14 food beverage

Skill pixelab-ch/higgsfield-skills/skills/14-food-beverage

Crafts production-grade food and beverage video prompts for Higgsfield and routes to the best model (seedance_2_0 primary, marketing_studio_video fallback). Use when the user wants food videos, recipe content, restaurant promos, beverage ads, cooking videos, food ASMR, menu showcases, food delivery ads, café content, or any food/drink video. Handles text-to-video (default) and optional image-to-video with full prompt assembly, model selection, and parameter validation.From its SKILL.md

Install

npx -y skills add pixelab-ch/higgsfield-skills --skill 14-food-beverage

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.9 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

Higgsfield Food and Beverage Skill

What this skill does

Crafts production-grade food and beverage video prompts and routes them to the best Higgsfield model to make dishes, drinks, and ingredients look irresistible on screen. On request, it assembles the full parameter set, surfaces the credit cost, and — after explicit user confirmation — generates the asset via the opt-in generation flow. Text-to-video is the default path; image-to-video is conditional on the user supplying a reference image.

Model routing

Primary and fallback video models

	seedance_2_0 (primary)	marketing_studio_video (fallback)
Rationale	Genre control (e.g., `drama`, `epic`) for mood-driven food cinematography; supports video and audio references	Dedicated marketing pipeline; use for ad-optimised output
Resolution	`480p`, `720p`, `1080p` (default `720p`)	`480p`, `720p`, `1080p`
Aspect ratios	`auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
Duration	4–15 s (continuous range)	4–15 s (continuous range)
Extra params	`mode` {`std`, `fast`}; `genre` {`auto`, `action`, `horror`, `comedy`, `noir`, `drama`, `epic`}	`generate_audio` bool; optional `folder_id`, `hook_id`, `setting_id`, `ad_reference_id`
Media roles	`image`, `start_image`, `end_image`, `video`, `audio`	`avatars`, `image`, `start_image`, `end_image`

Routing rule: Use seedance_2_0 by default — genre tags such as drama or epic give the model a mood direction that suits fine-dining and cinematic food content. Fall back to marketing_studio_video only when (1) the primary model is unavailable, or (2) the user wants an ad-optimised output with generate_audio or ad reference inputs. If falling back, inform the user of the switch. Never switch silently.

MODEL-06 directive: If a parameter is rejected at generation time, call higgsfield:models_explore with the target model name to re-verify the live schema. Full parameter tables: references/model-specs.md.

Per-platform aspect ratio

Quick rule: 9:16 for TikTok / Reels / Shorts; 16:9 for YouTube and restaurant websites; 1:1 for Instagram and Pinterest. Full per-platform table: references/model-specs.md.

Prompt-building workflow

Gather intent — Confirm: food or beverage type, request category (restaurant promo, packaged product, recipe/how-to, lifestyle/ASMR), target platform, aspect ratio, desired duration, and mood tone (intimate, celebratory, dramatic, cozy).
Select model — Apply the routing table above. Choose seedance_2_0 by default; select marketing_studio_video only when a routing trigger applies.
Build the prompt — Use the craft principles in the references below:
- Opening 2-second hook from references/hooks.md
- Lighting, staging, texture, money-shot techniques from references/food-styling.md
- Worked example prompts by food category and platform from references/examples.md
Present for review — Show the assembled prompt and all parameters to the user for review and refinement before any generation call.

Opt-in generation

Generation costs Higgsfield credits and requires explicit user confirmation before any generate call is made. This skill never auto-generates.

Full step-by-step flow (confirmation gate, balance/cost surface, generate → poll → display): ../../shared/generation-flow.md

This skill's primary model: seedance_2_0

Media upload: Conditional — only when the user supplies a start_image, end_image, or other reference for image-to-video. This skill is NOT a mandatory-I2V skill; T2V is the default path. When a reference image is provided, run the higgsfield:media_upload → higgsfield:media_confirm atomic pair first.

Tool signatures: ../../shared/mcp-tools.md

Reference materials

File	Contents
references/model-specs.md	Per-model parameter tables, aspect ratios, durations, routing rationale for seedance_2_0 and marketing_studio_video
references/food-styling.md	Lighting playbook, money-shot library, colour palettes by cuisine, food styling tricks, movement and action vocabulary, sound/ASMR layering
references/hooks.md	2-second hook framework with 12 proven food/beverage hooks and prompt phrasing
references/examples.md	Master template + 5 full example prompts (fine dining, café latte art, fast-food burger, cocktail bar, croissant bakery)

What ships with it: 4 files

39.9 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most marketing audience skills give in ~1.2k tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

Apply Poppins font to headingsin 41 of 690, across 6 files
Apply Lora font to body textin 41 of 690, across 6 files
Use Arial fallback for headingsin 39 of 690, across 4 files
Use Georgia fallback for body textin 39 of 690, across 4 files
Maintain text hierarchy and formattingin 39 of 690, across 4 files
Use accent colors for non-text shapesin 38 of 690, across 3 files
Use RGB values for precise color matchingin 38 of 690, across 3 files
Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
Use active voice instead of passive voicein 26 of 690, across 10 files
Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

Build the prompt using reference materials
Present the assembled prompt for user review before generation
Obtain explicit user confirmation before making generate calls
Inform the user when switching models
use seedance_2_0 as the primary model
fall back to marketing_studio_video only when routing triggers apply

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.