Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问许可证需确认审计提醒

gemini-genGemini GEN 命令行

Agent Skill

gemini-gen 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。

总安装

374

周安装

15

GitHub Stars

7

下载量

121
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:gemini-gen(Gemini GEN 命令行)
来源仓库:https://github.com/arcocodes/renoise-plugins-official
仓库路径:skills/gemini-gen
安装命令:
npx skills add https://github.com/arcocodes/renoise-plugins-official --skill gemini-gen
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/arcocodes/renoise-plugins-official --skill gemini-gen

简介

用于处理 GitHub 仓库、Issue 和 Pull Request 协作信息。

  • 适合围绕代码变更、仓库状态进行整理和协作管理。
  • 通过 GitHub 安装,建议确认权限范围和命令执行边界。
  • 可能触发联网、文件读写等操作,需评估安全风险。
  • 适用于 Codex、Claude、Cursor 和 Gemini CLI 开发场景。

SKILL.md

Gemini Gen — Visual Understanding & Multimodal Analysis

Gemini 3.1 Pro via Renoise gateway. Zero npm dependencies, native fetch only. Handles files of any size automatically — small files are sent inline, large files (>20MB) are uploaded first.

Quick Start

# Analyze a product photo
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file photo.jpg --mode product

# Extract a video script with timestamps
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file clip.mp4 --mode video-script

# Extract visual style keywords from a reference
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file reference.jpg --mode style

# Free-form analysis
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file photo.jpg "Describe this image in detail"

Analysis Modes

Preset modes auto-select optimal resolution and output format. Use --mode for common tasks instead of writing custom prompts.

Product Analysis (--mode product)

Analyzes product photos and returns structured JSON with type, color, material, selling points, brand tone, and scene suggestions. Auto-selects high resolution for maximum detail.

node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file product.jpg --mode product

Output:

{
  "type": "resistance loop bands",
  "color": "Pink 10lb, Blue 15lb, Mint green 20lb",
  "material": "TPE elastic, matte finish",
  "selling_points": ["3 resistance levels", "foldable and portable", "pastel color scheme"],
  "brand_tone": "Youthful athletic, trendy fitness",
  "scene_suggestions": ["living room workout", "hotel room fitness", "outdoor park"]
}

Video Script Extraction (--mode video-script)

Watches a video and outputs timestamped dialogue, scene descriptions, and camera movements. Auto-selects low resolution to reduce token consumption.

node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file clip.mp4 --mode video-script

Style Extraction (--mode style)

Extracts visual style keywords from a reference image or video: color palette, lighting, camera language, composition, and mood.

node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file reference.jpg --mode style

CLI Usage

# Text only
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs "Explain quantum computing"

# Analyze an image (high resolution for product detail)
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file photo.jpg --resolution high "Describe this product"

# Analyze a video (low resolution to save tokens)
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file clip.mp4 --resolution low "Summarize this clip"

# Multiple images
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file a.jpg --file b.jpg "Compare these two"

# JSON output mode
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --json "Return a JSON object with name and age"

Options

FlagDefaultDescription
--file <path>Attach local file (repeatable). Files >20MB auto-uploaded
--file-uri <uri>Attach uploaded file by URI (requires --file-mime)
--file-mime <mime>MIME type for --file-uri
--resolution <level>mediumlow / medium / high / ultra_high
--model <name>gemini-3.1-proModel name
--temperature <n>1.0Temperature
--max-tokens <n>8192Max output tokens
--jsonoffRequest JSON response format
--mode <name>Preset analysis mode: product, video-script, style

Resolution Levels

mediaResolution controls token allocation per image/frame:

LevelImage TokensVideo Frame TokensBest For
low28070Bulk processing, video analysis
medium560140General use (default)
high840210Product photos, fine text
ultra_high1120280Extreme detail

Large File Handling

Files larger than 20MB are automatically uploaded before analysis — no manual steps needed. The upload goes through the Renoise file gateway and returns a temporary URL (valid for 1 hour).

# This just works — the script detects file size and auto-uploads if needed
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file large-video.mp4 "Analyze this video"

For manual uploads (e.g. reusing the same large file across multiple calls):

# Upload once
FILE_URL=$(node ${CLAUDE_PLUGIN_ROOT}/skills/renoise-gen/scripts/upload.mjs large-video.mp4)

# Use the URL in multiple calls
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file-uri "$FILE_URL" --file-mime video/mp4 "Summarize"
node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file-uri "$FILE_URL" --file-mime video/mp4 "Extract dialogue"

When to Use vs When Not

Use gemini-gen forUse renoise-gen for
Analyzing product photosGenerating images
Understanding video contentGenerating videos
Extracting scripts from videoText-to-video / image-to-video
Comparing visual assetsProduct design sheets
OCR / text extractionScene backgrounds
Describing scenes for prompts

API Reference (Advanced)

Endpoint

POST https://renoise.ai/api/public/llm/proxy/v1beta/models/{model}:generateContent?key={RENOISE_API_KEY}

Request Format

{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "inlineData": { "mimeType": "image/jpeg", "data": "<base64>" }, "mediaResolution": { "level": "media_resolution_high" } },
        { "text": "Describe this image" }
      ]
    }
  ],
  "generationConfig": {
    "temperature": 1.0,
    "maxOutputTokens": 8192
  }
}

Supported MIME Types

ExtensionMIME TypeMax Inline
.jpg/.jpegimage/jpeg20MB
.pngimage/png20MB
.webpimage/webp20MB
.gifimage/gif20MB
.mp4video/mp420MB
.movvideo/quicktime20MB
.webmvideo/webm20MB

Error Handling

  • 400: Bad request (check prompt format)
  • 403: Invalid API key
  • 429: Rate limited (wait and retry)
  • 500: Server error (retry with backoff)

Authentication

Environment variable RENOISE_API_KEY. Get one at: https://www.renoise.ai

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.15%
按下载量换算39

Claude

29.72%
按下载量换算36

Cursor

19.23%
按下载量换算23

Gemini CLI

9.48%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills