
fal.ai Skills
SkillOfficial fal.ai skills: agents use the genmedia CLI to call fal's 1,000+ models for text-to-image, image-to-video, voiceover, product shots and ad creatives, and storyboard shorts, with prompting guides per model. Needs a fal.ai account and API key (pay as you go) and the genmedia CLI.
fal.ai Skills
Agent skills for fal.ai. The default execution path is the genmedia CLI: discover an endpoint, inspect its schema, run it, poll status when needed, and download outputs. Most skills in this repo are knowledge layers that tell an agent which endpoint to use, how to prompt it, and how to chain calls.
Compatible with Claude.ai Projects, Claude Code, and other agent platforms supporting the community skills format.
Current system
- Skills live directly under
skills/<name>/. - Each skill has a required
SKILL.mdwithnameanddescriptionfrontmatter. - Larger skills may add
references/files for prompt patterns, endpoint notes, examples, or workflows. skills/index.jsonis the generated registry for the current skill folders.- User-facing model execution should go through
genmediaunless a skill explicitly documents another workflow in its own folder.
Skills
Core
| Skill | Purpose |
|---|---|
| genmedia | The CLI surface. models, schema, run, status, upload, pricing, docs. Every other skill calls genmedia for execution. |
| model-routing | Endpoint-first model defaults for production skills. |
Umbrellas, knowledge organized by modality, family, or use case
| Skill | Purpose |
|---|---|
| fal-models-catalog | Curated endpoint picks across 10 modalities (text-to-image, image-to-image, text-to-video, image-to-video, video-to-video, text-to-3d, image-to-3d, text-to-audio, audio-to-text, image-to-text). |
| fal-prompting | Family-specific prompt craft (Kling, GPT Image 2, Happy Horse). |
| fal-recipes | Use-case pipelines (cinematography, character design, commercial, storytelling, lipsync, restoration, virtual try-on, video with audio, product shot). |
Production skills
| Skill | Purpose |
|---|---|
| character-design | Original characters, identity anchors, reference consistency, and character-driven media. |
| cinematography | Cinematic stills and video direction: shot language, lighting, lens, color, and camera movement. |
| commercial | Product photography, ads, e-commerce batches, product reveal videos, and brand-safe product prompts. |
| marketing | Campaign matrices, launch kits, paid social variants, landing-page visuals, banners, and channel-specific marketing assets. |
| storytelling | Multi-shot narratives, storyboards, brand films, social stories, and sequence continuity. |
| ugc | Creator ads, talking-head clips, testimonials, demos, unboxing, reaction, faceless voiceover, and short vertical social videos. |
Workflow and vertical skills
| Skill | Purpose |
|---|---|
| fal-workflow | Multi-step pipelines. Mode A authors fal.ai workflow JSON; Mode B drives genmedia CLI orchestration. |
| fan-cam | Personalized live sports broadcast fan-cam videos from a user photo with GPT Image 2 and Kling v3. |
| fal-gamedev | 2D pixel-art game assets: characters, sprite sheets, parallax and isometric backgrounds. |
| fal-redesign | Website redesign: screenshot review, vision-driven reference image, build spec, and implementation guidance. |
| fal-regenerate-3d | Interactive 3D character-selector experience with Three.js, Meshy, and Seedance. |
| genmedia-workflow | Genmedia-oriented workflow planning, node rules, pipeline patterns, and reusable recipes. |
Setup
1. Get an API key
2. Install genmedia
Install genmedia from fal-ai-community/genmedia-cli, then run genmedia setup.
3. Install skills
Claude.ai: upload skill .zip files to your project from skills/.
Any project with genmedia installed:
genmedia init
Installs the default skill bundle into .agents/skills/ or .claude/skills/.
Skill format
skills/
└── skill-name/
├── SKILL.md # YAML frontmatter (name, description) + body
└── references/ # optional, for umbrellas
└── *.md
License
MIT
関連リソース

Higgsfield AI Skills
SkillHiggsfield's official skills: generate images, video and voiceover from a single prompt for product shots, e-commerce hero images, YouTube thumbnails, brand guidelines and narrated explainers. Requires the Higgsfield CLI and a signed-in account; generations use account credits.
higgsfield-ai/skills1.3k
genmedia CLI
CLIOfficial agent-first CLI from fal: search and run 1,200+ image, video and speech generation models on fal.ai, check parameters and pricing, upload inputs and download results, with structured JSON output. Good for batch image and promo asset generation. Needs a fal.ai API key, billed per use.
fal-ai-community/genmedia-cli80
Meitu Skills
SkillMeitu's official skills: one prompt gets agents posters, covers, sticker packs, ID photos and multi-angle e-commerce product shots, plus background removal, image restoration, image-to-video and music or voiceover for videos. Needs MeituHub AK/SK keys (free credits for new users) and meitu-cli.
meitu/meitu-skills34
MeiGen AI Design MCP
MCPGenerates product shots, marketing posters and illustrations, removes or swaps backgrounds, upscales and makes videos, with 1,400+ prompt templates and parallel variations. Cloud use needs a MeiGen account and paid credits; the npm version can use OpenAI-compatible APIs or local ComfyUI.
jau123/MeiGen-AI-Design-MCP1.8k
inference.sh Skills
SkillCalls image and video models such as FLUX, Veo and Seedance through inference.sh's belt CLI to generate images, video, avatars and voiceovers, plus guides for thumbnails, storyboards, press releases and social copy. Needs belt and a free inference.sh account; model calls are billed per use.
inference-sh/skills769
Higgsfield
PluginHiggsfield's official Codex plugin: uses its remote MCP to generate images and video from text or photos, like product-shot video ads or animated stills, with built-in flows for faceless narration, voiceover and burned-in captions. Needs a Higgsfield account; billed in credits.
openai/plugins7.5k