image-generation · devin-axis — Claude Code skill: what it does, how to install
image-generation generates image assets through the iPolloWork service for slide decks and web pages. Operates directly in chat without opening Image Studio.
LicenseRef-Proprietary ★ 7,523 updated 2026-10-29
npx skills add Devin-AXIS/iPolloWork --skill image-generation -a claude-codeWhat image-generation does
This skill interfaces with the openai-image-generation service under iPolloWork. It first inspects the environment using ipollowork_extension_list_actions and executes the status action to inspect authorization and models. Model selection happens automatically. The agent picks the active model via saved defaults, defaultModel, or the first compatible option. It confirms choices with the user only if models are missing, costs shift drastically, or an explicit choice was requested.
Creation runs through image_generate under ipollowork_extension_call, supplying prompt details such as lighting and camera perspective. The agent stores the resulting asset in the workspace assets folder, then returns a project-relative Markdown image reference. Secrets remain protected. The skill forbids requesting or printing API keys in conversation files. If credentials fail, the workflow reports the state instead of freezing the session.
What it helps with
- create supporting imagery for slides or web blocks
- inspect model capabilities and authorization via the
statusaction - store generated images directly in the project assets folder
- link final graphics via project-relative Markdown syntax
Example prompts for the agent
- Generate a header banner of an office workspace with natural morning sunlight for our landing page
- Create a vector-style illustration of a cloud server setup for the architecture slide
How to install image-generation
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill image-generation -a claude-code2Manually: put the files in place
~/.claude/skills/image-generation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image-generation/
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill image-generation -a codex2Manually: put the files in place
.agents/skills/image-generation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill image-generation -a cursor2Manually: put the files in place
.cursor/skills/image-generation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Devin-AXIS/iPolloWork .agents/skills/image-generation2Manually: put the files in place
.github/skills/image-generation/SKILL.md1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill image-generation -a gemini-cli2Platform CLI
gemini skills install https://github.com/Devin-AXIS/iPolloWork --path .agents/skills/image-generationManually: put the files in place
.devin/skills/image-generation/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about image-generation
How to install image-generation in Claude Code?
Run npx skills add Devin-AXIS/iPolloWork --skill image-generation -a claude-code. The skill configuration saves to ~/.claude/skills/image-generation/SKILL.md.
What does the image-generation skill do?
It queries openai-image-generation inside iPolloWork, evaluates valid models, and triggers image_generate. It saves the finished asset to the project directory and returns a Markdown link.
Do I need to provide an API key in the chat?
No, the skill strictly prohibits pasting or requesting API tokens inside chat sessions or workspace files. It verifies access through the extension status check.
Similar skills
All skills for Design →image-generation by other authors comes first.