Higgsfield prompting
Skill produtoramaxvision/maxvision-utilities/media-forge/skills/higgsfield-prompting
MaxVision's curated Claude Code marketplace — production-grade skills for n8n workflows, Google Tag Manager API, and more.
npx -y skills add produtoramaxvision/maxvision-utilities --skill higgsfield-promptingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 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.
What its author says it does
Copied from the file, not written here
Higgsfield prompting playbook — MCSLA formula, DoP camera verbs, Cinema Studio lens dictionary, Soul ID lifecycle, Marketing Studio templates. Trigger when caller plans a Higgsfield generation.
SKILL.md
5.4 KB, ~1.4k tokens by cl100k_base, as published. Nobody here has run it
Higgsfield Prompting Playbook
1. MCSLA Formula (universal)
Every Higgsfield prompt benefits from these five concentric layers, in order:
| Layer | Question | Example |
|---|---|---|
| M Motion | What moves? | "the bartender slides a glass across the counter" |
| C Camera | How does the lens move? | "crane_up + dolly_in" (DoP verbs) |
| S Subject | Who/what is the focal point? | "a noir-era bartender in mid-thirties, scar under left eye" |
| L Lighting | What kind of light, from where? | "single tungsten bulb above, hard rim from window left" |
| A Aesthetic | What is the emotional / style register? | "1940s Hollywood noir, high contrast, slight bloom" |
Compose in this order; the platform's Soul models tokenise Motion + Camera first, then resolve Subject inside the implied Lighting + Aesthetic frame.
2. DoP Camera Verb Cheatsheet (22 verbs)
| Verb | Use when |
|---|---|
dolly_in | Push closer to subject (heighten intimacy / suspense) |
dolly_out | Pull back to reveal context |
crane_up | Rise above scene (god-view, reveal) |
crane_down | Descend onto subject (introduce / land into action) |
orbit | Circle subject (showcase 360°, build awe) |
crash_zoom | Snap zoom-in (reactive, comedic, jolt) |
bullet_time | Frozen-orbit (Matrix; iconic) |
fpv_drone | First-person drone weave (action / sports) |
handheld | Naturalistic, slight wobble (documentary / vérité) |
whip_pan | Fast horizontal sweep (energy transition) |
tilt_up / tilt_down | Vertical reveal |
pan_left / pan_right | Horizontal reveal |
arc | Arc move (parallax + reveal) |
truck | Sideways tracking (parallel to action) |
pedestal | Vertical lift without tilt (architectural) |
rack_focus | Shift focal plane between foreground / background |
vertigo_effect | Dolly-zoom (Hitchcock — anxiety / dread) |
static | No camera motion (composition is the statement) |
low_angle / high_angle | Static angle modifiers |
Best practice: combine ≤2 verbs per shot. More than 2 collapses into incoherent motion.
3. Cinema Studio 3.5 Lens Dictionary
| Field | Typical Values | Effect |
|---|---|---|
focalLengthMm | 14, 24, 35, 50, 85, 135 | Wide → tele (compression) |
apertureFStop | 1.4, 1.8, 2.0, 2.8, 5.6, 8 | Shallow → deep DOF |
sensorSize | full-frame, super35, apsc, m43, imax | Sensor crop + look |
colorGrading | teal-orange, bleach-bypass, noir, pastel, vibrant, plus free-form | Era / mood |
lensId | e.g. arri-master-prime-35mm, cooke-s4-50mm, zeiss-master-anamorphic-50mm | Specific lens character |
Recipe for "Sundance indie drama":
{ "focalLengthMm": 35, "apertureFStop": 2.0, "sensorSize": "super35", "colorGrading": "bleach-bypass" }
Recipe for "Wes Anderson symmetry":
{ "focalLengthMm": 35, "apertureFStop": 8, "sensorSize": "full-frame", "colorGrading": "pastel", "lensId": "cooke-s4-35mm" }
4. Soul ID Lifecycle Best Practices
- Train once per character — pick 3-7 source images covering frontal, 3/4, profile, varied expression. Training is
250 credits ($9.75 on Plus). - Name aggressively — character name is the lookup key. Use unique distinguishing names: not "Sarah" but "Sarah Nguyen, lead reporter".
- Mark used after every successful generation —
media_higgsfield_soul_id markUsedupdates the LRU. - Audit periodically —
media_higgsfield_soul_id listshows training cost + last_used; archive IDs unused >90 days. - One Soul ID per project character — do NOT train multiple IDs for the same character; consistency degrades.
5. Marketing Studio Template Decision Tree
| Caller intent | Template | Best for |
|---|---|---|
| Show product in use | lifestyle | Casual / aspirational |
| Open the box, reveal item | unboxing | E-commerce, hype |
| Hard-sell with VO | tv-spot | DTC brand launches |
| Showcase texture/material | asmr | Beauty, food, fabric |
| Lateral motion + product flips | hyper-motion | Sneakers, gadgets, drinks |
| Customer talks to camera | testimonial | Trust building |
| Influencer-style POV | ugc | Social commerce |
| Pros vs cons walkthrough | product-review | Tech, comparison |
| Short looped beats | reel | Reels, TikTok, Shorts |
Always include a clean productUrl — the platform crawls product imagery from it.
6. Mode → Tool Map
| Mode requested | Use tool |
|---|---|
| Pure t2v with aesthetic preset | media_higgsfield_soul_id (to fetch ID) + provider generate |
| i2v with camera motion | media_higgsfield_dop |
| Cinematic lens control | media_higgsfield_cinema_studio |
| Talking head (photo + audio) | media_higgsfield_speak |
| Product UGC | media_higgsfield_marketing_studio |
| Swap character in existing video | media_higgsfield_recast |
| Score a candidate | media_higgsfield_virality_predictor |
Gives 0 of the 12 instructions most prompt engineering skills give in ~1.4k tokens
Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06
- ask at most three clarifying questionsin 22 of 563, across 15 files
- respond in the user input languagein 14 of 563, across 9 files
- preserve the original intentin 13 of 563, across 11 files
- Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
- Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
- Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
- Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
- validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
- generate quantitative baseline performance reportsin 12 of 563, across 2 files
- create representative test scenariosin 12 of 563, across 2 files
- treat prompts as codein 12 of 563, across 5 files
- test prompts on diverse inputsin 12 of 563, across 8 files
Said here and by no other author read
- Order prompt layers as motion, camera, subject, lighting, then aesthetic
- Combine no more than two camera verbs per shot
- Use the lens dictionary for cinematic controls
- Train exactly one Soul ID per project character
- Use three to seven source images to train a Soul ID
- Give each Soul ID a unique distinguishing name
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.