SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-20 UTC

No new commits yet today

Open the update feed

higgsfield-ai-prompt-skillOSideMedia/higgsfield-ai-prompt-skill

Turns "generate cinematic AI video" into an executable prompt-engineering workflow, so Claude outputs prompts and parame…

No ratings yet Rate this skill
Stars720
Forks126
Watchers720
Open Issues2

InstallOne-line install

Installable · 21 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add OSideMedia/higgsfield-ai-prompt-skill

21 more are not listed — run npx skills@latest add OSideMedia/higgsfield-ai-prompt-skill --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Turns "generate cinematic AI video" into an executable prompt-engineering workflow, so Claude outputs prompts and parameters that can be fed directly into video models. Key capabilities include: 1. Routing declaration: the first line of each response states which sub-skills are being invoked, preventing the model from drifting off-task; 2. Generation parameter decisions: determines generation type (image/video/app), video duration, aspect ratio and model preference item by item, outputting a ready-to-use parameter set; 3. Multi-model adaptation: produces model-specific prompt phrasing for Higgsfield Cinema Studio 2.5/3.0/4.0, Kling, Veo, Seedance 2.5, Wan and Dreamina; 4. Character acting and camera control: uses Soul ID and Motion Control to describe character performance, camera movement and 3D viewpoints for more controllable results; 5. Asset repurposing: rewrites existing footage into new variations to extend the lifespan of a single piece of content.

Use Cases

converting storyboards and scripts into prompts for AI short films and ads, comparing one concept across multiple video models, generating consistent character shots across a sequence, remaking and re-versioning existing footage.

Target Roles

Film/TV director & audio-video producer, content creator / social media operator, AI / algorithm engineer, product manager (PM).

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1298
Data sourceGitHub
RepositoryOSideMedia/higgsfield-ai-prompt-skill
CategoryAI & Agent Skills / AI Video & Filmmaking
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1176172630
Node IDR_kgDORhr4Vg
Rank#982 (position within the source ranking)
Site-wide popularity rank#1173 (computed live from Stars, across all 5884 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-302026-10-112026-09-30 · 6612026-10-11 · 720
  • Now720
  • Previous point · 09-30 661
  • vs previous point +59
  • 2 data points 11 days
0501001502026-09-302026-10-112026-09-30 · 1162026-10-11 · 126
  • Now126
  • Previous point · 09-30 116
  • vs previous point +10
  • 2 data points 11 days

TimelineTimeline

Repository created2026-03-08 18:03:418 months ago
Data last updated2026-10-26 12:06:5425 days ago
Last commit2026-09-27 03:24:181 months ago

CommitLatest commit

Version [v3.40.0] committed by OSideMedia. Update Category: Release & Version Milestone Deployment. Commit details: Merge pull request #108 from OSideMedia/release/v3.40.0. This update milestone release delivery and production build archiving.

7075497 v3.40.0 OSideMedia 2026-09-27

Next stepsNext steps