Agent skill

Higgsfield Motion Design

by OSideMedia in OSideMedia/higgsfield-ai-prompt-skill

End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector.

MITAuto-check passedMedia & Creative

Install Higgsfield Motion Design

skills CLI
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-motion-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-motion-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/higgsfield-motion-design .claude/skills/higgsfield-motion-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
higgsfield-motion-design
GitHub stars
713
Token cost
~2.3k tokens
SKILL.md length
1,037 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector.

  • Works in 6 steps: Determine the flow type → Brief intake (one message) → Asset handling → …
  • The user wants to create motion design
  • SKILL.md covers QUICK FACTS, STEP 0 — Determine the flow type, STEP 1 — Brief intake (one… and STEP 2 — Asset handling, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Higgsfield Motion Design is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video from my logo', 'animated brand', 'motion graphics', 'brand motion', 'kinetic graphics', 'promo video', or 'ad video'. Drives a storyboard-first pipeline: brief → storyboard sheet (GPT Image 2) →…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Motion graphics, Video production and AI video generation. It works with Seedance and Remotion. The repository describes itself as: Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an… The licence is MIT.

When your agent uses it

  • The user wants to create motion design
  • Make a video from an image
  • Build an animated ad
  • Turn a product into motion

Example prompts

  • “make a motion”
  • “motion design”
  • “animate this”
  • “/higgsfield-motion-design”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Determine the flow type
  2. Brief intake (one message)
  3. Asset handling
  4. Generate the storyboard
  5. Generate the video
  6. Review & iterate

What it can do on your machine

Read from SKILL.md and the folder at commit 7075497. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Higgsfield Motion Design loads about 2.3k tokens when it runs. Until then it costs about 213 tokens; SKILL.md has 1,037 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~213
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OSideMedia/higgsfield-ai-prompt-skill at commit 7075497, republished under its MIT licence (© OSideMedia). 1,037 words, ~2,323 tokens.

Download SKILL.mdSave it as .claude/skills/higgsfield-motion-design/SKILL.md (or your agent's skills folder).
name
higgsfield-motion-design
description
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video from my logo', 'animated brand', 'motion graphics', 'brand motion', 'kinetic graphics', 'promo video', or 'ad video'. Drives a storyboard-first pipeline: brief → storyboard sheet (GPT Image 2) → video (Seedance 2.0) — an AI-generated pixel video clip. Distinct from higgsfield-motion (the named camera/motion preset library) and from higgsfield-vibe-motion (deterministic Remotion code with crisp text); use vibe-motion instead when the text/logo must stay perfectly crisp, editable, and deployable as code.
user-invocable
true
metadata.tags
higgsfield, motion-design, animated-ad, logo-animation, brand, motion-graphics, storyboard, classicMD, highMD
metadata.version
1.0.1
metadata.updated
2026-06-22
metadata.parent
higgsfield

Higgsfield Motion Design

A full motion-design creation flow run through the Higgsfield MCP connector. Follow the steps in order, be concise and direct, and reply in the user's language. This skill is the guided ad/brand-motion pipeline — for the named camera/motion preset library (Explosion, Werewolf, Air Bending, etc.) use higgsfield-motion instead.

Not a spec sheet. Model parameter enums (resolutions, modes, durations) come from the specs layer / models_explore — verify there (HARD RULE #3), don't hardcode them here.

QUICK FACTS

  • Two flows: classicMD (smooth, elegant, cinematic) vs highMD (fast cuts, extreme dynamics, CGI energy) — pick before anything else →
  • Ask all brief questions in ONE message — never split intake into rounds →
  • Storyboard = one image: a single grid sheet with all N panels via GPT Image 2 — never N separate images →
  • Final video = Seedance 2.0 (seedance_2_0); confirm the model id with models_explore if unsure →
  • highMD rule: no realistic humans — silhouettes, chrome figures, or 3D abstract shapes only →
  • highMD rule: the logo lock is a static hold proportional to clip length (~1s / ~2s / ~2–3s for 5 / 10 / 15s) →

STEP 0 — Determine the flow type

Identify which workflow applies before anything else:

  • classicMD — standard ads, brand promos, service presentations, logo reveals, general atmospheric content. Smooth transitions, elegant typography, cinematic feel.
  • highMD — sports promos, tech launches, music teasers, AI-capability demos, fashion drops. Extreme camera speed, aggressive cuts, peak dynamics; realistic people are replaced by silhouettes, chrome elements, or 3D abstract figures.

If the request makes the flow obvious, proceed silently. If ambiguous, ask once:

"Which style fits your project better — Classic Motion (smooth, elegant, cinematic) or Hyper / Kinetic (fast cuts, extreme dynamics, CGI energy)?"


STEP 1 — Brief intake (one message)

Ask all of these in a single message (never split into rounds). Save every answer before proceeding:

  1. Existing assets? — Yes (upload logo / product photo / reference) · No (help me create the visual)
  2. Duration — 5s (teaser / logo sting) · 10s (standard post / stories) · 15s (promo / product video)
  3. Frame format — 16:9 (horizontal) · 9:16 (vertical Reels/TikTok/Stories) · 1:1 (square feed)
  4. Mood / style (free input) — e.g. energetic, minimalist, luxury, technological, atmospheric, aggressive, cinematic
  5. Brand / product name and tagline (if any)
  6. Storyboard frames — 6 (standard) · 8 (detailed) · 9 (maximum coverage)

STEP 2 — Asset handling

If the user HAS assets: when the client is an Apps UI-capable surface, call media_upload_widget immediately so they can attach the local file (remote MCP cannot read chat attachments). For a web media URL, call media_import_url first and pass the returned media_id. Then proceed to Step 3.

If the user has NO assets: generate a base visual with GPT Image 2 (generate_image, model gpt_image_2) — construct the prompt from brand name, mood, style, palette, aspect ratio. Display the result with job_display, ask "Does this work or want changes?", regenerate if needed, then proceed once approved.


STEP 3 — Generate the storyboard

The core creative step. Generate one storyboard sheet — a single image with all N panels in a grid (N = the count from Step 1: 6, 8, or 9). Do not generate N separate images.

Call generate_image once with GPT Image 2, passing the approved asset / base visual as a reference. Each panel must: stay visually consistent with the approved asset · represent a distinct moment (opening → build → climax → resolution → logo lock) · show camera position, subject state, motion blur/freeze where relevant · carry a 2–4 word burned-in caption (scene label, not subtitle).

  • classicMD panels: smooth compositions, elegant typography zones, cinematic lighting.
  • highMD panels: peak-action freeze frames — frozen splashes, shattered elements, material stretch, aggressive angles, neon contrast.

Prompt skeleton:

Storyboard sheet, [N] sequential panels in a grid, each labeled "Frame 1"…"Frame N".
Panel 1: [scene]. Panel 2: [scene]. … Panel N: [logo lock / brand name].
Each panel: [camera angle], [motion state], [mood/lighting]. Style: [cinematic / kinetic].
Consistent color palette throughout. Clean storyboard design, thin borders between panels.

Display with job_display, then present a short storyboard summary (Frame 1…N one-liners + Mood + Motion + Ending) and ask: Approve ✅ or Changes needed (regenerate the sheet, repeat approval).


Show full SKILL.md (427 more words)Show less

STEP 4 — Generate the video

Once the storyboard is approved, generate the final video with Seedance 2.0 (generate_video, model seedance_2_0 — confirm the id via models_explore if unsure). Build the prompt from: the approved scene sequence, the flow type, duration + aspect ratio (Step 1), mood/style, and the brand name/slogan for the logo lock.

  • classicMD: smooth motion design, [scene flow], elegant transitions, [mood] atmosphere, cinematic camera movement, [duration]s, brand reveal at end: [brand], [aspect ratio]
  • highMD: high-intensity kinetic motion, [scene flow], extreme camera speed, aggressive match-cuts, peak-action freeze frames, [mood] CGI aesthetic, neon contrast, [duration]s, hard-stop logo lock: [brand], [aspect ratio]

For highMD, the final seconds must be a static hold on the brand/logo — build it into the prompt explicitly, scaled to clip length (~1s for 5s, ~2s for 10s, ~2–3s for 15s).

Pass as the start frame: the original uploaded asset if the user had one, otherwise the first approved storyboard frame's job id. Seedance 2.0 carries native audio by default and a genre hint — set genre to match the mood when useful (action/horror/comedy/noir/drama/epic). Display with job_display.

Resolution note: Seedance 2.0 reaches 4K only in mode=std; mode=fast caps at 720p. See higgsfield-seedance / the specs layer.


STEP 5 — Review & iterate

Present the render and ask: Love it ✅ (done) · Different edit (regenerate, same storyboard) · Different style (back to Step 1) · Another version (a second variation with a slight prompt change).


Notes & rules

  • Ask all Step 1 questions at once; never split intake.
  • Storyboard = one grid image via GPT Image 2; never N separate images. No separate moodboard step — go brief → storyboard.
  • Image model: GPT Image 2 (gpt_image_2). Video model: Seedance 2.0 (seedance_2_0).
  • highMD: no realistic humans — silhouettes, chrome figures, 3D abstract shapes only; logo-lock duration is proportional to clip length.
  • classicMD logo can appear as opener, closer, or both — ask if unspecified.
  • Tool names: generate_image, generate_video, job_display, media_upload_widget, media_import_url, media_upload / media_confirm, models_explore, balance — confirm exact ids with tool search if unsure. Check credits with balance if the user seems concerned about usage.
  • Match the user's language throughout. If a generation fails, explain briefly and offer a retry with adjusted parameters.
  • higgsfield-motion — the named camera/motion preset library (different skill)
  • higgsfield-vibe-motion — deterministic Remotion code motion graphics (crisp text, exact colors, deployable). Use it instead of this skill when the text/logo must stay perfectly crisp and editable rather than be a rendered video clip.
  • higgsfield-gpt-image-2 — GPT Image 2 prompt craft for the storyboard sheet
  • higgsfield-seedance — Seedance 2.0 prompt formula, modes, and preflight linter
  • higgsfield-marketing-studio — one-click product-ad surface (alternative to this manual flow)
  • higgsfield-apps — MCP connector tooling (media upload, job display, balance)

© OSideMedia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/higgsfield-motion-design of OSideMedia/higgsfield-ai-prompt-skill.

Open the folder on GitHubat commit 7075497

Compare with similar skills

Higgsfield Motion Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Higgsfield Motion Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Higgsfield Motion Design this skillOSideMedia/higgsfield-ai-prompt-skill713—~2.3kAutomated safety check: PassMIT
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone
HyperFrames Video Entry Pointheygen-com/hyperframes60k3 repos~5.2kAutomated safety check: PassApache-2.0
Anything2explainerVincentwei1021/anything2explainer2.4k—~2.7kAutomated safety check: PassCustom licence
Remotion Motion Graphicshaidrrrry/claude-remotion-skill340—~2kAutomated safety check: PassMIT
Remotion Ad Videoleosssvip-dot/remotion-ad-video-skill111—~6.3kAutomated safety check: PassMIT

Similar skills

  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    60k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Anything2explainer

    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated…

    2.4k GitHub stars~2.7k tokensUpdated 22 days ago
    Media & CreativeAuto-check passed
  • Remotion Motion Graphics

    haidrrrry/claude-remotion-skill

    Create and edit professional motion graphics videos with Remotion (React-based video).

    340 GitHub stars~2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Remotion Ad Video

    leosssvip-dot/remotion-ad-video-skill

    A skill your agent uses when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine…

    111 GitHub stars~6.3k tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed
  • Video

    Nexus-JPF/note-companion

    When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks.

    870 GitHub starsUsed in 3 repos~3.6k tokens
    Media & CreativeAuto-check passed

More from OSideMedia/higgsfield-ai-prompt-skill

All 33 skills in this repo
  • Higgsfield

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano…

    713 GitHub stars~9.1k tokensUpdated 14 days ago
    Auto-check passed
  • Higgsfield Assist

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to…

    713 GitHub stars~2.9k tokensUpdated 14 days ago
    Auto-check passed
  • Higgsfield Image Shots

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type…

    713 GitHub stars~5.1k tokensUpdated 14 days ago
    Auto-check passed
  • Higgsfield Mixed Media

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user asks about Mixed Media, wants to apply artistic preset styles to an image (Noir, Sketch, Paper, Canvas, Particles, Neon, etc.), combine multiple artistic…

    713 GitHub stars~2.3k tokensUpdated 14 days ago
    Auto-check passed
  • Higgsfield Moodboard

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to…

    713 GitHub stars~2.3k tokensUpdated 14 days ago
    Auto-check passed
  • Higgsfield Motion

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user wants to apply a named Higgsfield motion preset, asks about VFX presets, transformation effects, elemental effects, or transition presets.

    713 GitHub stars~5k tokensUpdated 14 days ago
    Auto-check passed

Questions about Higgsfield Motion Design

What does Higgsfield Motion Design do?

End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Higgsfield Motion Design is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector.

When should I use Higgsfield Motion Design?

Higgsfield Motion Design fits situations like: the user wants to create motion design; make a video from an image; build an animated ad; turn a product into motion.

How do I install Higgsfield Motion Design in Claude Code?

Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-motion-design -a claude-code`. Or copy the skill folder (skills/higgsfield-motion-design in OSideMedia/higgsfield-ai-prompt-skill) into .claude/skills/higgsfield-motion-design in your project. Claude Code loads it when a task matches its description.

How do I install Higgsfield Motion Design in Codex?

Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-motion-design -a codex`. Or copy the skill folder (skills/higgsfield-motion-design in OSideMedia/higgsfield-ai-prompt-skill) into .agents/skills/higgsfield-motion-design in your project. Codex loads it when a task matches its description.

Can I use Higgsfield Motion Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-motion-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/higgsfield-motion-design, .gemini/skills/higgsfield-motion-design, .github/skills/higgsfield-motion-design and .opencode/skills/higgsfield-motion-design in your project.

What does Higgsfield Motion Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Higgsfield Motion Design is instructions for the agent only.

Does Higgsfield Motion Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Higgsfield Motion Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Higgsfield Motion Design use?

Higgsfield Motion Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Higgsfield Motion Design use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Higgsfield Motion Design?

Skills that share tags, products or a category with Higgsfield Motion Design: Super Video Maker (Bomx/super-video-maker-skill, 310 stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Anything2explainer (Vincentwei1021/anything2explainer, 2.4k stars) and Remotion Motion Graphics (haidrrrry/claude-remotion-skill, 340 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Higgsfield Motion Design?

OSideMedia (a GitHub user) maintains it in OSideMedia/higgsfield-ai-prompt-skill, which has 713 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on September 27, 2026.

Source: OSideMedia/higgsfield-ai-prompt-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.