Skillget

fal-ai-skill

agent
Security Audit
Fail
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in skills/fal/scripts/create-workflow.sh
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This is a Claude Code plugin that allows you to generate images, video, audio, and other media using the fal.ai platform directly from your development environment.

Security Assessment
Overall Risk: Medium. The tool requires your fal.ai API key to function, which it stores locally in an unencrypted `.env` file in your working directory. The agent executes shell commands to interact with the platform and fetch OpenAPI schemas. It makes external network requests to the fal.ai API to generate media and retrieve model data. While no hardcoded secrets were found, an automated scan flagged a critical issue: a recursive force deletion command (`rm -rf`) exists within a setup script. Although no explicitly dangerous system permissions were requested, the presence of an unguarded `rm -rf` in a shell script introduces a risk of unintended local data loss if mishandled.

Quality Assessment
The project is under the standard MIT license and was actively updated very recently (pushed to 0 days ago). However, it suffers from extremely low community visibility, boasting only 5 GitHub stars. This means the codebase has not been broadly reviewed by the open-source community, making it difficult to gauge its overall reliability or security based on public trust metrics alone.

Verdict
Use with caution due to active maintenance but low community trust and the presence of a risky `rm -rf` shell command.
SUMMARY

Claude code plugin to interact with fal ai

README.md

fal - Claude Code Plugin

License: MIT
Version

Generate images, videos, audio, and more using fal.ai AI models directly from Claude Code.

Installation

/plugin marketplace add analyticalmonk/fal-ai-skill
/plugin install fal@fal-ai-skill

Setup

  1. Get your API key at fal.ai/dashboard/keys
  2. The setup script is interactive - it prompts for your key directly. Run it yourself in the Claude Code prompt:
! bash skills/fal/scripts/setup.sh --add-fal-key

This saves your key to a .env file in your current working directory. The plugin reads it automatically from there.

If you already have a key, you can also create the .env file manually:

echo 'FAL_KEY="your-key-here"' > .env

Capabilities

Category Examples
Image Generation Text-to-image with Flux, NanoBanana, Ideogram
Video Generation Text-to-video with Veo, image-to-video with Kling
Audio Text-to-speech (MiniMax, ElevenLabs), speech-to-text (Whisper)
Image Editing Style transfer, object removal, background replacement, inpainting
Upscaling Image and video upscaling (Aura SR, Clarity, Topaz)
Workflows Chain multiple models into pipelines
Platform Pricing, usage tracking, cost estimation

Quick Start

Just ask Claude naturally:

  • "Generate an image of a mountain landscape"
  • "Create a video of ocean waves"
  • "Convert this text to speech"
  • "Remove the background from this image"
  • "What fal models are available for video generation?"

Model Discovery

The plugin includes the fal MCP server for searching documentation and discovering models. It also provides scripts for fetching exact OpenAPI schemas:

/fal search models for text-to-video
/fal get schema for fal-ai/flux/dev

Troubleshooting

FAL_KEY not set: Run ! bash skills/fal/scripts/setup.sh --add-fal-key in the Claude Code prompt to interactively set your key. It saves to .env in your working directory.

Video generation timeout: Video models can take several minutes. The plugin uses queue mode by default with a 10-minute timeout. For very long tasks, use async mode: /fal generate --mode async --prompt "..." and check status later.

Unknown model parameters: Use /fal get schema for MODEL_ID to see the exact parameters a model accepts. Not all models support all options (e.g., image_size, num_images).

License

MIT

Reviews (0)

No results found