Agent skill

Higgsfield Workspaces

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

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 /…

MITAuto-check passedMedia & Creative

Install Higgsfield Workspaces

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

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

GitHub CLI
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-workspaces --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-workspaces .claude/skills/higgsfield-workspaces && 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-workspaces
GitHub stars
701
Token cost
~4.6k tokens
SKILL.md length
2,588 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

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 /…

  • Works in 6 steps: Open the right workspace — the one… → Choose the right feature inside it —… → Select the model that fits the job —… → …
  • The user is unsure which Higgsfield workspace fits their task
  • SKILL.md covers Introduction, The Decision Matrix, Workspace Descriptions and The Six-Step Project Logic, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

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.

When your agent uses it

  • The user is unsure which Higgsfield workspace fits their task
  • Is asking what should I use for X

Example prompts

  • “what should I use for X”
  • “/higgsfield-workspaces”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Open the right workspace — the one matching your production problem.
  2. Choose the right feature inside it — mode, preset, or tool that fits the
  3. Select the model that fits the job — quality, speed, and cost tradeoffs
  4. Prepare the input — hero frame, reference image, source video, audio
  5. Add the prompt, script, or controls — MCSLA for scene prompts, UI
  6. Generate, review, iterate — expect multiple passes. Change one variable

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 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.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k

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). 2,588 words, ~4,593 tokens.

Download SKILL.mdSave it as .claude/skills/higgsfield-workspaces/SKILL.md (or your agent's skills folder).
name
higgsfield-workspaces
description
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.
user-invocable
true
metadata.tags
higgsfield, workspaces, routing, decision, cinema-studio, lipsync, draw-to-video, viral-hub, sora-trends, click-to-ad, higgsfield-audio
metadata.version
1.3.0
metadata.updated
2026-09-26
metadata.parent
higgsfield

Higgsfield Workspaces — Task-First Decision Layer

Introduction

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.


The Decision Matrix

Your production problemStart with workspace
Cinematic scene with deliberate camera directionCinema Studio
Speaking character, dubbing, or avatar videoLipsync Studio
Rough idea, sketch, or storyboard testDraw to Video / Sketch to Video
Fast short-form or viral-style contentViral Hub presets (Sora 2 Trends is built on the retired Sora 2 — see its section)
Product ad or ecommerce variationClick to Ad
Narration, voice swap, or translationHiggsfield 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.


Workspace Descriptions

Cinema Studio

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.

Lipsync Studio

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.

Draw to Video / Sketch to Video

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:

  • Early ideation, when you're still deciding what the shot wants to be.
  • Shot blocking experiments — testing how a composition reads in motion.
  • Pre-production validation before committing to Cinema Studio scene work.
  • Fast iteration on framing, staging, and silhouette before the prompt or reference set is locked.

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:

  • Realization pattern — describe the scene the sketch was pointing toward, including lighting and mood, and end with a camera direction that matches what the sketch implies. Use this when you want a faithful interpretation of the rough drawing.
  • Variation pattern — keep the blocking implicit (the sketch handles it) and use the prompt to swap style, lighting, genre, or time-of-day across multiple generations. Same composition, different treatments. Useful for picking a visual direction before committing.

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.

Viral Hub presets

[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:

  • TikTok, Reels, and Shorts deliverables — anywhere the format itself is more important than full cinematic control.
  • Trend-jacking, where speed of iteration and platform fluency beat per-shot polish.
  • Content where the audience expects a specific format-native rhythm rather than a deliberate director's hand.

Distinguishing features:

  • Vertical-first composition. 9:16 is the default, with 1:1 and 4:5 also common. Compositions are framed for phones, not for film.
  • Pacing optimized for short-attention spans. Fast cuts, hook-driven openings, and a "payoff by second three" structure are baked into the templates rather than something the prompt has to enforce.
  • Templated patterns for common trend formats. POV reveals, before-and-after flips, "tell me without telling me" setups, day-in-the-life loops, and similar recurring structures each have a starting template. Picking the template is most of the structural work.

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.

Click to Ad

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.

Show full SKILL.md (1,121 more words)Show less
Higgsfield Audio

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:

  • Voiceover work where the final output is an audio file (narration, podcast inserts, ad reads, e-learning tracks).
  • Voice swap on an existing audio track — change who says it without changing the timing or the emotional shape of the performance.
  • Translation of an existing audio track into another language, ideally preserving as much of the original speaker's character as the engine supports.
  • Any time you need a voice asset that will be fed into a downstream workspace (a finished track to feed into Lipsync Studio, an ad read to drop under a Click to Ad video, narration to underlay a Cinema Studio sequence).

Three core capabilities:

  • Voiceover generation. Text in, spoken audio out. Voice characteristics — gender, age range, tone, pacing, energy level — are directable. Use this for greenfield voice work where there is no source audio.
  • Voice swap. Source audio in, same audio in a different voice out. The timing, prosody, and emotional inflection of the original performance carry over; only the speaker identity changes. This is the right tool when an existing performance is structurally good but the voice is wrong (a bad scratch track, a placeholder read, an unlicensable original).
  • Translation. Source audio in, the same content rendered in another language out. Where the engine supports it, the original speaker's voice characteristics are preserved across the translation, so the localized version still sounds like the same person.

Input characteristics:

  • For voiceover: clean text or a script. Stage directions and tone notes belong in the prompt, not in the script body.
  • For voice swap: source audio plus a target voice reference. The cleaner the source, the cleaner the swap.
  • For translation: source audio plus the target language. Optionally a voice match preference if the engine offers it.

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.


Higgsfield Collab

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:

  • Private — invited members only.
  • Public — discoverable, view-only for non-members.
  • Open — anyone can join with owner approval.

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.


The Six-Step Project Logic

Every workspace follows the same high-level project flow. Memorizing this sequence means you can navigate any new workspace without re-learning it.

  1. Open the right workspace — the one matching your production problem.
  2. Choose the right feature inside it — mode, preset, or tool that fits the specific shot or asset you're producing.
  3. Select the model that fits the job — quality, speed, and cost tradeoffs live here, inside the workspace you already chose.
  4. Prepare the input — hero frame, reference image, source video, audio clip, or any starting asset the workspace expects.
  5. Add the prompt, script, or controls — MCSLA for scene prompts, UI settings for Cinema Studio, motion reference for Motion Control, and so on.
  6. Generate, review, iterate — expect multiple passes. Change one variable per iteration so you can tell what drove the improvement.

Relationship to MCSLA

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 audio
  • higgsfield-soul — character references and Soul Cast avatars, often upstream of Lipsync
  • higgsfield-apps — one-click workflows, including sketch-based and trend-based entry points
  • higgsfield-models — model selection once a workspace is chosen
  • higgsfield-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

Files

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

Open the folder on GitHubat commit 7075497

Compare with similar skills

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.

Higgsfield Workspaces compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Higgsfield Workspaces this skillOSideMedia/higgsfield-ai-prompt-skill701—~4.6kAutomated safety check: PassMIT
Video Generationbytedance/deer-flow83k4 repos~1.4kAutomated safety check: PassMIT
Video Shotseternityspring/reelbench-skills8682 repos~1.8kAutomated safety check: NotesApache-2.0
Video Cover Imageitwanger/toBeBetterJavaer18k—~3.3kAutomated safety check: PassNone
Seedancesongguoxs/seedance-prompt-skill2.9k1 repos~2.5kAutomated safety check: PassNone
HyperFrames Video Entry Pointheygen-com/hyperframes59k3 repos~5.2kAutomated safety check: PassApache-2.0

Similar skills

  • 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.

    83k GitHub starsUsed in 4 repos~1.4k tokens
    Media & CreativeAuto-check passed
  • Video Shots

    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.

    868 GitHub starsUsed in 2 repos~1.8k tokens
    Media & CreativeAuto-check: notes
  • Video Cover Image

    itwanger/toBeBetterJavaer

    Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.

    18k GitHub stars~3.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Seedance

    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"…

    2.9k GitHub starsUsed in 1 repo~2.5k tokens
    Media & CreativeAuto-check passed
  • 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.

    59k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Lanshu Create AI Presenter Video

    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…

    2.5k GitHub stars~3.6k tokensUpdated 2 days ago
    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…

    701 GitHub stars~9.1k tokensUpdated 11 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…

    701 GitHub stars~2.9k tokensUpdated 11 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…

    701 GitHub stars~5.1k tokensUpdated 11 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…

    701 GitHub stars~2.3k tokensUpdated 11 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…

    701 GitHub stars~2.3k tokensUpdated 11 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.

    701 GitHub stars~5k tokensUpdated 11 days ago
    Auto-check passed

Questions about Higgsfield Workspaces

What does Higgsfield Workspaces do?

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'.

When should I use Higgsfield Workspaces?

Higgsfield Workspaces fits situations like: the user is unsure which Higgsfield workspace fits their task; is asking what should I use for X.

How do I install Higgsfield Workspaces in Claude Code?

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.

How do I install Higgsfield Workspaces in Codex?

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.

Can I use Higgsfield Workspaces 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-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.

What does Higgsfield Workspaces need to run?

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

Does Higgsfield Workspaces 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 Workspaces 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 Workspaces use?

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.

How many tokens does Higgsfield Workspaces use?

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.

What are the alternatives to Higgsfield Workspaces?

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.

Who maintains Higgsfield Workspaces?

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.