Higgsfield Claude Skills: 19 skills for video and UGC ads
Higgsfield Claude Skills
19 Claude Code skills for Higgsfield: Seedance 2.0 prompts in 15 styles and generation automated through Playwright
- 459 ★ on the repository
- Last commit
Broad access
Why this level
- The skills drive a Playwright browser under your Higgsfield account: they type text, pick files and press buttons, including the one that starts generation
- JavaScript snippets run on the service's pages, and you sign in to your account in the same Playwright window
- The `ugc-hot-girl` skill writes prompts for photorealistic fictional characters in ad reviews: such a clip must be labeled as advertising and as AI-generated, and must not be passed off as a real customer review
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/higgsfield-claude-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The skills drive a Playwright browser under your Higgsfield account: they type text, pick files and press buttons, including the one that starts generation
- JavaScript snippets run on the service's pages, and you sign in to your account in the same Playwright window
- The `ugc-hot-girl` skill writes prompts for photorealistic fictional characters in ad reviews: such a clip must be labeled as advertising and as AI-generated, and must not be passed off as a real customer review
This is third-party code. Review the repository files before installing.
What it does
A set of 19 Claude Code skills that works with the Higgsfield generation service. Fifteen skills write Seedance 2.0 video prompts in a chosen style: cinematic, 3D, cartoon, comic, fight scenes, anime, advertising, music videos, fashion, food, real estate and more. A prompt runs 15–25 lines and includes a hook for the first two seconds, a timeline split up to 15 seconds, camera moves, lighting, atmosphere and sound. The other four skills form an end-to-end pipeline. `ugc-hot-girl` writes a character prompt for UGC-style ads (a clip made to look like a user testimonial), `higgsfield-image-auto` generates an image on the Soul 2.0 model through the browser, `seedance-auto-generate` creates a video from the chosen image, and `ugc-video-auto` runs the whole path from image to clip. Playwright MCP drives the browser. The skill asks for confirmation before pressing the Generate button. For long batches the project suggests keeping a `SESSION-RESUME.md` file: after a crash the agent reads it and continues from the right step. The prompts for the 15 styles are adapted from the beshuaxian/higgsfield-seedance2-jineng project.
Who it is for. For marketers and social media specialists who make short ad clips and UGC for TikTok and Reels and already work in Higgsfield.
Good fit when
- You need a 9:16 ad clip for TikTok or Reels and want to take it from a character prompt to a finished video
- You want Claude Code to open the Higgsfield pages itself, pick an image from your generations and fill in the video form
- You need a detailed Seedance 2.0 prompt for a specific niche: real estate, food, fashion or a 360-degree product view
- You are making a series with several characters and want to resume from the step where a crash happened
- You want to turn a character image into an anime-style fight scene
Not a fit when
- You have no Higgsfield account: login is done by hand in the Playwright window, and without a login automation does not start
- You need the official set from the service itself: Higgsfield has its own skills, CLI and MCP server
- You do not work in Claude Code: the skills are invoked as Claude Code slash commands
- The service layout has changed: the steps are tied to the current pages and model addresses, and automation may stop working
- You need a real customer review: the characters are fictional and the clip must not be passed off as a genuine review
Example request
/ugc-video-auto Create a UGC video for my new vitamin C serum: TikTok format, testimonial styleLimitations
Automation runs through the Higgsfield site pages with Playwright: the skill clears the prompt field with a JavaScript snippet, types text slowly to imitate keypresses and picks an image in the upload dialog. The authors note that the prompt bar on the site sometimes disappears, and refreshing the page helps.
Node.js, Claude Code, a free Higgsfield account and Playwright MCP are required. Generation limits and plan terms are set by the service itself. The repository has no license file, so the terms for reusing the skills are unclear.
The repository was last updated in April 2026.
How to disable. Delete the copied skill folders from the project's `.claude/skills/` directory. To remove the Playwright server, run `claude mcp remove playwright`.
FAQ
How do I install the Higgsfield skills in Claude Code?
Paste a request into Claude Code to clone the repository into a temporary folder, copy every subfolder into `.claude/skills/` and install Playwright MCP with `claude mcp add playwright npx @playwright/mcp@latest`. After that 19 slash commands appear.
Which video styles are supported?
Six creative: cinematic, 3D, cartoon, comic to video, fight scenes, anime. Five commercial: motion design, e-commerce, 360-degree product view, social hook, brand story. Four industry: music video, fashion, food and beverage, real estate.
How does the path from image to video work?
The skill generates an image on the Soul 2.0 model page, then opens the Seedance 2.0 video page, picks the image on the generations tab and passes it into the form without downloading and re-uploading.
What if Playwright asks me to sign in?
Log in to Higgsfield by hand in the browser window Playwright opened and repeat the command. That window is managed separately from your everyday browser.
What if the prompt bar does not clear between runs?
Add a rule to the project's `CLAUDE.md` to clear the prompt bar with a JavaScript snippet and take a screenshot after clearing: without an explicit rule Claude skips this step.
Discussion
No questions or reviews yet.
Related
SkillsHiggsfield Prompt Skill
higgsfield-ai-prompt-skill
A skill that turns a request into prompts for the Higgsfield video service: 32 subskills for cinema, VFX, canvas. An independent project, the service is paid
Fifteen Claude Code skills for launch films, animated charts and reels made entirely from code, with no After Effects
Higgsfield skills
higgsfield-skills
Eight official Higgsfield skills: generation, Soul character, product shoots, brand kit, marketplace cards, websites, video and thumbnails
Seven Claude Code skills and a prompt library for the Seedance, Kling and HappyHorse video models: prompts, storyboards, debugging
A Claude Code skill that turns an idea into a five-stage prompt for Sora, Kling, Veo and Seedance, with templates for 21 genres
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Higgsfield Claude Skills: 19 skills for video and UGC ads (this entry) | no | 459 | |
| Higgsfield skills | yes | 1,787 | eight official Higgsfield skills: generation, a Soul character, product photography, a brand kit and more |
| Higgsfield Prompt Skill | no | 822 | a skill that turns a request into prompts for Higgsfield: 32 sub-skills, cinema, VFX and canvas |
| AI Video Generator | no | 445 | ten skills that write Seedance 2.0 video prompts with timing, camera, light and sound |
README in short
The description is in English. It shows invocation examples for the styles, the addresses of the Higgsfield model pages and a table of common problems, from a vanished prompt bar to an editor that rejects fast typing.
README badge
Original SKILL.md
--- name: ugc-video-auto description: Full UGC ad video pipeline — generates a character image on Higgsfield, then creates a Seedance 2.0 video from it. Orchestrates the complete flow from image prompt to finished UGC video. Use when the user wants to create a UGC ad video end-to-end, or wants to take a generated image from Higgsfield's image tab into video creation. Triggers on "create a UGC video", "make a UGC ad", "UGC pipeline", "turn this into a UGC video", or any request combining image generation with video creation for ads/UGC content. Requires Playwright MCP tools. --- # UGC Video Auto — Full Pipeline via Playwright This skill orchestrates the complete UGC ad video pipeline on Higgsfield: generate a character image → select it for video → add a UGC video prompt → generate a Seedance 2.0 video. All automated via Playwright. --- ## Pipeline Overview ``` Step 1: Generate character image → /image/soul-v2 Step 2: Navigate to video page → /create/video?model=seedance_2_0 Step 3: Select image from gallery → Upload dialog → "Image Generations" tab Step 4: Write UGC video prompt → Lexical editor (contenteditable) Step 5: Configure & generate → Click Generate ``` --- ## Prerequisites - User must be **logged in** to higgsfield.ai in the Playwright browser session - **Playwright MCP** plugin must be enabled - Load each Playwright tool with `ToolSearch` before first use ## Input Requirements The user provides: 1. **Character description** OR a pre-made image prompt (invoke `/ugc-hot-girl` to generate one) 2. **Product/brand context** — what the UGC video is advertising 3. **Video style** — testimonial, product showcase, unboxing, reaction, etc. Optional overrides: - **Image model**: Soul 2.0 (default, best for portraits) - **Video model**: Seedance 2.0 (default) - **Duration**: 5s, 8s (default), 10s - **Ratio**: Auto, 16:9, 9:16 (TikTok/Reels), 1:1 - **Resolution**: 720p (default), 1080p --- ## Full Automation Flow ### Phase 1: Generate the Character Image #### Step 1.1: Navigate to image generation ``` browser_navigate → url: "https://higgsfield.ai/image/soul-v2" ``` Wait for page load, take a snapshot. #### Step 1.2: Enter the image prompt Find the textbox (Playwright ID: `hf:tour-image-prompt`, placeholder: "Describe the scene you imagine"):