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 · Prompts by model
• 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: Prompt specific model families well: Kling, GPT Image 2 and Happy Horse guides, loaded only when needed.
• Replicate Prompt Images: Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
• Replicate Prompt Videos: Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
• Video Prompting Guide: Write prompts that video models follow: shot types, camera moves and per-model tips from Veo to Sora.
• FLUX 3 Prompt Doctor: Diagnose a FLUX 3 video brief before spending: resolve missing, conflicting or schema-changing asks.
• FLUX Image Best Practices: Prompt FLUX image models well: structure, JSON prompts, hex colors, typography and multi-reference edits.