higgsfield（higgsfield 搜索）

Higgsfield AI Prompt Skill

Language rule: Reply in whatever language the user writes in.

MANDATORY WORKFLOW — do these in order, every time

For ANY Higgsfield-related request, follow this contract:

1. Route the request. Match the user's ask to the routing table in the "Route to the Right Skill" section below, and open the matching sub-skill file(s) with the read tool BEFORE writing any prompt or advice. Do not rely on prior knowledge — platform vocabulary, preset names, and model parameters must be read fresh from the skill files, because this platform's lineup changes between releases.
2. Apply MCSLA (Model · Camera · Subject · Look · Action) to every video prompt unless the user explicitly opts out. Full definition lives in skills/higgsfield-prompt/SKILL.md.
3. Use named platform vocabulary only. Camera names, motion presets, and style tokens must come from vocab.md or the relevant sub-skill. Do not invent terms the platform doesn't recognize — invented names silently degrade generations without warning.
4. Append shared negative constraints from skills/shared/negative-constraints.md before delivering any prompt.
5. On the first Higgsfield response in a conversation, state ONE short line naming which sub-skill you're routing to. Example: "Routing to higgsfield-prompt + higgsfield-camera for a cinematic chase." One line only, then proceed with the work.

HARD RULES (do not skip under any circumstances)

• NEVER write a Higgsfield prompt without reading at least skills/higgsfield-prompt/SKILL.md first in the current conversation.
• NEVER substitute generic video-prompt vocabulary for named Higgsfield presets.
• NEVER skip MCSLA structure on video prompts.
• NEVER invent model versions, camera presets, or motion preset names. If the user names one you don't see in the skill files, say so and ask for clarification.
• If you find yourself thinking "I already know how to do this from training" — stop. Read the file. Your training data for this platform is stale.

What Is Higgsfield?

Higgsfield is a cinematic AI video and image generation platform built for filmmakers and creators. Unlike single-model tools, Higgsfield hosts multiple generation engines on one platform — Kling 3.0/3.0 Omni/3.0 Motion Control, Sora 2, Google Veo 3.1/3.1 Lite, Wan 2.7/2.6/2.5, Seedance 2.0/Pro, Minimax Hailuo 2.3/02, Higgsfield DoP (Lite/Standard/Turbo) for video; Soul 2.0, Soul Cinema Preview, Soul Cast, Nano Banana Pro/2, Kling Image 3.0/Omni, Seedream 4.0, GPT Image 1.5, Flux 2/Kontext for images — plus a library of 100+ named Motion Presets, a Soul ID character consistency system, Cinema Studio 2.5, Cinema Studio 3.0 (Business/Team plan), and Cinema Studio 3.5 with Soul Cast AI actors, native dual-channel stereo audio, and 80+ one-click Apps.

Workflow

Fast Path — Simple Creative Requests

If the user provides a clear creative intent ("write me a prompt for a car chase at night") with no specific constraints, generate immediately using these sensible defaults:

Fast Path still requires reading skills/higgsfield-prompt/SKILL.md first — Fast Path means skip clarifying questions, NOT skip the file read.

Do not ask clarifying questions. Deliver a ready-to-paste prompt. Mention the defaults used so the user can adjust if they want something different.

If you did not read skills/higgsfield-prompt/SKILL.md earlier in this conversation, read it now before writing the prompt.

Full Path — Production Requests

When the user signals production-grade intent (Cinema Studio, multi-shot, specific model, budget constraints, client work), confirm before generating:

Required:

• Generation type: Image / Video / App (one-click)
• Video duration: 5s / 10s (image-to-video clips are 3–5s; text-to-video up to 10s+)
• Aspect ratio: 16:9 / 9:16 / 1:1 / 4:5 / 4:3 / 2.35:1 (default: 16:9)
• Model preference (or ask Claude to recommend — see skills/higgsfield-models/SKILL.md)

Optional (skip if user already provided):

• Visual style: Cinematic / VHS / Super 8MM / Anamorphic / Abstract
• Soul ID character reference (if character consistency needed)
• Reference image for image-to-video
• Motion preset preference

Ask everything in one message — do not split across multiple rounds.

Route to the Right Skill

Check Templates for Genre Match

Before writing a prompt from scratch, check if the user's request matches a common genre pattern. The templates/ folder contains 10 annotated example templates with line-by-line breakdowns, recommended models, negative constraints, and variations.

Use the template as a starting point — adapt the example prompt to the user's specific request. The annotations explain WHY each element works, helping you make informed substitutions.

Build the Prompt Using the MCSLA Formula

Full MCSLA definition and prompt structure → skills/higgsfield-prompt/SKILL.md

Quick summary — five layers, every prompt:

Core rules:

• Be specific — name camera presets, describe VFX concretely
• Keep prompts under 200 words
• Subject → Action → Camera → Style is the most reliable order

Output Format

Single prompt:

**Model**: [model name]
**Aspect ratio**: [ratio]  **Duration**: [Xs]  **Style**: [style]

[Prompt]

**Camera**: [camera control name]
**Motion preset** (if used): [preset name]

Two versions (when style varies):

### Version 1 — [Style Name]
[Prompt]

---
### Version 2 — [Style Name]
[Prompt]

Output rules:

• Output a clean, ready-to-paste prompt — no meta-commentary after
• Do not explain what every line does unless the user asks
• Always name the camera control and motion preset explicitly

@ Reference Rules

• User uploads image: use [reference image] or describe it as "the provided reference"
• For Soul ID character: note "using Soul ID character reference" in the prompt
• For video extension: note "extend from [reference video], continue with..."
• For style transfer: note "match the visual style of [reference image]"

Shared Resources

Sub-Skills (auto-loaded as needed)

Full vocabulary in vocab.md Full motion preset library in skills/higgsfield-motion/SKILL.md Model comparison in model-guide.md Example prompts in prompt-examples.md Shared negative constraints in skills/shared/negative-constraints.md Genre-specific annotated templates in templates/