메뉴
General-purpose Gemini assistant for tasks requiring multimodal analysis, long context, or specialized Gemini capabilities. Use when you need to leverage Gemini-specific features.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
/blog-schedule - Manage Post Schedule
Generate a blog post from source materials (text, PDFs, images, transcripts). Use when user wants to create a blog post or article.
Render carousel slides from social/carousel.md into 1080x1350 PNG images.
Push blog posts to Google Docs for review, then pull comments and suggestions back as feedback for discussion.
Generate AI images for content using Gemini or other image generation APIs. Use when user needs diagrams, illustrations, or visual content.
Initialize a new content project with the standard directory structure in projects). Use when user wants to create a new blog post and one doesn't exist for it.
| name | gemini-3 |
| description | General-purpose Gemini assistant for tasks requiring multimodal analysis, long context, or specialized Gemini capabilities. Use when you need to leverage Gemini-specific features. |
Query Google's Gemini 3 models for general-purpose tasks. Specifically configured for Gemini 3 and related Gemini models.
/gemini-3 [prompt]
uv CLI: brew install uv or pip install uvGEMINI_API_KEY environment variable (or set in ~/.content/config.yaml)# Basic query (uses gemini-2.5-pro by default)
uv run .claude/skills/gemini-3/scripts/query.py "Your prompt here"
# With Gemini 3 (when available)
uv run .claude/skills/gemini-3/scripts/query.py "Your prompt here" --model gemini-3-pro
# With image input
uv run .claude/skills/gemini-3/scripts/query.py "Analyze this image" --image path/to/image.png
# With PDF or document input
uv run .claude/skills/gemini-3/scripts/query.py "Summarize this document" --file path/to/document.pdf
# Multiple files
uv run .claude/skills/gemini-3/scripts/query.py "Compare these" --file doc1.pdf --file doc2.pdf --image chart.png
gemini-2.5-pro (default) - Latest available multimodal modelgemini-3-pro - When available, Gemini 3 with advanced reasoninggemini-3-pro-image-preview - For image generation tasksgemini-2.0-flash-exp - Experimental fast modelPrints response to stdout. Use shell redirection to save:
uv run .claude/skills/gemini-3/scripts/query.py "prompt" > output.txt
This skill is named gemini-3 to indicate it's configured for Google's Gemini 3 model family. The script supports multiple Gemini models via the --model parameter, with Gemini 3 being the target model when it becomes available.