SkillsAdd

fal-ai-community/skills

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 family's known nuances should be applied. For endpoint selection ("which model for X"), use `fal-models-catalog` instead. This skill is about how to talk to a model once it has been chosen.

First seen May 1, 2026

Installation

$ npx skills add fal-ai-community/skills --skill fal-prompting
View on skills.sh ↗ GitHub repository ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

pi-prompting Similar name
agents365-ai/365-skills

Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for …

2.6K installs
design-first-ui-prompting Similar name
mengto/skills

Use when you need design-first, spec-driven, skimmable prompts for UI generation. Covers prompt…

18 installs
gpt-5-4-prompting Similar name
openai/codex-plugin-cc

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and re…

692 installs
kling-3-prompting Similar name
aedev-tools/kling-3-prompting-skill

Write better prompts for Kling 3.0 AI video generation. Use when the user wants to create, writ…

566 installs
video-prompting Similar name
square-zero-labs/video-prompting-skill

Draft and refine prompts for video generation models (including text-to-video, image/keyframe-t…

448 installs
ai-video-prompting Similar name
guia-matthieu/clawfu-skills 326 installs

Also in this package

Other skills from fal-ai-community/skills · top by installs.

npx skills add fal-ai-community/skills
fal-image-edit 919 cinematography 7 genmedia 435 fal-generate 369 fal-models-catalog 6 fal-audio 300 fal-redesign 289 character-design 283 model-routing 282 fal-upscale 277

Browse all from fal-ai-community/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 237
License MIT
Default branch main
Open issues 2
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,758 B
  • docs SUMMARY.md 505 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 294 installs

SKILL.md

fal.ai Prompting

Runtime: All endpoint calls run via the genmedia CLI. See the genmedia skill for command syntax; run genmedia init once 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](references/kling.md) Working with Kling video models (O3, v3), multi-prompt, element controls, Standard vs Pro tier
[gpt-image-2.md](references/gpt-image-2.md) Working with openai/gpt-image-2 or /edit, structured prompts, EXACT TEXT, multi-image compositing
[happy-horse.md](references/happy-horse.md) Working with alibaba/happy-horse/text-to-video or image-to-video, brevity-first, camera language

Universal principles (all families)

  1. Visual facts beat prestige adjectives. Replace "stunning, cinematic, masterpiece" with "overcast daylight, brushed aluminum, 50mm feel."
  2. Style tags need visual targets. "Minimalist brutalist" → "cream background, heavy black sans serif, asymmetrical type block, generous negative space."
  3. One controlled variable per iteration. Comparison only works when one axis changes at a time.
  4. Inspect schema before assuming a control exists. genmedia schema <endpoint_id> --json. Negative prompt, seed, multi-prompt, and reference-image fields differ across families.
  5. 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](../fal-models-catalog/references/text-to-image.md)
  • Text-to-video endpoint selection → [fal-models-catalog/references/text-to-video.md](../fal-models-catalog/references/text-to-video.md)
  • Image-to-video endpoint selection → [fal-models-catalog/references/image-to-video.md](../fal-models-catalog/references/image-to-video.md)