# higgsfield-ai/skills

> A set of Markdown skills for AI coding agents (Claude Code, Cursor, Codex) that use Higgsfield AI to generate images, video, audio, and 3D, and to build visual brand systems and ad creatives.

- Magnitude: 5.8 out of 10 — Breakout
- Stars: 1,651 total · +6 stars measured 2026-10-26, 11:33–13:10 UTC, ≈ 57 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: MIT · Created: 2026-04-09 · Last push: 2026-09-26
- GitHub: https://github.com/higgsfield-ai/skills · Page: https://gitnova.dev/en/r/higgsfield-ai/skills

## Useful for

- Generate an image or video from a text prompt via the agent
- Train a Soul Character and use its reference_id for face-faithful generation
- Build a brandbook with palette, SVG logo, and typography

## Why it’s here

- Star-counter measurements on 2026-10-26 (UTC), 11:33–13:10: 1645 → 1651 stars (+6). This is the change over that interval.
- Estimated end-of-day forecast: about +57 stars, using observed gains and the previous day.
- Over the last two days the pace is 17× that of the previous week and a half.
- GitHub Trending Python today: #11, +253 stars.
- About 21 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 320
- Issues and pull requests: 13
- Watchers: 9
- Average over the last week: 51 per day
- Usual pace: 8 per day
- Stars in the last hour (measured): 5

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-26: 11, 14, 14, 14, 5, 8, 6, 4, 9, 4, 5, 6, 4, 4, 9, 7, 8, 10, 12, 8, 6, 6, 8, 15, 13, 8, 6, 9, 250, 6

## Spotted in now

- GitHub Trending Python today: #11, +253 stars

## Similar by description

1. **SegFault42/HeliosGen** — 1.0 · Cooling · Generative media · TypeScript · +2 stars measured 2026-10-26, 00:21–13:22 UTC, ≈ 4 by evening
   Desktop app for visually building AI image and video generation pipelines on an infinite node canvas with references and automation chains. Runs fully locally using your own kie.ai key.
   Full card: https://gitnova.dev/en/r/SegFault42/HeliosGen.md
2. **MiniMax-AI/MiniMax-H3** — 3.0 · Steady · Generative media · Python · +49 stars measured 2026-10-26, 00:14–13:15 UTC, ≈ 86 by evening
   MiniMax H3 is an omni-modal generative system that understands text, images, video and audio and generates video with native stereo audio up to 2K and 15 seconds. The repository bundles prompt-writing and style-specific video generation…
   Full card: https://gitnova.dev/en/r/MiniMax-AI/MiniMax-H3.md
3. **Leonxlnx/taste-skill** — 4.2 · Steady · AI agents · JavaScript · +284 stars measured 2026-10-26, 00:12–13:11 UTC, ≈ 513 by evening
   A collection of Agent Skills that push AI agents to produce well-designed interfaces instead of boilerplate: stronger layout, typography, spacing and motion. Also includes image-generation skills for web, mobile and brand-kit reference…
   Full card: https://gitnova.dev/en/r/Leonxlnx/taste-skill.md
4. **jakubkrehel/skills** — 4.6 · Breakout · AI agents · Markdown · +171 stars measured 2026-10-26, 00:14–13:23 UTC, ≈ 292 by evening
   A set of AI agent skills for interface design: typography, color, accessibility, layout and UI copy. Installed via npx or as a Claude Code plugin.
   Full card: https://gitnova.dev/en/r/jakubkrehel/skills.md
5. **glanderness/BeefTV** — 2.1 · Steady · Generative media · TypeScript · +18 stars measured 2026-10-26, 00:17–13:17 UTC, ≈ 33 by evening
   A local-first desktop video workspace with AI agents: on a free canvas it links models, assets and generation tasks for text, images, video and audio into an editable workflow.
   Full card: https://gitnova.dev/en/r/glanderness/BeefTV.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-26 13:24 UTC, updated every 30 minutes.