Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

FAL Image Generate & Edit (Proxied)

Calls any FAL image model (nano-banana edit, flux, gpt-image...) through an internal billing proxy to produce ad keyframes and product hero edits.

Image & VideoAdvanced★ 1,230⑂ 212AI score 5/10Last updated: Oct 3, 2026

What it does

  • Gives one uniform calling convention for many FAL image models: nano-banana/edit, flux, the gpt-image family, and more.
  • Forces every paid call through the bundled media_proxy.py (GooseWorks proxy) instead of a provider SDK's default host, so spend is billed to the Ads agent.
  • Runs as gen_image.py --model ... --payload '{...}' --out keyframe.png and returns a public *.fal.media URL.
  • Model name and prompt come from the template recipe in the DB, keeping the capability itself model-agnostic.
  • If a recipe needs a creator/avatar still, it must read the bundled references/avatar-generation.md first; if the guide can't be opened, it stops and names the missing file.

Who it's for

  • Teams running a FAL-based ad image pipeline where models change often.
  • Organizations that must tightly control billing routes and retry policy for paid generations.
  • Users already on the GooseWorks agent stack with an MCP upload → presign flow.

Example uses

  1. Generate a video ad keyframe with the recipe's flux model, then pass the returned *.fal.media URL downstream.
  2. Edit a product hero shot: upload a local photo via MCP to get a public URL, feed it as image_urls to nano-banana/edit to swap background/lighting.
  3. Transform a flat packaging cover into an angled mockup for thumbnails.

Note: without the internal proxy, recipe DB and MCP upload, this skill won't work as written.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/gooseworks-ai/goose-skills/HEAD/skills/ads/capabilities/create-image-fal/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/ads/capabilities/create-image-fal folder from the GitHub repo gooseworks-ai/goose-skills into my ~/.claude/skills/create-image-fal/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/gooseworks-ai/goose-skills.git && mkdir -p ~/.claude/skills && cp -r goose-skills/skills/ads/capabilities/create-image-fal ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/gooseworks-ai/goose-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r goose-skills/skills/ads/capabilities/create-image-fal ~/.claude/skills/
  5. Verify gen_image.py, media_proxy.py and references/avatar-generation.md landed in the copied folder; if missing, copy them from the parent directory too.
  6. Set the proxy endpoint and auth environment variables needed for FAL calls (internal team values required).
  7. Restart Claude Code and try a prompt like "Edit this product hero image with FAL" to confirm the skill loads.
View source on GitHub ↗License: MIT