Higgsfield Skills for AI Video and Audio
Higgsfield is a generative video tool, and the skills in this topic are the ones that drive it from an AI agent: turning a prompt or a still into a first clip, holding a face or figure steady across shots where the product supports it, controlling how a still becomes a shot, laying speech on the picture, changing an existing clip instead of starting over, and exporting a file you can post or edit elsewhere. Read the ranked list as a set of entry points, not a single path. Match the sub-topic to the job in front of you — generation if you have nothing yet, character consistency or motion if you have a look to protect, voice and audio or edit if the cut already exists — then open the skill that fits and check its own documentation before you load it.
8 to start with34 top options
Start with these.
Higgsfield is a generative video tool: start from an image or idea, animate, voice, restyle, and export.
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect169,921 · popularity
higgsfield-generate
Notable - Rank 02View Agent SkillDirect
higgsfield
A comprehensive Higgsfield AI prompt skill covering video/image prompt writing, model selection (Kling, Sora 2, Veo, Wan, Seedance, Soul), camera controls, motion presets, Soul ID consistency, and troubleshooting.
450 · popularity - Rank 03View Agent SkillDirect
higgsfield-soul-id
Trains a Soul Character identity model on a person's face for identity-faithful Higgsfield image and video generation, then reuses it via --soul-id in generate commands.
Needs (stated): Paid account
172,947 · popularity - Rank 04View Agent SkillDirect
ugc-video-auto
Orchestrates a full UGC ad video pipeline on Higgsfield via Playwright: generates a character image, then creates a Seedance 2.0 video from it end-to-end.
156 · popularity - Rank 05View Agent SkillDirect
seedance-auto-generate
Automates Seedance 2.0 video creation on Higgsfield using Playwright, uploading an image, filling a prompt, and clicking Generate, with a catalog of style sub-skills.
150 · popularity - Rank 06View Agent SkillDirect
seedance-cinematic
Generates cinematic film-style video prompts for Seedance 2.0 on Higgsfield, covering dramatic lighting, camera language, depth of field, and 2-second hook frameworks.
303 · popularity - Rank 07View Agent SkillDirect
seedance-social-hook
Generates viral social media hook video prompts for TikTok, Reels, and Shorts using Seedance 2.0 on Higgsfield, focused on scroll-stopping first-2-second openers.
296 · popularity - Rank 08View Agent SkillDirect
seedance-faceless-channel
Generates faceless content video prompts for Seedance 2.0 on Higgsfield, covering narration-driven, stock-footage-style, and anonymous creator videos with hook tables.
128 · popularity
Explore 26 more Agent Skills
- Rank 09View Agent SkillDirect
seedance-fashion-lookbook
Generates fashion lookbook, model showcase, and style video prompts for Seedance 2.0 on Higgsfield, covering outfit reveals, runway clips, and fashion campaign hooks.
278 · popularity - Rank 10View Agent SkillDirect
seedance-comic-to-video
Converts comic panels, manga pages, webtoons, and storyboards into animated video prompts using Seedance 2.0 on Higgsfield, with story inference and style preservation.
274 · popularity - Rank 11View Agent SkillDirect
seedance-motion-design-ad
Generates motion design advertisement video prompts for software and tech companies using Seedance 2.0 on Higgsfield, covering UI animation, product launches, and SaaS promos.
259 · popularity - Rank 12View Agent SkillDirect
seedance-anime-action
Generates anime-style video prompts for Seedance 2.0 on Higgsfield, covering shonen action, mecha, isekai, and other Japanese animation aesthetics with hook frameworks.
248 · popularity - Rank 13View Agent SkillDirect
seedance-brand-story
Generates brand storytelling and narrative video prompts for Seedance 2.0 on Higgsfield, covering origin stories, mission videos, brand films, and founder narratives.
246 · popularity - Rank 14View Agent SkillDirect
seedance-product-360
Generates product 360-degree turntable, multi-angle showcase, and product reveal video prompts for Seedance 2.0 on Higgsfield, with material-aware lighting guidance.
244 · popularity - Rank 15View Agent SkillDirect
higgsfield-video-explainer
Build a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: one narrator, one universal style key, one Seed Audio take and one Gemini Omni clip per block, then server-side assembly with explainer_video. Use when: "make an explainer video", "explain this in a…
101,378 · popularity - Rank 16View Agent SkillDirect
higgsfield-youtube-thumbnail
Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a truthful information-gap concept, preserves up to three referenced identities, supports logos and controlled variants, renders the main image with Nano Banana Pro, and applies focused…
79,596 · popularity - Rank 17View Agent SkillDirect
higgsfield-product-photoshoot
Generates brand-quality product images through Higgsfield's product-photoshoot prompt enhancement on GPT Image 2, with modes for studio, lifestyle, hero banner, ad creative, and virtual try-on.
174,073 · popularity - Rank 18View Agent SkillDirect
higgsfield-marketplace-cards
Generates marketplace-ready product image cards through Higgsfield, including compliant main images, secondary product images, and A+ style content modules.
171,055 · popularity - Rank 19View Agent SkillDirect
higgsfield-brandkit
Creates and extends visual brand systems through the Higgsfield CLI: palettes, SVG logos, typography, mockups, social graphics, packaging, and editable brandbooks.
79,531 · popularity - Rank 20View Agent SkillDirect
higgsfield-image-auto
Automates the full Higgsfield image generation flow using Playwright browser automation, navigating to the image page, entering a prompt, configuring settings, and clicking Generate.
295 · popularity - Rank 21View Agent SkillDirect
ugc-hot-girl
Generates detailed AI image prompts for creating attractive female UGC ad characters optimized for Higgsfield Soul 2.0 or Nano Banana Pro.
148 · popularity - Rank 22View Agent SkillDirect
ai-video-generation
NotableGenerate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, genera
142,615 · popularity - Rank 23View Agent SkillDirect
ai-avatar-video
Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2…
371,428 · popularity - Rank 24View Agent SkillPossible
remotion-to-hyperframes
Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build…
400,852 · popularity - Rank 25View Agent SkillPossible
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline,…
382,107 · popularity - Rank 26View Agent SkillPossible
character-design-sheet
Creates consistent characters across AI-generated images using reference sheets, turnaround views, expression sheets, and LoRA techniques via inference.sh CLI.
44,649 · popularity - Rank 27View Agent SkillPossible
video-prompting
Drafts and refines prompts for video generation models like Veo, Wan, Seedance, and LTX, plus character-sheet prompts for image-to-video consistency.
520 · popularity - Rank 28View Agent SkillPossible
happyhorse
Generates and edits videos with Alibaba HappyHorse 1.0 models via inference.sh CLI, covering text-to-video, image-to-video, reference-to-video, and natural-language video editing.
10,324 · popularity - Rank 29View Agent SkillPossible
muapi-character-story-video
Creates multi-part animated story videos by establishing a consistent character, generating sequential scenes, and animating them via muapi image and video models.
664 · popularity - Rank 30View Agent SkillPossible
comfyui-character-gen
Builds identity-preserving character generation workflows in ComfyUI, selecting methods like InfiniteYou, FLUX Kontext, PuLID, and InstantID, with video and talking-head pipelines.
623 · popularity - Rank 31View Agent SkillPossible
cinematic-script-writer
Creates cinematic scripts for AI video generation with cinematography knowledge, character/voice/environment consistency, and Google Drive storage integration.
827 · popularity - Rank 32View Agent SkillPossible
imagegen
OfficialGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
- Rank 33View Agent SkillPossible
remotion-render
NotableExport a Remotion video
- Rank 34View Agent SkillPossible
higgsfield-websites
Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield…
113,070 · popularity
What this topic covers
Each sub-topic groups Agent Skills for a specific situation.
- Generate
- Get a first clip from a prompt or a still.
- Character consistency
- The same face or figure across shots, if the product supports it.
- Motion
- How the still becomes a shot.
- Voice & audio
- Speech sitting on the picture.
- Edit
- Change an existing clip without starting over.
- Export
- A file you can actually post or edit elsewhere.
Frequently asked questions
- What is the difference between the Generate and Motion sub-topics?
- Generate covers getting a first clip out of a prompt or a still, so it is where you start when you have no footage. Motion covers how that still becomes a shot, which matters once you already have an image and care about the movement inside the frame.
- How is this list ordered?
- It is ranked by observed search demand, with skills that directly match the topic placed first. No single publisher can take more than a capped share of the list.
- Can I keep the same character across multiple shots?
- Character consistency is a sub-topic here, covering the same face or figure across shots where the product supports it. Check the individual skill's documentation to see what it actually handles before relying on it for a sequence.
- Do I need to start over to change a clip I already made?
- No. The Edit sub-topic covers changing an existing clip without starting over, and Export covers producing a file you can post or edit elsewhere.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for higgsfield-generate into ~/.claude/skills/higgsfield-generate/ for yourself, or .claude/skills/higgsfield-generate/ to share it with a project.
- From the registry — run npx skills add higgsfield-ai/skills@higgsfield-generate.
- Or download higgsfield-generate from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.