image-save
Automatically detects and saves generated images into the /results folder.
Install
mkdir -p .claude/skills/image-save && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13916" && unzip -o skill.zip -d .claude/skills/image-save && rm skill.zipInstalls to .claude/skills/image-save
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
If the user request has a JSON key where type === "image", follow the rules to save the output correctly.Key capabilities
- →Identify JSON keys with type 'image'
- →Generate images based on user requests
- →Save generated images to a specified directory
- →Assign filenames based on job ID
- →Ensure images are saved with a .png extension
How it works
The skill checks user requests for JSON keys marked as 'image' type, then generates the relevant image. It saves the generated image to the 'results/' directory, using the job ID as the filename and ensuring a .png extension.
Inputs & outputs
When to use image-save
- →Saving generated diagrams to disk
- →Managing AI-generated assets
- →Structuring output for image generation tasks
About this skill
Image Save Workflow
Rules
- Even if the user does not explicitly request image generation, if the type contains "image", prioritize this and generate the image most relevant to the user's request.
- After image generation completes, save the output into
results/. - Set the filename to the jobid.
- Always use the
.pngextension.
When not to use it
- →When the user request does not involve image generation
- →When the output format is not an image
- →When images need to be saved with a different extension
Limitations
- →Only saves images with a .png extension
- →Requires the output to be saved in the 'results/' directory
- →Filenames are strictly set to the job ID
How it compares
This skill automates the process of saving generated images with specific naming and formatting conventions, unlike manual saving which requires explicit file management.
Compared to similar skills
image-save side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| image-save (this skill) | 0 | 6mo | No flags | Beginner |
| skills | 0 | 2mo | Review | Beginner |
| gemini-logo-remover | 9 | 8mo | Review | Beginner |
| ai-media | 0 | 3mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
skills
Sergio-prog
Fram is a compact media workshop for the terminal, API, and Telegram. The current primary surface is the `fram` CLI, backed by the same typed processing core used by the API and bot.
gemini-logo-remover
bear2u
Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.
ai-media
arcasilesgroup
Generates images, videos, and audio via AI models (fal-ai MCP): cheap iteration models, expensive production finals, cost-estimate before generation. Trigger for 'generate an image', 'create a thumbnail', 'make a voiceover', 'AI video', 'text to speech for'. Not for design composition; use /ai-visua
t2i
elbruno
This skill teaches AI agents (GitHub Copilot, Claude Code, and MCP-aware assistants) how to use the **t2i** command-line tool for image generation. Learn the commands, workflows, and best practices for automating text-to-image tasks in scripts and terminal environments.
planning-visual-tasks
ShinyGua
v1.2 LLM-driven planner. Turns a natural-language instruction into a structured Plan envelope (`contracts/agent/plan.schema.json`) of typed sub-goals (workflow_search → model_resolve → comfyui_execute → llm_transform → evaluate → mcp_tool → checkpoint → wait_user). Use whenever a user instruction ne
mmx-cli
Anhvu1107
ALWAYS use this when the request matches MMX CLI: Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform.