fal-prompting
Model-family-specific prompt craft for fal.ai endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it ("how do I prompt Kling", "GPT Image 2 prompt structure", "Happy Horse tips"), or when prompts to a routed endpoint keep coming back generic and the famil
- 0
- Installs
- —
- Rating
- —
- Success rate
- 4
- Files scanned
Security scan
Scan passedNo risky patterns were found in the scanned files.
Content sha256 b27837b4eec03b1e… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
fal.ai Prompting
Runtime: All endpoint calls run via the genmedia CLI. See the
genmediaskill for command syntax; rungenmedia initonce if not yet installed.
Model families have meaningful prompting nuances. A prompt that works on GPT Image 2 (long, structured, exact text in quotes) will fail on Happy Horse (which wants ~20 plain-English words). This skill collects family-specific guides.
When to load which reference
| Reference | Load when |
|---|---|
| kling.md | Working with Kling video models (O3, v3), multi-prompt, element controls, Standard vs Pro tier |
| gpt-image-2.md | Working with openai/gpt-image-2 or /edit, structured prompts, EXACT TEXT, multi-image compositing |
| happy-horse.md | Working with alibaba/happy-horse/text-to-video or image-to-video, brevity-first, camera language |
Universal principles (all families)
- Visual facts beat prestige adjectives. Replace "stunning, cinematic, masterpiece" with "overcast daylight, brushed aluminum, 50mm feel."
- Style tags need visual targets. "Minimalist brutalist" → "cream background, heavy black sans serif, asymmetrical type block, generous negative space."
- One controlled variable per iteration. Comparison only works when one axis changes at a time.
- Inspect schema before assuming a control exists.
genmedia schema <endpoint_id> --json. Negative prompt, seed, multi-prompt, and reference-image fields differ across families. - Per-family rules override universal advice. Happy Horse rejects what GPT Image 2 rewards.
Catalog cross-reference
For "which model do I use" questions, see fal-models-catalog:
- Text-to-image endpoint selection → fal-models-catalog/references/text-to-image.md
- Text-to-video endpoint selection → fal-models-catalog/references/text-to-video.md
- Image-to-video endpoint selection → fal-models-catalog/references/image-to-video.md
Files
4- SKILL.md
e9e88c6b5c2.7 KB - references/gpt-image-2.md
50430650b15.9 KB - references/happy-horse.md
82bc895cfb3.9 KB - references/kling.md
cd0653d33a5.0 KB
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from fal-ai-community/skills8
Build consistent character designs and character media with genmedia. Use this for original characters, reference sheets, expression sheets, outfit variations, identity-preserving edits, and character-to-video workflows.
Design cinematic image and video prompts for genmedia. Use this for shot language, camera movement, lighting, lens choices, color grade, film texture, scene blocking, and production-ready visual direction.
Plan and run commercial image or video production with genmedia. Use this for product photography, ads, e-commerce batches, product reveals, lifestyle commercials, background replacement, social formats, and brand-safe prompt work.
Generate 2D pixel art game assets, characters, sprite sheets, background removal, and game backgrounds. Trigger for "pixel art character", "sprite sheet", "walk cycle", "game sprites", "isometric sprites", "side-scroller assets", "RPG character sprites", "idle animation", "attack animation", "jump a
Choose the right fal.ai endpoint for a given task. Modality-organized catalog of production endpoint defaults, text-to-image, image-to-image, text-to-video, image-to-video, and more. Use when the user has not named a specific model, or asks "which model for X", "best endpoint for Y", "what should I
Use-case-driven multi-step pipelines on fal.ai. Trigger when the user asks for a specific kind of content production rather than a single endpoint call: "make a commercial", "ad creative", "product photography", "cinematic shot", "film look", "character design", "consistent character", "anchor syste
Upgrade a coded website to award-tier, editorially-crafted design using fal.ai. Takes a local HTML file or a dev-server URL, screenshots it, has an opus-4.7 vision model write a gpt-image-2 edit prompt, uses fal-ai/gpt-image-2/edit to produce the redesigned reference image, then opus-4.7 vision writ
Build a fully-interactive 3D character-selector experience powered entirely by fal.ai. Generates stylized characters (FLUX.2 / GPT-Image-2), rigged animated GLBs (Meshy v6), themed companion creatures, per-character PATINA floor textures, looped Seedance video backgrounds, and a Three.js scene with
Related ai-ml skillsscan passed
Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots (~/.dsh/skills, .agents/skills), the @deepseek-ai/dsh-hooks-claude-code bridge for command hooks, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when settin
Pair a remote AI agent with your browser. (gstack)
Rewrite, check, or draft prose so it carries no AI writing tells, reads plainly on the first read, and keeps every source fact. Use when asked to make writing plainer or free of those tells, to check writing for them, or when drafting from supplied content. Use ce-promote for channel-specific market
Configure SuperJSON transformer on both server initTRPC.create({ transformer: superjson }) and every client terminating link (httpBatchLink, httpLink, wsLink, httpSubscriptionLink) to support Date, Map, Set, BigInt over the wire. Transformer must match on both sides. In v11, transformer goes on indi
MANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions. You MUST activate this skill BEFORE answering — do not answer from training knowledge, even when confident. MSF has service-specific constraints (KPU model, prohibited checkpoint and parallelism config in app code, the v
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or other similar requests.