higgsfield-ai/skills
Official Higgsfield skills that let an agent run image, video, 3D and audio generation through the Higgsfield CLI, build narrated explainer videos and train a reusable face identity.
The generate skill installs the higgsfield CLI if it is missing, asks you to sign in, picks a model for the request and submits the job with --wait; Seedance 2.5 is the default for video, with Kling, Veo and others used when you name them. It covers text-to-video, image-to-video with start and end frames, video edit and extend and aspect-ratio reframing, plus a Marketing Studio mode for ad and UGC-style videos and a Virality Predictor that scores a finished video's hook and retention. The explainer skill turns a topic or document into a narrated, non-photoreal video assembled from 10-second blocks, and the Soul ID skill trains a face identity from 5 to 20 photos so a person stays consistent across generations. All of it runs on a Higgsfield account (Soul training needs a paid plan), and the repo's five other skills, for brand kits, product photos, marketplace cards, YouTube thumbnails and websites, are not part of this entry.
Included skills
01From the README
The install command quoted from the repository README.
npx skills add higgsfield-ai/skills02Claude Code, skills folder
Copy the skill's folder, the one that holds SKILL.md, into ~/.claude/skills/ to use it in every project on your machine, or into .claude/skills/ in a repository to use it there and share it by committing it. Claude Code picks up changes to these folders during a session. If the folder did not exist when the session started, run /reload-skills.
03Claude Code, plugin marketplace
Some repos publish a plugin marketplace, a .claude-plugin/marketplace.json file. Add it in Claude Code, then install a plugin from it with /plugin install plugin-name@marketplace-name. Plugins can bundle hooks and MCP servers along with skills, so read the details panel before you confirm.
/plugin marketplace add higgsfield-ai/skills04Codex, skills folder or $skill-installer
Codex reads skills from .agents/skills in your working folder and its parent folders up to the repository root, and from $HOME/.agents/skills for every repository. Copy the skill's folder into one of them, or run $skill-installer inside Codex and ask it to install from the repo. Codex detects new skills automatically and needs a restart only if one does not appear.
The first command is quoted from the author's README. The others are the standard ways to install a skill from a GitHub repository. They are templates and may not apply here, for example if the repo has no plugin marketplace, so follow the README first.
The production stages this skill covers, and where Pencil0 picks up.
nexu-io/open-design
A skill bundled with the OpenDesign app that plans one short AI video shot, writes the prompt the way the chosen model prefers and renders it through the app's media command.
calesthio/OpenMontage
An open-source repo in which a coding agent directs video production through staged pipelines, with a large set of skills on video-model APIs, music, speech, editing and composition.
yikart/AiToEarn
Video-focused SKILL.md files from the AiToEarn content agent, led by a short-drama recap skill that submits clips for AI narration and voice-over; they rely on the platform's own tool calls.
MiniMax-AI/MiniMax-H3
MiniMax's official skills for its H3 video model: one portable prompt-writing skill plus eight style-specific video workflows that need the MiniMax Hub agent.
dramaclaw/dramaclaw
An agent skill that moves a novel or script already loaded into a DramaClaw project through its AI drama pipeline, starting one queued step per message.
ArcReel/ArcReel
Skills that let an agent drive ArcReel, a self-hosted AI video workbench, from script prompts and reference sheets through storyboard stills, clips, narration and a timeline edit.
This is a third-party skill. It is not maintained or audited by Pencil0, and skills can run scripts on your machine, so read the SKILL.md and any scripts before installing. Stars, license and dates are a GitHub snapshot and may be out of date.