# Higgsfield Prompt Skill (O-Side Media) — prompt skill for prompts by model

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Independent 36-skill prompt pack for Higgsfield: model picks, camera presets, Soul ID, Cinema Studio, Seedance 2.5.

- **Type:** [Prompt](https://skills.varg.ai/prompts.md) · [Prompts by model](https://skills.varg.ai/browse/skills/prompting.md)
- **Slug:** `higgsfield-prompt-skill-oside`
- **Status:** live
- **Publisher:** O-Side Media (community)
- **License:** MIT
- **Source:** https://github.com/OSideMedia/higgsfield-ai-prompt-skill
- **Works in:** Claude Code, Claude.ai, Cursor, Codex
- **Requires:** Higgsfield account (generation and credits), Optional: Python 3 for the lint and preflight scripts
- **Cost:** Prompts only; generation is billed in Higgsfield credits
- **Adoption:** 799 GitHub stars (GitHub, 2026-10-26)

## What it does

An independent prompt pack for Higgsfield users, not made by Higgsfield. A root skill writes and refines video and image prompts with its MCSLA formula, picks the model, camera controls and motion presets for each shot, and routes to 35 sub-skills covering Seedance 2.5 and 2.0 (omni-reference, video edit and extend, VFX), Cinema Studio 2.5/3.0/3.5, Kling 3.0 Motion Control, Soul ID character consistency, an acting system, a shot-list director, a feature-film pipeline, 3D, audio, moodboards and troubleshooting. It keeps a generation ledger, lints claims and Seedance prompts with Python scripts, and ships updates almost weekly (v3.42.0 on 2026-10-23).

## Use when

- Write or fix prompts for any Higgsfield model
- Pick camera controls and motion presets per shot
- Keep a character consistent with Soul ID

## Not for

- Generating without a Higgsfield account
- Other platforms (prompts assume Higgsfield's model menu)

## Install

- Claude Code: `git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield`

**Models it drives:** seedance_2_5, seedance_2, kling_v3, veo_3_1, nano_banana_pro, soul

## More prompts by model skills

- [fal Prompting](https://skills.varg.ai/skills/fal-prompting.md): Prompt specific model families well: Kling, GPT Image 2 and Happy Horse guides, loaded only when needed.
- [Replicate Prompt Images](https://skills.varg.ai/skills/replicate-prompt-images.md): Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
- [Replicate Prompt Videos](https://skills.varg.ai/skills/replicate-prompt-videos.md): Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
- [Video Prompting Guide](https://skills.varg.ai/skills/inference-sh-video-prompting-guide.md): Write prompts that video models follow: shot types, camera moves and per-model tips from Veo to Sora.
- [FLUX 3 Prompt Doctor](https://skills.varg.ai/skills/flux-3-prompt-doctor.md): Diagnose a FLUX 3 video brief before spending: resolve missing, conflicting or schema-changing asks.
- [FLUX Image Best Practices](https://skills.varg.ai/skills/flux-image-best-practices.md): Prompt FLUX image models well: structure, JSON prompts, hex colors, typography and multi-reference edits.