skills/image-generation-agent/SKILL.md
Image Generation Agent: Google Gemini-powered image generation tool (Nano Banana / Gemini 2.5 & 3 Flash Image). Use this to generate images from a text prompt, produce low-cost draft previews, or render high-resolution finals at 0.5K, 1K, 2K, or 4K. Use when an agent needs image generation agent, ai image generation, nano banana image creation, google gemini image api, text to image, generate budget image, prompt, aspect ratio through AgentPMT-hosted remote tool calls.
npx skillsauth add AgentPMT/agent-skills image-generation-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Last updated: 2026-06-09.
If the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.
AI image generator powered by Google Gemini 3 Flash Image and "Nano Banana". Create photorealistic product photography, marketing creative, social graphics, app icons, concept art, hero images, and brand assets from a single text prompt — or edit an existing image by passing up to four reference photos for style, subject, or scene guidance. Choose your output tier: a low-cost budget draft for ideation, or crisp 0.5K, 1K, 2K, and 4K final renders for print, ads, e-commerce, and presentation use. Supports 14 aspect ratios including 1:1, 16:9, 9:16, 21:9, 4:5, and ultra-wide 8:1 banner formats. Every generated image is auto-saved to AgentPMT File Manager with a 7-day signed download URL, file_id, width, height, MIME type, and size bytes — ready to drop into chat, hand off to another tool, or pull into a workflow. Built for designers, marketers, e-commerce sellers, content creators, and AI agents that need on-demand visuals without leaving the conversation.
Create images from prompts, or edit an image by adding reference images. Generated images are saved to File Manager and returned with a signed URL that users can open or download directly, plus file_id, MIME type, size, width, and height.
generate_budget_image: Lower-cost drafts, previews, simple assets, or 1024px-class output.generate_image_0_5k: Small high-efficiency output.generate_image_1k: Standard final images.generate_image_2k: Higher-resolution social, presentation, or product assets.generate_image_4k: Highest-resolution final assets.prompt is required for every generation action.aspect_ratio defaults to 1:1.reference_images is optional and accepts up to 4 images.{"source_kind":"file_id","file_id":"<file-id>"}{"source_kind":"url","url":"https://example.com/image.png"}{"source_kind":"base64","base64_data":"<base64>","mime_type":"image/png"}filename is optional. The final extension is inferred from the generated image.expiration_days defaults to 7 and must be from 1 to 7.Only use reference images you have the right to use.
generate_budget_image supports:
1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
High-resolution actions support:
1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9.
Budget text-to-image:
{
"action": "generate_budget_image",
"prompt": "A clean blue circle icon on a white background, flat vector style",
"aspect_ratio": "1:1"
}
High-resolution text-to-image:
{
"action": "generate_image_2k",
"prompt": "A polished product mockup of a reusable water bottle on a white studio sweep",
"aspect_ratio": "16:9",
"filename": "water-bottle-product-mockup"
}
Reference-image edit from File Manager:
{
"action": "generate_image_1k",
"prompt": "Keep the subject and pose. Replace the background with a bright minimalist studio scene.",
"reference_images": [
{
"source_kind": "file_id",
"file_id": "<file-manager-file-id>"
}
],
"aspect_ratio": "3:4"
}
Successful calls return:
{
"success": true,
"action": "generate_image_1k",
"tier": "1k",
"model_tier": "standard",
"aspect_ratio": "1:1",
"image_size": "1K",
"reference_image_count": 0,
"images": [
{
"file_id": "...",
"filename": "...png",
"signed_url": "https://...",
"signed_url_expires_in": 604800,
"content_type": "image/png",
"size_bytes": 123456,
"width": 1024,
"height": 1024
}
],
"text_parts": [],
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0
}
}
Image Generation Agent on AgentPMT.generate_budget_image, generate_image_0_5k, generate_image_1k, generate_image_2k, generate_image_4k.file-management, page: https://clawhub.ai/agentpmt/file-management; skills.sh: npx skills add AgentPMT/agent-skills --skill file-management) - Use this companion skill to inspect, download, upload, and manage files referenced by this product.No categories or industry tags are published for this tool.
Complete generated action schema: ./schema.md.
Supported action count: 5.
x402 availability: not enabled for this product.
generate_budget_image (action slug: generate-budget-image): Create or edit a lower-cost image from a prompt and optional reference images. Use for drafts, previews, and standard 1024px-class outputs. Price: 8 credits. Parameters: aspect_ratio, expiration_days, filename, prompt, reference_images.generate_image_0_5k (action slug: generate-image-0-5k): Create or edit a high-efficiency 0.5K image from a prompt and optional reference images. Price: 10 credits. Parameters: aspect_ratio, expiration_days, filename, prompt, reference_images.generate_image_1k (action slug: generate-image-1k): Create or edit a 1K image from a prompt and optional reference images. Price: 15 credits. Parameters: aspect_ratio, expiration_days, filename, prompt, reference_images.generate_image_2k (action slug: generate-image-2k): Create or edit a 2K image from a prompt and optional reference images. Price: 25 credits. Parameters: aspect_ratio, expiration_days, filename, prompt, reference_images.generate_image_4k (action slug: generate-image-4k): Create or edit a 4K image from a prompt and optional reference images. Price: 40 credits. Parameters: aspect_ratio, expiration_days, filename, prompt, reference_images.Use the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.
agentpmt-tool-search-and-execution with action: "get_schema", and tool_id: "image-generation-agent".agentpmt-tool-search-and-execution with action: "get_instructions" and tool_id: "image-generation-agent", or call this product with action: "get_instructions" when the product tool is already selected.MCP schema lookup through the main AgentPMT MCP server:
{
"method": "tools/call",
"params": {
"name": "AgentPMT-Tool-Search-and-Execution",
"arguments": {
"action": "get_schema",
"tool_id": "image-generation-agent"
}
}
}
For live examples, keep the same MCP tool and use these arguments:
{
"action": "get_instructions",
"tool_id": "image-generation-agent"
}
Authenticated AgentPMT REST schema lookup body:
{
"name": "agentpmt-tool-search-and-execution",
"parameters": {
"action": "get_schema",
"tool_id": "image-generation-agent"
}
}
Authenticated AgentPMT REST live examples body:
{
"name": "agentpmt-tool-search-and-execution",
"parameters": {
"action": "get_instructions",
"tool_id": "image-generation-agent"
}
}
Product slug: image-generation-agent
Marketplace page: https://www.agentpmt.com/marketplace/image-generation-agent
../agentpmt-account-mcp-rest-api-setup to connect the main MCP server or REST API for an Agent Group where this tool is enabled.../what-is-agentpmt for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.If those setup skills are not installed beside this product skill, use the downloads below.
Core AgentPMT setup skills:
openclaw skills install what-is-agentpmtnpx skills add AgentPMT/agent-skills --skill what-is-agentpmtopenclaw skills install agentpmt-account-mcp-rest-api-setupnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setupskills.sh install script:
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
MCP call shape after the main AgentPMT MCP server is connected:
{
"method": "tools/call",
"params": {
"name": "Image-Generation-Agent",
"arguments": {
"action": "generate_budget_image",
"aspect_ratio": "1:1",
"expiration_days": 1,
"filename": "example filename",
"prompt": "example prompt",
"reference_images": [
{
"base64_data": "example base64 data",
"file_id": "example file id",
"mime_type": "image/png",
"source_kind": "file_id",
"url": "https://example.com"
}
]
}
}
}
Use the exact tool name returned by tools/list; the name above is the expected readable form.
Authenticated AgentPMT REST call body:
{
"name": "image-generation-agent",
"parameters": {
"action": "generate_budget_image",
"aspect_ratio": "1:1",
"expiration_days": 1,
"filename": "example filename",
"prompt": "example prompt",
"reference_images": [
{
"base64_data": "example base64 data",
"file_id": "example file id",
"mime_type": "image/png",
"source_kind": "file_id",
"url": "https://example.com"
}
]
}
}
Use the setup skill for the account connection details before making REST calls.
passed or success-style boolean, use it as the workflow gate.get_schema or get_instructions before retrying.generate_budget_image fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.what-is-agentpmt, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: npx skills add AgentPMT/agent-skills --skill what-is-agentpmt)agentpmt-account-mcp-rest-api-setup, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup)tools
Plaud Transcripts Corrected With Your Own Terminology Glossary: Fixes the words your transcription keeps getting wrong, by giving the pipeline your vocabulary instead of hoping a bigger model guesses right. Every speech model mangles terms it has never seen: cell line and reagent names, drug and device names, case and matter numbers, part numbers, local spelling and number conventions, team and client names. Swapping to a different model does not fix this, because none of them have your terms e.
tools
Plaud Spoken Field Notes to a Structured Sheet: Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured details on the job rather than writing them down: window and flooring measurements, equipment specs, inspection findings, punch lists, service call notes. Say the details out loud in the same order each visit (client, room, width, drop, colour, notes) and the workflow reads each new Plaud recordin.
development
Plaud Recordings to Google Calendar Events: Puts the meetings you agree to out loud straight onto your Google Calendar, without Zapier in the middle. Plaud's own app has no Calendar integration, so this closes that gap directly: each new recording is scanned, the transcript pulled, and any genuine scheduling commitment spoken in it ("let's do Tuesday at 3", "I'll come back out Thursday morning") is extracted with the relative date resolved against the recording's own date and your timezone. Eac.
development
One Plaud Recording, Several Differently Formatted Summaries: Gets you past the one-template-per-recording ceiling. The Plaud app applies a single AutoFlow template to a recording, so if you want a short recap for yourself, a decisions-only version for the people who missed it, and a clean action list for your task manager, you are re-running or rewriting by hand. This workflow reads the transcript once and produces every format you have defined in a single pass: you list the output formats you.