Token导航 LogoToken导航

Agent Skill · 待分类

media-generation(媒体一代)

media-generation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

media-generation 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在待分类类的 11,208 个 Skill 里排第 2,075。

总安装 1,905周安装 81GitHub Stars 5下载 667核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:media-generation(媒体一代)
来源仓库:https://github.com/merit-systems/agentcash-skills
仓库路径:skills/media-generation
安装命令:
npx skills add https://github.com/merit-systems/agentcash-skills --skill media-generation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/merit-systems/agentcash-skills --skill media-generation

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

media-generation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。通过 npx skills add 命令从指定仓库安装并使用该技能。

安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/media-generation

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/merit-systems/agentcash-skills --skill media-g…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

media-generation 怎么安装?

在终端执行 npx skills add https://github.com/merit-systems/agentcash-skills --skill media-generation。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

media-generation 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

media-generation 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

media-generation 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

media-generation 用的人多吗?

公开数据是累计安装 1,905 次,近一周安装 81 次,下载 667 次,GitHub 5 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

media-generation 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
media-generation

媒体一代 · 本页

1,9055需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Media Generation with StableStudio

Generate images and videos via x402 payments at https://stablestudio.dev.

Setup

If the agentcash CLI is not yet installed, see rules/getting-started.md for installation and wallet setup.

Quick Reference

Image Models

ModelEndpointCostTimeEdit?
nano-banana-pro (default)nano-banana-pro/generate$0.13-0.24~10sYes
nano-banananano-banana/generate$0.039~5sYes
gpt-image-1.5gpt-image-1.5/generate$0.009-0.20~3sYes
gpt-image-1gpt-image-1/generate$0.011-0.25~10sYes
grokgrok/generate$0.07~3sYes
flux-2-proflux-2-pro/generate$0.05-0.06~5sYes

All endpoints are prefixed with https://stablestudio.dev/api/generate/. Edit endpoints use /edit instead of /generate.

Video Models

ModelEndpointCostTime
veo-3.1 (default)veo-3.1/generate$1.60-3.201-2min
veo-3.1-fastveo-3.1-fast/generate$0.40-0.80~30s
grok-videogrok-video/generate$0.15-0.75~17s
seedanceseedance/t2v or seedance/i2v$0.33-0.99~1min
seedance-fastseedance-fast/t2v or seedance-fast/i2v$0.04-0.12~40s
wan-2.6wan-2.6/t2v or wan-2.6/i2v$0.34-1.022-5min
sora-2sora-2/generate$0.40-1.201-3min
sora-2-prosora-2-pro/generate$3.00-12.502-5min

Image Generation

Default: nano-banana-pro. This is the best image model by far — highest quality, supports up to 4K, and the cost is reasonable. Always use nano-banana-pro unless the user specifically requests a different model or has a strong reason to use something else (e.g., budget constraints, needing ultra-wide aspect ratios from grok).

npx agentcash@latest fetch https://stablestudio.dev/api/generate/nano-banana-pro/generate -m POST -b '{
  "prompt": "a cat wearing a space helmet, photorealistic",
  "aspectRatio": "16:9",
  "imageSize": "2K"
}'

nano-banana-pro options:

  • aspectRatio: "1:1", "16:9", "9:16"
  • imageSize: "1K", "2K", "4K"

Other Image Models

gpt-image-1.5 -- Fastest, cheapest per-image. Uses quality and size instead of aspect ratio:

npx agentcash@latest fetch https://stablestudio.dev/api/generate/gpt-image-1.5/generate -m POST -b '{
  "prompt": "a watercolor painting of a mountain lake",
  "quality": "high",
  "size": "1536x1024"
}'

Options: quality: "low"/"medium"/"high". size: "1024x1024", "1536x1024", "1024x1536". Same schema for gpt-image-1.

grok -- Fast, wide aspect ratio support. Note: uses aspect_ratio (underscore):

npx agentcash@latest fetch https://stablestudio.dev/api/generate/grok/generate -m POST -b '{
  "prompt": "neon cyberpunk cityscape at night",
  "aspect_ratio": "16:9"
}'

Options: aspect_ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "2:1", "1:2", "19.5:9", "9:19.5", "20:9", "9:20".

flux-2-pro -- High quality with resolution control:

npx agentcash@latest fetch https://stablestudio.dev/api/generate/flux-2-pro/generate -m POST -b '{
  "prompt": "editorial photo of a vintage car in golden hour light",
  "aspect_ratio": "3:2",
  "resolution": "2 MP"
}'

Options: aspect_ratio: "1:1", "16:9", "9:16", "3:2", "2:3", "4:5", "5:4", "4:3", "3:4". resolution: "0.5 MP", "1 MP", "2 MP".

nano-banana -- Budget option ($0.039). Same schema as nano-banana-pro but without imageSize.

Video Generation

Recommended: veo-3.1 (best quality)

npx agentcash@latest fetch https://stablestudio.dev/api/generate/veo-3.1/generate -m POST -b '{
  "prompt": "a timelapse of clouds moving over mountains",
  "durationSeconds": "6",
  "aspectRatio": "16:9"
}'

veo-3.1 options:

  • durationSeconds: "4", "6", "8"
  • aspectRatio: "16:9", "9:16"

veo-3.1 also supports frame interpolation -- animate between a start image and end image by providing image and lastFrame blob URLs in the body.

veo-3.1-fast -- Same schema as veo-3.1, 4x cheaper, ~30s instead of 1-2min.

Other Video Models

seedance -- Good quality with audio generation support. Use seedance/t2v (text-to-video) or seedance/i2v (image-to-video):

npx agentcash@latest fetch https://stablestudio.dev/api/generate/seedance/t2v -m POST -b '{
  "prompt": "a bird taking flight from a branch in slow motion",
  "duration": "8",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": false,
  "camera_fixed": false
}'

Options: duration: "4"-"12". resolution: "480p", "720p", "1080p". aspect_ratio: "16:9", "9:16", "4:3", "3:4", "1:1", "21:9". For i2v, add "image": "https://blob-url..." and omit generate_audio/camera_fixed.

seedance-fast -- Same schema, 8x cheaper, slightly lower quality.

grok-video -- Cheapest short video option:

npx agentcash@latest fetch https://stablestudio.dev/api/generate/grok-video/generate -m POST -b '{
  "prompt": "a candle flame flickering",
  "duration": "6",
  "resolution": "720p",
  "aspect_ratio": "16:9"
}'

Options: duration: "3", "6", "9", "12", "15". resolution: "480p", "720p". aspect_ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3".

wan-2.6 -- Budget, supports t2v and i2v. duration: "5", "10", "15". t2v uses size ("1280*720", "720*1280", "1920*1080", "1080*1920"); i2v uses resolution ("720p", "1080p") and image.

sora-2 -- seconds: "4", "8", "12". size: "1280x720", "720x1280".

sora-2-pro -- Premium. seconds: "10", "15", "25". size: "1280x720", "720x1280", "1792x1024", "1024x1792".

Job Polling

Generation returns a jobId. Poll until complete:

npx agentcash@latest fetch https://stablestudio.dev/api/jobs/{jobId}

Poll images every 3s, videos every 10s. Result contains imageUrl or videoUrl. fetch handles both paid submission requests and free SIWX polling requests.

Image Editing

Requires uploading the source image first. See rules/uploads.md.

All image models support /edit. The edit endpoint accepts images (array of blob URLs) plus a prompt.

npx agentcash@latest fetch https://stablestudio.dev/api/generate/nano-banana-pro/edit -m POST -b '{
  "prompt": "change the background to a beach sunset",
  "images": ["https://...blob-url..."]
}'

Grok edit also supports aspect_ratio. GPT-image edit uses the same quality/size options as generate.

Model Comparison

Image Models

ModelCostSpeedBest For
nano-banana-pro$0.13-0.24~10sGeneral purpose, up to 4K resolution
nano-banana$0.039~5sQuick drafts, budget
gpt-image-1.5$0.009-0.20~3sFastest, cheapest (quality varies)
gpt-image-1$0.011-0.25~10sHigher quality GPT images
grok$0.07~3sFast, many aspect ratios
flux-2-pro$0.05-0.06~5sHigh quality, resolution control

Video Models

ModelCostSpeedBest For
veo-3.1$1.60-3.201-2minBest quality, interpolation
veo-3.1-fast$0.40-0.80~30sQuick high-quality video
grok-video$0.15-0.75~17sCheapest short videos
seedance$0.33-0.99~1minGood quality, audio support
seedance-fast$0.04-0.12~40sBudget video with decent quality
wan-2.6$0.34-1.022-5minBudget, text or image input
sora-2$0.40-1.201-3minPremium quality
sora-2-pro$3.00-12.502-5minHighest quality, longest duration

平台分布

Codex

38.48%
按下载量换算257

Claude

30.19%
按下载量换算201

Cursor

17.39%
按下载量换算116

Gemini CLI

8.57%
按下载量换算57

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills