Core Speed Art

Generate video, images, audio, and music using 40+ AI models via fal.ai. Use for video generation (Kling v3, Sora 2, Veo 3.1, LTX 2.3, Pixverse v5), image ge...

Security Scan

The skill's code, runtime instructions, and requested environment (FAL_KEY + uv) align with its stated purpose of driving fal.ai models; nothing in the bundle suggests hidden or unrelated access.

Purpose & Capability

Name/description (multi-model fal.ai media) match the included script and reference docs. The skill requires 'uv' (used to run the included Python script) and FAL_KEY (fal.ai API key), which are reasonable and expected.

Instruction Scope

SKILL.md instructs the agent to run the provided script against fal.ai endpoints and to read the included model reference files — this is within scope. Minor privacy/operational notes: the script prints the first ~200 chars of request args (may expose prompts) and downloads whatever URLs the fal.ai API returns to disk (expected for saving outputs but could fetch arbitrary remote files if the service returns unexpected URLs).

Install Mechanism

The registry listing shows no external install spec, but SKILL.md includes an install hint to 'pip install uv'. The script uses PEP-723 inline metadata (fal-client dependency) so 'uv' will install fal-client at runtime; these are standard PyPI installs (not arbitrary archive downloads). This is moderate-risk compared with no install step but appears proportionate to the skill's needs.

Credentials

Only FAL_KEY is required. That credential is necessary for calling fal.ai and matches the described functionality. No unrelated secrets or config paths requested.

Persistence & Privilege

Skill is not always-enabled and does not request elevated platform privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.

Assessment

This skill appears to do exactly what it says: run a small Python client against fal.ai using your FAL_KEY. Before installing, confirm you want to give the skill access to a fal.ai API key (this allows use/billing on your account). Installing the helper 'uv' will pull packages from PyPI (uv and fal-client) — verify you trust those packages or install them in a controlled environment. Note the script will download whatever URLs the API returns and prints parts of the request JSON (your prompt may be logged to stdout); if you have sensitive prompts or inputs, avoid sending them. If you want extra assurance, review the included scripts/fal.py and the listed references (they are all present and readable) or run the script in an isolated environment first.

Corespeed Art — Multi-Model AI Media via fal.ai

Auth: Set FAL_KEY with your fal.ai API key (get one at https://fal.ai/dashboard/keys).

Workflow

1. Pick a model from the tables below
2. Read its reference file to get the exact endpoint and parameters
3. Run the command with the endpoint and JSON parameters

Usage

uv run {baseDir}/scripts/fal.py ENDPOINT --json '{"param":"value"}' -f output.ext [-i input.ext]

• ENDPOINT — the fal.ai model path from the reference file (e.g. fal-ai/nano-banana-2)
• --json — model parameters as JSON object
• -f — output filename
• -i — input file(s) to upload (repeat for multiple), auto-injected as image_url/image_urls/start_image_url/video_url
• --audio — audio input file (for lipsync)

Image Generation

Model	Best For	Reference
Nano Banana 2	Pro quality, web search, thinking	Read nanobanana.md
FLUX 2 Pro	Photorealistic, zero-config	Read flux.md
FLUX Schnell	⚡ Fastest iteration	Read flux.md
FLUX Pro v1.1	Accelerated, commercial use	Read flux.md
FLUX.1 Dev	12B params, fine-tuning friendly	Read flux.md
GPT Image 1.5	Transparent bg, instruction following	Read gpt.md
Qwen Image 2 Pro	Chinese+English, typography, native 2K	Read qwen.md
Recraft V4 Pro	Design/marketing, color control	Read recraft.md
Seedream 5 Lite	Multi-image editing, reasoning	Read seedream.md

Video Generation

Model	Best For	Reference
Kling v3 Pro I2V	Best I2V, multi-shot, audio, 3–15s	Read kling.md
Sora 2 T2V	Long video up to 20s, characters	Read sora.md
Sora 2 I2V	Image→video with Sora	Read sora.md
Veo 3.1 T2V	Cinematic + native audio/dialogue	Read veo.md
Veo 3.1 I2V	Image→video with audio	Read veo.md
LTX 2.3 T2V Fast	⚡ Fast, up to 2160p/20s, open source	Read ltx.md
LTX 2.3 I2V	Image→video, start+end frame	Read ltx.md
Pixverse v5 I2V	Anime, 3D, clay, cyberpunk styles	Read pixverse.md

Audio / TTS

Model	Best For	Reference
MiniMax Speech-02 HD	30+ languages, loudness normalization	Read minimax-speech.md

Music & Sound Effects

Model	Best For	Reference
Beatoven Music	AI music, up to 90s	Read beatoven-music.md

Utilities

Tool	Best For	Reference
Topaz Upscale	AI image/video upscale 2x–4x	Read topaz.md
BRIA RMBG	Professional background removal	Read bria-rmbg.md
Sync Lipsync	Audio-driven lip sync on video	Read sync-lipsync.md

Notes

• No manual Python setup required. The script uses PEP 723 inline metadata. uv run automatically creates an isolated virtual environment and installs the fal-client dependency on first run.
• fal.ai uses a queue system — the script polls until generation completes.
• Video generation can take 30s–3min.
• Use timestamps in filenames: yyyy-mm-dd-hh-mm-ss-name.ext.
• Script prints MEDIA: line for OpenClaw to auto-attach.
• Do not read generated media back; report the saved path only.