Higgsfield Recipes logo

Higgsfield Recipes

Community
OSideMedia
higgsfield-recipes

Use when the user wants a genre-specific scene template, starting point for a type of video (action, horror, romance, product ad, documentary, sci-fi, dance, etc.), or asks for prompt examples for a specific style of content.

Overview

PublisherOSideMedia
Repositoryhiggsfield-ai-prompt-skill
Skill namehiggsfield-recipes
Stars
722
Forks
126
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by OSideMedia on GitHub. Read the source before you install it.

Installation

Install the Higgsfield Recipes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-recipes
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git /tmp/higgsfield-ai-prompt-skill
mkdir -p .claude/skills
cp -r /tmp/higgsfield-ai-prompt-skill/skills/higgsfield-recipes .claude/skills/higgsfield-recipes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Higgsfield Recipes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Higgsfield Recipes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Higgsfield Recipes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Higgsfield Genre Recipe Templates

Each recipe is a ready-to-adapt template. Fill in the bracketed fields with your specific details. All examples are compliant — no real names or IPs.

Style: Anamorphic in these recipes is a single-shot Look-line choice — a standalone generation with no location plate, where the words are the only route to the look (root SKILL.md HARD RULE 7: a style register, never an output ratio). For a multi-shot Seedance sequence that must hold the lens across shots, the lens goes into the location plates instead and the optics words leave the video prompt (../higgsfield-seedance/SKILL.md § Bake it into the asset) — one studio's practice; Hell Grind keeps the look in the prompt too, and which holds better is OPEN (../shared/house-rulings.md P2-6).


Recipe 1: Action / Chase

Core pattern: Establish → Pursuit → Obstacle → Climax Best models: Kling 2.6 Camera: Action Run, FPV Drone, Crash Zoom In, Bullet Time Style: Cinematic or Anamorphic

Template:

[Subject description — clothing, build, energy] sprints through [environment].
Camera: Action Run — low behind them, matching pace.
[Obstacle appears — what is it]. They [dodge action], barely clearing it.
The camera Whip Pans to [pursuer/threat].
Bullet Time as [climax action — punch, leap, collision].
Style: Cinematic, high contrast, [warm/cold] tones. [Aspect ratio].

Example:

A woman in a tactical jacket sprints through a rain-soaked night market,
weaving between stalls and startled vendors.
Camera: Action Run — low behind her, matching her sprint.
A metal gate drops ahead. She slides under it without breaking stride.
Whip Pan to the two men pursuing her through the crowd.
Bullet Time as she leaps from a loading dock onto a moving truck below.
Style: Cinematic, cold blue shadows, amber market light. 16:9.

Recipe 2: Emotional Drama / Character Moment

Core pattern: Establish space → Reveal character state → Emotional beat Best models: Kling 2.6, Kling 3.0 Camera: Dolly In, Arc, Head Tracking, Focus Change Style: Cinematic, Super 8MM

Template:

[Character — appearance, posture, state] is in [intimate environment].
[What they are doing — quiet action revealing emotion].
Camera: slow Dolly In toward [their face / hands / significant object].
[Something shifts — they react, realize, remember].
Style: [Cinematic / Super 8MM], [lighting — golden / overcast / practical only].
[Color grade — warm/cool, contrast level].

Example:

A grey-haired man sits alone at a kitchen table. An old letter in his hands.
He reads slowly, lips barely moving, eyes growing distant.
Camera: slow Dolly In toward his face.
He looks up at the empty chair across from him.
Style: Cinematic. Warm late-afternoon window light, soft shadows.
Slightly desaturated. 16:9.

Recipe 3: Product Advertisement

Core pattern: Texture reveal → Feature showcase → Emotional connection → End frame Best models: Kling 3.0, Nano Banana Pro (for image) Camera: Lazy Susan, Dolly In, Robo Arm Style: Cinematic

Template:

[Product description — no brand name. Color, material, shape, size].
[Setting — surface, environment, lighting setup].
Camera: [Lazy Susan / Robo Arm] revealing [product feature].
[Hero moment — pour, cut, open, glow, activate — macro slow motion].
[Lifestyle context if relevant — who is using it, in what moment].
Style: Commercial ad quality, [clean/warm/dramatic] lighting. [Aspect ratio].
Sound: [product-specific audio cue].

Example:

A matte black insulated travel mug, minimal design, no branding.
Placed on a raw concrete countertop beside a morning window.
Camera: Robo Arm arcing slowly from the base up around to the lid.
Hot coffee pours in — steam rises in a slow macro shot.
A hand wraps around the mug. Close-up of warmth on the palms.
Style: Cinematic commercial, warm neutral tones, soft diffused light. 16:9.
Sound: gentle liquid pour, soft ceramic texture.

Recipe 4: Sci-Fi / Futuristic

Core pattern: World establish → Reveal tech/threat → Action beat Best models: Kling 2.6, Wan 2.5 (not in the API catalog as of the 2026-09-26 snapshot; may be UI-only — verify in the live UI before recommending) Camera: Crane Up, FPV Drone, Super Dolly Out, Dutch Angle Style: Cinematic or Anamorphic Motion presets: Cyborg, Plasma Explosion, Glitch, Wireframe, Portal

Template:

[Futuristic environment — city, facility, space, wasteland].
[Character — description, what they wear, what they carry].
[The situation — what's happening, what's the threat or goal].
Camera: [movement choice — crane up / FPV / orbit].
[Key visual moment — tech activating, weapon firing, transformation].
Style: [Cinematic / Anamorphic], [cold blue / neon / desaturated orange]. [Ratio].
Apply [motion preset] at [moment in scene].

Example:

A battle-worn space station corridor, flickering lights, debris floating in zero gravity.
A soldier in heavy tactical armor drifts along a handrail, rifle raised.
Ahead — a door sealed shut, sparking at the edges.
Camera: FPV Drone drifting ahead of her through the corridor.
She plants an explosive charge. Steps back. Detonation.
Style: Cinematic, cold steel blue, 2.35:1 anamorphic.
Apply Plasma Explosion preset at the moment of detonation.

Recipe 5: Horror / Supernatural

Core pattern: False calm → Wrong detail → Escalation → Reveal Best models: Kling 2.6, Wan 2.5 (not in the API catalog as of the 2026-09-26 snapshot; may be UI-only — verify in the live UI before recommending) Camera: Dolly In, Dutch Angle, Handheld, Crash Zoom In Style: VHS or Cinematic (low key) Motion presets: Horror Face, Raven Transition, Shadow Smoke, Storm Creature

Template:

[Ordinary setting made unsettling — house, street, hospital].
[Character — alone, unaware].
[Wrong detail appears — something that shouldn't be there].
Camera: slow Dolly In toward [the wrong thing].
[Character notices. Reaction.] Camera: Dutch Angle.
Style: [VHS / Cinematic low key], [sickly tones / crushed blacks].
Apply [Horror Face / Raven Transition] preset at the reveal moment.

Example:

An empty suburban house at night. Every light on, but no one visible through the windows.
A woman walks up the front path, keys in hand.
She stops. The front door is already open — just an inch.
Camera: slow Dolly In toward the open door crack.
She pushes it open. The hallway is exactly as she left it. Except the mirror at the end
shows a room that doesn't match. Camera: Dutch Angle.
Style: VHS, desaturated greens, practical light only, 4:3.
Apply Horror Face preset in the mirror reflection.

Recipe 6: Romance / Intimate

Core pattern: Meeting of eyes → Tension → Connection moment Best models: Kling 2.6, Kling 3.0 Camera: Arc, Dolly In, Focus Change, Kiss Style: Cinematic or Super 8MM

Template:

[Two characters — brief appearance note each].
[Setting — intimate, warmly lit, specific].
[The moment — what are they doing, what is the tension].
Camera: [Arc / Dolly In / Kiss control].
[The beat — a look, a touch, a word].
Style: [Cinematic / Super 8MM], [warm golden / soft overcast] light. [Ratio].

Example:

Two people stand on a rooftop terrace at dusk, city glowing below them.
They've been talking for hours — coffee cups empty, leaning toward each other.
A long silence. She looks at him.
Camera: Arc slowly around both of them, city blurring behind.
He reaches over and tucks a strand of hair behind her ear.
Style: Cinematic. Golden hour warm tones, shallow depth of field. 16:9.

Recipe 7: Documentary / Nature

Core pattern: Environment establish → Subject in context → Observational moment Best models: Veo 3, Kling 2.6 Camera: Crane Down, Timelapse Landscape, Dolly Right/Left, Overhead Style: Cinematic (natural grade)

Template:

[Location — specific, vivid, real-feeling].
[Subject — animal, person, phenomenon].
[What is happening — natural behavior, unposed].
Camera: [observational movement — slow pan, timelapse, crane].
[Detail moment — close-up of something specific and visually striking].
Style: Cinematic, natural grade, [time of day], [weather]. [Ratio].
No artificial effects — pure observational documentary feel.

Example:

A fog-covered estuary at dawn. Herons standing motionless in the shallows.
One extends its neck. Still. Then strikes — beak in the water, pulls out a small fish.
Camera: Timelapse Landscape as the fog burns off over 10 minutes.
Close-up: water droplets on feathers catching first light.
Style: Cinematic, natural light, neutral grade. 16:9.

Recipe 8: Dance / Music Video

Core pattern: Establish space → Performance builds → Beat sync climax Best models: Minimax Hailuo 2.3, Kling 2.6 Camera: 360 Orbit, Dolly In/Out on beat, Overhead, Crash Zoom In Style: Cinematic or Anamorphic Motion presets: Glow Trace, Live Concert, Color Rain

Template:

[Dancer/performer — description, outfit].
[Performance space — lighting, scale, atmosphere].
[Dance style / energy — specific movements to describe].
Camera: [movement, ideally synced to beats — orbit, dolly, overhead].
[Climax moment — signature move, camera impact].
Style: [Cinematic / Anamorphic], [color grade — neon / warm / high contrast]. [Ratio].
Apply [Glow Trace / Live Concert] preset for additional visual energy.

Example:

A female dancer in a white flowing dress performs alone in a vast black studio.
Only a single overhead spotlight on her.
She moves through contemporary choreography — slow arms, sudden explosive turns.
Camera: 360 Orbit tightening toward her as the movement intensifies.
Overhead shot as she collapses to the floor in the final beat.
Style: Cinematic, pure black and white contrast, 16:9.
Apply Glow Trace preset — her movement leaves a trail of white light.

Recipe 9: Transformation / Before & After

Core pattern: Before state → Trigger → Transformation → After state Best models: Kling 2.6, Wan 2.5 (not in the API catalog as of the 2026-09-26 snapshot; may be UI-only — verify in the live UI before recommending) Camera: Dolly In to trigger, single continuous shot where possible Style: Varies by tone Motion presets: Animalization, Werewolf, Cyborg, Flame On, Turning Metal, Freezing

Template:

[Subject in their before state — normal, restrained, plain].
[Trigger moment — what causes the transformation].
Camera: [movement toward the trigger moment].
[Transformation unfolds — describe the visual change].
[After state — what they become].
Style: [appropriate to transformation type]. [Ratio].
Apply [preset name] preset to execute the transformation effect.

Example:

A businesswoman in a grey suit stands in a sterile office, staring out the window.
The lights flicker. She turns. Her eyes begin to glow.
Camera: Crash Zoom In on her eyes.
Her suit tears at the shoulders. Her form expands.
Style: Cinematic, cold fluorescent transitioning to deep red. 16:9.
Apply Monstrosity preset for the transformation sequence.

Negative constraints: Before generating from any recipe, check the relevant artifact categories in ../shared/negative-constraints.md. Action recipes → Body/Motion; Horror → Content Filter/Safety; Character-focused → Face/Identity.

Identity vs. Motion: For recipes involving Soul ID characters, split the output into Identity Block + Motion Block. See higgsfield-prompt and higgsfield-soul for the rule and examples.


Related skills

  • higgsfield-prompt — MCSLA formula, Identity/Motion separation
  • higgsfield-camera — Camera controls referenced in recipes
  • higgsfield-motion — Motion presets referenced in recipes
  • higgsfield-style — Visual styles and color grades
  • higgsfield-soul — Soul ID for character-consistent sequences
  • higgsfield-models — Model selection per recipe type
  • templates/ — Annotated prompt templates expand on these recipes with line-by-line breakdowns

Frequently asked questions

What does the Higgsfield Recipes AI skill do?

Use when the user wants a genre-specific scene template, starting point for a type of video (action, horror, romance, product ad, documentary, sci-fi, dance, etc.), or asks for prompt examples for a specific style of content.

Why use Higgsfield Recipes on TypingMind?

Because you install it once and use it with any model. Higgsfield Recipes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Higgsfield Recipes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-recipes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Higgsfield Recipes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Higgsfield Recipes?

As many as you like. As long as a model supports skills, you can use Higgsfield Recipes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Higgsfield Recipes AI skill free?

Yes. It is published on GitHub by OSideMedia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇