Video Generation
bytedance/deer-flow
Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.
A skill your agent uses when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad /…
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-workspaces .claude/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.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/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .claude/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspacesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/higgsfield-workspaces .agents/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .agents/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/higgsfield-workspaces .cursor/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .cursor/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git --path skills/higgsfield-workspaces--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/higgsfield-workspaces .gemini/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .gemini/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspacesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/higgsfield-workspaces .github/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .github/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/higgsfield-workspaces .opencode/skills/higgsfield-workspaces && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-workspaces" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-workspaces into .opencode/skills/higgsfield-workspaces/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-workspaces", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
higgsfield-workspacesA skill your agent uses when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad /…
Higgsfield Workspaces is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. Use when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad / Higgsfield Audio (Sora 2 Trends is built on the retired Sora 2), or is asking 'what should I use for X'. This sub-skill routes by production problem BEFORE model selection.
Its SKILL.md is about 4.6k 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 AI video generation. 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.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 7075497. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Higgsfield Workspaces loads about 4.6k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 2,588 words of instructions outside code blocks.
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.
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.
The full file from OSideMedia/higgsfield-ai-prompt-skill at commit 7075497, republished under its MIT licence (© OSideMedia). 2,588 words, ~4,593 tokens.
.claude/skills/higgsfield-workspaces/SKILL.md (or your agent's skills folder).Higgsfield is organized around workspaces, each one tuned for a specific kind of production work. The right starting question is not "which model should I use?" but "what am I actually trying to make?" Inside a workspace, model choice still matters — it shapes quality, speed, and cost — but a workspace mismatch costs more time than a suboptimal model. Pick the workspace by the task, then pick the model by the result you want.
| Your production problem | Start with workspace |
|---|---|
| Cinematic scene with deliberate camera direction | Cinema Studio |
| Speaking character, dubbing, or avatar video | Lipsync Studio |
| Rough idea, sketch, or storyboard test | Draw to Video / Sketch to Video |
| Fast short-form or viral-style content | Viral Hub presets (Sora 2 Trends is built on the retired Sora 2 — see its section) |
| Product ad or ecommerce variation | Click to Ad |
| Narration, voice swap, or translation | Higgsfield Audio |
If the user's task matches more than one row, pick the workspace whose output most closely resembles the final deliverable — you can always chain into another workspace for polish or audio later.
The professional filmmaking environment on Higgsfield. Built for multi-shot,
character-consistent sequences where camera direction, genre framing, and visual
cohesion matter. Cinema Studio 2.5 offers optical physics (camera body + lens
stack) and built-in color grading; Cinema Studio 3.0 (Business/Team plan) adds
native audio, Smart camera planning, and longer durations. Choose this workspace
when the work needs to feel like a film. For prompt construction, Director Panel
use, optical stack selection, and multi-shot planning, see higgsfield-cinema.
The workspace for putting words into a character's mouth. It pairs an image,
video, or generated face with an audio track and synchronizes the lip movement
to the speech. Use it for dubbed performances, talking-head avatars, character
dialogue, and lipsync work layered on top of existing video generations. For
audio layer design (dialogue, SFX, ambient, BGM) that feeds into Lipsync Studio,
see higgsfield-audio. For character reference management and Soul Cast avatar
generation that commonly sits upstream, see higgsfield-soul.
The workspace for taking a rough sketch, blocking diagram, or storyboard panel and turning it into a generated video. It exists to bridge the gap between paper-stage ideation and motion testing — the place to validate a shot idea before it earns the credits and time of a full Cinema Studio build.
When to use:
Input characteristics: the workspace is forgiving. Hand-drawn storyboards, blocking diagrams with stick figures or geometric placeholders, even a crude napkin sketch all work as input. Quality of line is not the point — clarity of compositional intent is. A messy sketch with a clear staging idea outperforms a polished sketch whose staging is muddled.
The prompt's role: the sketch carries composition and blocking; the prompt carries everything else. Subject details, environment, lighting, mood, and material qualities all live in the prompt. Think of the prompt as describing the realized scene the sketch was hinting at — the sketch told the engine where things sit and how they move; the prompt tells it what they are.
Scope — this workspace, not a Seedance reference slot. Here the sketch is
the input the workspace is built to realize, and a draft that inherits its
layout is the point. Attached to a Seedance generation it is a different
regime: a drawing in the first-frame role becomes frame one, drawing and all,
and a position diagram goes in last as a position reference only — one
incomplete-record house run found it does not reliably move blocking
(../higgsfield-seedance/FAILURE-MODES.md § A fight generated as separate
clips comes back choppy; ../../templates/seedance/staging-reference.md;
../shared/house-rulings.md P2-11). Do not carry "the sketch carries
blocking" from here into a Seedance prompt.
Output expectations: test-quality, short. The output is a tool for shot validation, not usually the final delivery. Treat the result as a draft, then either refine the prompt (if blocking is right but the realized scene is off) or re-block with a new sketch (if the staging itself needs to change).
Two prompt patterns:
Cross-reference: when the test reads well and you want a longer, multi-shot
realization, move into Cinema Studio with the validated blocking in mind. If
you need higher fidelity earlier in the process — a pre-rendered hero frame
that subsequent shots can reference — the Hero Frame workflow inside Cinema
Studio is the alternative path. See higgsfield-cinema for that handoff.
[OFFICIAL — Higgsfield MCP tool schema, get_presets, 2026-09-26] Higgsfield's preset
galleries are browsed with get_presets; source: 'viral' lists the Viral Hub chain
presets (the gallery behind /effects requests). Browsing opens a preview and starts
nothing — a preset runs through execute_preset only when the user explicitly asks to
generate. This is where fast short-form / viral work starts now that Sora 2 Trends sits on
a retired model. Presets are the viral-effects / social product, not film grammar (the
scope caveat at the top of ../higgsfield-motion/SKILL.md): a trend piece that needs
deliberate camera direction belongs in Cinema Studio.
Built on Sora 2 — likely affected by its shutdown (unconfirmed in the UI). OpenAI shut the Sora 2 API down on 2026-09-24
[OFFICIAL — OpenAI deprecations page, read 2026-09-26]. Whether this workspace still works in Higgsfield's web UI after that date is unconfirmed — on 2026-09-26 higgsfield.ai/sora-2 was still up with no shutdown notice. Don't route new work here; fast short-form / viral work starts from the Viral Hub presets above. The description below is kept as reference.
A templated workspace built on top of the Sora 2 model, tuned for trend-led short-form content. The distinction worth holding onto: this is not the same as selecting Sora 2 as a raw model elsewhere on the platform. Trends wraps the model in pre-tuned templates optimized for viral pacing, vertical framing, and quick iteration cycles. The templating is the point — it does work that would otherwise have to be re-invented every shot.
When to use:
Distinguishing features:
Input characteristics: usually a hook idea or a trend reference. Characters and locations can be specified, but the templating handles a lot of structure that you'd otherwise have to direct manually. The lift on input is light.
The prompt's role: provide the specific subject and beat for the chosen trend template. The template handles pacing and format; the prompt handles what the shot is about within that format. Think of the prompt as content slotted into a structure that's already running.
Trade-offs vs. Cinema Studio: Trends sacrifices fine-grained control in exchange for speed and platform-native output. If the deliverable needs deliberate camera direction, character continuity across shots, or genre framing that the trend templates don't carry, Cinema Studio is the right workspace and the wrong question to ask in Trends.
Cross-reference: for one-click trend-flavored workflows that overlap with
this workspace (Vibe Motion, the various style apps), see higgsfield-apps.
When full cinematic control is needed instead of templated trend pacing,
escalate to higgsfield-cinema.
The product-focused ad workspace. Paste a product URL or upload an image and
Click to Ad produces a video ad variation tuned for ecommerce use. It's the
fastest way to produce packshot-adjacent content without writing a cinematic
prompt. Use it for product ads, ecommerce variations, and quick-turn commercial
content. For the full Click to Ad decision tree, companion product-ad apps
(Packshot, Giant Product, Macro Scene, Billboard Ad, and the rest of the ad
family), see higgsfield-apps.
The standalone voice workspace — and the most commonly misplaced one on the platform, because Higgsfield has three distinct audio surfaces that all sound similar by name. This workspace is the one where audio is the deliverable itself, not a layer baked into a video and not a sync target for a generated face.
When to use:
Three core capabilities:
Input characteristics:
The prompt's role: voice descriptors and direction notes. Tone (calm/urgent/conversational/authoritative), age range, accent, energy, and pacing are all directable through the prompt. The synthesis itself is handled by the audio engine — the prompt steers performance, not synthesis.
Distinction from Lipsync Studio: Lipsync Studio puts a voice (often generated here) onto a video character. The sync direction there is audio-to-video — the face follows the audio. Higgsfield Audio standalone produces voice as a deliverable in its own right, with no video involvement required. If the user wants a talking character on screen, route to Lipsync Studio; if they want a voice file, this is the workspace.
Distinction from in-video audio: the SCELA layer of a Cinema Studio
generation (dialogue, SFX, ambient, BGM) is baked into the video at
generation time. That work lives in higgsfield-audio. Standalone Higgsfield
Audio is voice-as-asset — a separate deliverable, not a layer.
Cross-reference: for the in-video audio layer design (SCELA, dialogue
blocking, ambient sound design, BGM direction), see higgsfield-audio. For
AI actor voices that pair with avatars and Soul Cast characters, see
higgsfield-soul. For when the voice asset produced here gets dropped onto a
generated face, see Lipsync Studio above.
Collab is Higgsfield's built-in collaboration space — the team-and-community layer that sits across the workspaces above. It is where a campaign or scene stops being a solo job and becomes a shared one. Use it when more than one person needs to generate, review, or talk through work together.
Shared projects. A project is a shared space where members generate together, chat, share assets, and hop on calls. Projects have three access levels:
Real-time communication. Chat is built into every project. Any project with two or more members supports audio and video calls — join, leave, and mute from inside the project, with a persistent call bar that stays visible as you navigate so you never lose the call.
Share to Collab. Send any generation straight into the project chat with one tap using the Share to Collab toggle. Teammates see the output along with its prompt, model, and progress, so they can react, give feedback, or build on it immediately.
Community feed. A recommended-and-trending feed of published work across the platform, for discovery and inspiration.
Orgs & Team Plans. Free Orgs enable collaborative identity sharing; paid Team Plans unlock shared credits, shared elements, admin controls, and SSO. Users also earn karma by liking, commenting, generating, and inviting friends, and can exchange karma for credits.
Collab vs Shared Canvas. Collab is project-level collaboration — shared spaces, chat, calls, and a community feed. Shared Canvas (see
../higgsfield-canvas/SKILL.md§ Shared Canvas) is board-level live co-editing of a single node graph. Reach for Collab to organize a team and a campaign; reach for Shared Canvas to build one pipeline together in real time.
This sub-skill documents only the collaboration features Higgsfield publishes; it does not assert limits beyond those.
Every workspace follows the same high-level project flow. Memorizing this sequence means you can navigate any new workspace without re-learning it.
Workspace-first is a routing layer that sits ABOVE the MCSLA prompt formula. Once you're inside the right workspace, MCSLA (Model · Camera · Subject · Look · Action) still governs how the prompt itself is built. Workspaces don't replace MCSLA — they decide which environment you'll apply MCSLA inside. A Cinema Studio prompt, a Draw to Video prompt, and a Click to Ad prompt all benefit from MCSLA discipline, but the UI controls, defaults, and model options around each prompt are different. Choose the workspace first; then apply MCSLA cleanly inside it.
higgsfield-cinema — prompt patterns for Cinema Studio (all modes)higgsfield-audio — audio layer design for Lipsync Studio and in-video audiohiggsfield-soul — character references and Soul Cast avatars, often upstream of Lipsynchiggsfield-apps — one-click workflows, including sketch-based and trend-based entry pointshiggsfield-models — model selection once a workspace is chosenhiggsfield-prompt — MCSLA formula applied inside any workspace© OSideMedia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/higgsfield-workspaces of OSideMedia/higgsfield-ai-prompt-skill.
Open the folder on GitHubat commit 7075497
Higgsfield Workspaces 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Higgsfield Workspaces this skillOSideMedia/higgsfield-ai-prompt-skill | 701 | — | ~4.6k | Automated safety check: Pass | MIT | |
| Video Generationbytedance/deer-flow | 83k | 4 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Video Shotseternityspring/reelbench-skills | 868 | 2 repos | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| Video Cover Imageitwanger/toBeBetterJavaer | 18k | — | ~3.3k | Automated safety check: Pass | None | |
| Seedancesongguoxs/seedance-prompt-skill | 2.9k | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 59k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 |
bytedance/deer-flow
Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.
eternityspring/reelbench-skills
拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.
itwanger/toBeBetterJavaer
Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
cclank/lanshu-create-ai-presenter-video
Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed in one of nine visual explainer styles…
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…
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…
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…
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…
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…
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.
Categories
A skill your agent uses when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad /…. Higgsfield Workspaces is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. Use when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad / Higgsfield Audio (Sora 2 Trends is built on the retired Sora 2), or is asking 'what should I use for X'.
Higgsfield Workspaces fits situations like: the user is unsure which Higgsfield workspace fits their task; is asking what should I use for X.
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a claude-code`. Or copy the skill folder (skills/higgsfield-workspaces in OSideMedia/higgsfield-ai-prompt-skill) into .claude/skills/higgsfield-workspaces in your project. Claude Code loads it when a task matches its description.
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-workspaces -a codex`. Or copy the skill folder (skills/higgsfield-workspaces in OSideMedia/higgsfield-ai-prompt-skill) into .agents/skills/higgsfield-workspaces in your project. Codex loads it when a task matches its description.
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-workspaces -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-workspaces, .gemini/skills/higgsfield-workspaces, .github/skills/higgsfield-workspaces and .opencode/skills/higgsfield-workspaces in your project.
SKILL.md names no scripts, command-line tools or credentials: Higgsfield Workspaces is instructions for the agent only.
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.
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.
Higgsfield Workspaces is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Higgsfield Workspaces: Video Generation (bytedance/deer-flow, 83k stars), Video Shots (eternityspring/reelbench-skills, 868 stars), Video Cover Image (itwanger/toBeBetterJavaer, 18k stars) and Seedance (songguoxs/seedance-prompt-skill, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
OSideMedia (a GitHub user) maintains it in OSideMedia/higgsfield-ai-prompt-skill, which has 701 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.