatar-description.md
  • assets/templates/product-recommendation-script.md
  • references/character-profile.md
  • references/scene-templates.md
  • references/script-templates.md
  • references/tool-usage-guide.md
  • references/visual-styles.md
  • scripts/generate_audio.py
  • scripts/generate_character.py
  • scripts/generate_image.py
  • scripts/generate_music.py
  • scripts/generate_scene.py
  • scripts/generate_video.py
  • scripts/generate_voice.py

Open the folder on GitHubat commit e92662c

Compare with similar skills

AgentKit Shopping Avatar Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AgentKit Shopping Avatar Video compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AgentKit Shopping Avatar Video this skillanbeime/skill7.8k—~1kAutomated safety check: PassNone
Wedding Video Guided Wizardaaronyi97/wedding-video-guided-wizard310—~1kAutomated safety check: PassMIT
RunninghubHM-RunningHub/OpenClaw_RH_Skills142—~1.6kAutomated safety check: PassApache-2.0
Media Genclacky-ai/openclacky1.2k—~7.5kAutomated safety check: PassMIT
Bailian Media Generationmodelstudioai/cli542—~2kAutomated safety check: PassApache-2.0
BlockrunBlockRunAI/blockrun-mcp391—~2.7kAutomated safety check: PassMIT

Similar skills

  • Wedding Video Guided Wizard

    aaronyi97/wedding-video-guided-wizard

    Guide a creator through a real couple's custom wedding video, from a shareable story intake card and Kimi writing pack through narration, external GPT image prompts, image-to-video packs, music and…

    310 GitHub stars~1k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Runninghub

    HM-RunningHub/OpenClaw_RH_Skills

    Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.

    142 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.5k tokensUpdated today
    Media & CreativeAuto-check passed
  • Bailian Media Generation

    modelstudioai/cli

    Chinese-language entry point into Alibaba Cloud Bailian's image, video and speech generation and understanding, routed through separate image, video, speech and vision commands.

    542 GitHub stars~2k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Blockrun

    BlockRunAI/blockrun-mcp

    Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

    391 GitHub stars~2.7k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Fal AI Media

    affaan-m/ECC

    Unified media generation via fal.ai MCP — image, video, and audio.

    277k GitHub starsUsed in 4 repos~1.9k tokens
    Media & CreativeAuto-check passed

More from anbeime/skill

All 62 skills in this repo
  • Produces a full material pack for a three-minute history-of-science explainer video from a theme, era and core conclusion: narration, storyboard, Veo2 prompts and character design.

    7.8k GitHub stars~480 tokensUpdated yesterday
    Auto-check passed
  • Turns a PPT content outline into styled slide images, an interactive HTML viewer and an optional stitched video from a content-planning partner skill.

    7.8k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes
  • Builds or improves a PowerPoint deck through a seven-role workflow: topic analysis, template choice, content planning, writing, image suggestions, editing and PPTX generation.

    7.8k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Turns a document into a narrated roadshow video through ten staged roles, from document analysis and slide planning to audio, subtitles and final composition.

    7.8k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check: notes
  • PPTX Generator

    anbeime/skill

    产品经理与运营专员在准备汇报展示时,将 JSON 数据一键转换为标准 .pptx 文件。自动应用多种布局、图表与表格样式,快速生成专业 PPT,彻底告别繁琐手工排版,让内容产出与展示更高效!

    7.8k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Adds Remotion-style video transitions and Framer Motion page animations to PPT-based videos and HTML slide viewers, planning the animation sequence first.

    7.8k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check: notes

Questions about AgentKit Shopping Avatar Video

What does AgentKit Shopping Avatar Video do?

Chinese-language skill that produces a 25-second vertical video of a digital shopping-guide avatar for e-commerce, chaining AI image, voice and video generation. Written in Chinese, the skill orchestrates ByteDance's agentkit-samples multimedia tools to build a nine-by-sixteen vertical video of a fixed shopping-guide character recommending a product. It generates the character's portrait and a scene background with AI image generation at a resolution of at least 1080 by 1920, cropped to the vertical ratio, synthesizes the sales script as sixteen-kilohertz mono speech and a matching background music track, then feeds the character image, scene image, voice file, music file and prompts into a video generator that produces five five-second scenes stitched into one 25-second clip.

When should I use AgentKit Shopping Avatar Video?

AgentKit Shopping Avatar Video fits situations like: generating a digital shopping-guide avatar for a livestream or short video; turning a finished sales script into a full product video; generating only the character portrait or only the scene background; preparing a reference image and audio for a companion video-generation skill.

How do I install AgentKit Shopping Avatar Video in Claude Code?

Run `npx skills add anbeime/skill --skill agentkit-multimedia-shopping -a claude-code`. Or copy the skill folder (skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping in anbeime/skill) into .claude/skills/agentkit-multimedia-shopping in your project. Claude Code loads it when a task matches its description.

How do I install AgentKit Shopping Avatar Video in Codex?

Run `npx skills add anbeime/skill --skill agentkit-multimedia-shopping -a codex`. Or copy the skill folder (skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping in anbeime/skill) into .agents/skills/agentkit-multimedia-shopping in your project. Codex loads it when a task matches its description.

Can I use AgentKit Shopping Avatar Video in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anbeime/skill --skill agentkit-multimedia-shopping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentkit-multimedia-shopping, .gemini/skills/agentkit-multimedia-shopping, .github/skills/agentkit-multimedia-shopping and .opencode/skills/agentkit-multimedia-shopping in your project.

What does AgentKit Shopping Avatar Video need to run?

Going by SKILL.md and its folder, AgentKit Shopping Avatar Video needs Python for the scripts in its folder. Our summary lists: Python with Pillow, requests and numpy; ByteDance agentkit-samples installed; API credentials for the image, voice and video services it calls.

Does AgentKit Shopping Avatar Video access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AgentKit Shopping Avatar Video safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AgentKit Shopping Avatar Video use?

No licence was found for AgentKit Shopping Avatar Video or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does AgentKit Shopping Avatar Video use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.4k tokens, read only when the agent opens those files.

What are the alternatives to AgentKit Shopping Avatar Video?

Skills that share tags, products or a category with AgentKit Shopping Avatar Video: Wedding Video Guided Wizard (aaronyi97/wedding-video-guided-wizard, 310 stars), Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 142 stars), Media Gen (clacky-ai/openclacky, 1.2k stars) and Bailian Media Generation (modelstudioai/cli, 542 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AgentKit Shopping Avatar Video?

anbeime (a GitHub user) maintains it in anbeime/skill, which has 7,813 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 10, 2026.

Source: anbeime/skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.