Agent skill · Audited from source
Higgsfield Cinema
skill · OSideMedia/higgsfield-ai-prompt-skillMIT licenceAudited 26 Oct 2026 · source 9e3a2f685c72
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 9e3a2f685c72 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and…
Cite
Cite this page
ModelsAtlas. “Higgsfield Cinema (OSideMedia/higgsfield-ai-prompt-skill)”. Retrieved 26 Oct 2026. https://modelsatlas.com/skills/osidemedia/higgsfield-cinema
Trust audit
Audit 0.4.1 · source read 26 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 9e3a2f685c72 · 26 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- PublisherOSideMedia GitHub userOwner of the repository this skill is read from
- Source folderOSideMedia/higgsfield-ai-prompt-skill/skills/higgsfield-cinemaThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict9e3a2f685c72A new audit runs when the source changes
- Repository statusNot archivedLast push 1 day ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and…
--- name: higgsfield-cinema description: "Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements. Use when the user mentions Cinema Studio, Cinema Studio 2.5, Cinema Studio 3.0, Cinema Studio 3.5, Cinema Studio 4.0 (`cinematic_studio_video_4_0` — its four modes, camera/lens/aperture/era/genre/pacing ids, light presets, color palette), Soul Cast, color grading, multi-shot video, shot sequences, storyboard workflow, Hero Frame, optical stack, keyframe interpolation, Elements system (@Characters/@Locations/@Props), Speed Ramp, Director Panel, Higgsfield Popcorn, Single Shot / Multi-Shot Auto / Multi-Shot Manual modes, Reference Anchor, Smart shot control, or any professional filmmaking workflow inside Higgsfield." user-invocable: true metadata: tags: [higgsfield, cinema-studio, cinema-studio-4, multi-shot, storyboard, popcorn, hero-frame, optical, elements, director-panel, speed-ramp, soul-cast, color-grading] version: 3.5.3 updated: 2026-09-26 parent: higgsfield --- # Higgsfield Cinema Studio 2.5 ## QUICK FACTS *Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.* - Four Cinema Studio versions are on the platform (2.5 / 3.0 / 3.5 / 4.0) — user-selected, no auto-routing; always detect the version first [→](#-version-detection--ask-first) - **Cinema Studio 4.0** (`cinematic_studio_video_4_0`, CLI workflow schema 2026-09-26): the same four modes as `seedance_2_5` (t2v / omni_reference / video_edit / video_extension), 480p–1080p, start/end image + image/video/audio refs; the 3.5 enum pills are GONE — camera / lens / aperture / era / genre / pacing are free `*_id` strings with no published values, so never invent one [→](#cinema-studio-40) - 4.0 vs 3.5 at the API: no `multi_shots` / `multi_prompt`, no `genre` enum, no `enhance_prompt`; `prompt` now REQUIRED; audio defaults ON; duration default 5s (range unpublished) [→](#what-changed-from-35-at-the-api) - Hard 512-character prompt cap; 2.5 @ Element chips eat ~80–100 hidden chars each [→](#-prompt-character-limit--512-characters) - Elements System: define @Characters/@Locations/@Props once, call everywhere [→](#elements-system--define-once-call-everywhere) - 3.5 main UI = three pills (Genre / Style / Camera), each Auto by default — override only with a creative reason [→](#the-three-pill-main-surface) - 7 confirmed 3.5 genres: General · Action · Horror · Comedy · Noir · Drama · Epic — never invent genre names [→](#cinema-studio-35-genres) - Style presets: 8 Color Palettes · 6 Lighting · 9 Camera Moveset Styles, or free-form Manual Style [→](#style-settings--three-operating-modes) - Camera axes: 3 bodies · 5 lenses · focal 8/14/35/50/75mm · aperture f/1.4–f/4–f/11; two camera vocabularies coexist — vocabulary follows the selected model [→](#camera-settings--four-axis-panel) - Output enums: 7 aspect ratios incl. 21:9 · 480p/720p/1080p · duration 4–15s · Sound On/Off [→](#cinema-studio-35-output-controls) - Lead every delivered shot with the one-line settings strip (UI presets ≠ prompt text; never restate strip values in the body) [→](#per-shot-settings-strip) - The UI shot counter caps internal cuts — "strictly N shots" must keep N within it (observed cap 4; API exposes no max — UI behavior, verify live) [→](#per-shot-settings-strip) - Manual Style = saved ≤2,000-char block of project LAWS (grade, lighting law, texture, performance register); it replaces the preset axes [→](#manual-style--authoring-guide) - 480p drafts validate the prompt, NOT the take — no seed param; transfer a look via Hero Frame + start/end-frame pinning [→](#drafts-validate-the-prompt-not-the-take) - Resolution matrix has two axes: shot physics × delivery context; 4K-finish pipelines master at model max res in std mode [→](#physics-rendering--resolution-decision-matrix) - Seedance fast mode cannot output 1080p — drafting in fast then "switching up" silently changes mode AND res [→](#physics-rendering--resolution-decision-matrix) - Big reference blocks live beside this file: 2.5 + 3.0 per-mode output templates in `references/output-formats-2-5-3-0.md`; Motion / Outfit / Palette / Product sheet specs in `references/reference-sheet-types.md` [→](#per-version-delivery-templates) Cinema Studio is Higgsfield's professional filmmaking environment — a full production workflow for multi-shot, character-consistent cinematic content. It's fundamentally different from single-clip generation: you're building sequences, not individual videos. --- ## Cinema Studio vs Standard Generation | | Standard Generation | Cinema Studio 2.5 | Cinema Studio 3.0 (Business/Team Plan) | Cinema Studio 3.5 | |--|--------------------|--------------------|----------------------------------------|--------------------| | Output | Single clip | Multi-shot sequence | Multi-shot sequence | Multi-shot sequence | | Character consistency | Manual / Soul ID only | Reference Anchor system | @ reference system (up to 9 images) | @ reference system (extends 3.0) | | AI actor generation | Not available | Soul Cast — generate actors from parameters (no photos) | Soul Cast — General (2K) / Character (4K) / Location (4K) modes, 0.125 credits | Same Soul Cast surface — see 3.0 | | Camera control | Named presets | Director Panel (18 movements) | Director Panel + Smart (auto camera planning) | Camera Settings 4-axis panel (Camera Body / Lens / Focal Length / Aperture) — see Cinema Studio 3.5 section | | Optical physics | Not available | Full camera body + lens stack | Not available | Available — restored via Camera Settings panel (different vocabulary from 2.5 — see Cinema Studio 3.5 section) | | Color grading | Not available | Built-in suite (temp, contrast, grain, bloom, etc.) |
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 9e3a2f6
git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill git -C higgsfield-ai-prompt-skill checkout 9e3a2f685c72
The author documents no install command, so this uses the repository directly. Our verdict covers commit 9e3a2f685c72 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
9e3a2f685c72
Similar skills
OSideMedia/higgsfield-ai-prompt-skill
Use 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 generations, or named moodboard styles like…
OSideMedia/higgsfield-ai-prompt-skill
Use when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Wan (incl. Wan 3.0), Seedance (incl. 2.5), Veo 3, Minimax Hailuo / MiniMax H3, FLUX 3 Video, Gemini Omni…
OSideMedia/higgsfield-ai-prompt-skill
Use when the user mentions Marketing Studio, DTC Ads, ad video, UGC video, the marketing_studio_video MCP model, or wants to generate one of the 9 Marketing Studio ad presets (UGC, Tutorial, Unboxing, Hyper Motion,…
OSideMedia/higgsfield-ai-prompt-skill
Use 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 treatments, or create stylized…
OSideMedia/higgsfield-ai-prompt-skill
Use 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 (close-up, wide shot, cowboy shot, etc.), or…
OSideMedia/higgsfield-ai-prompt-skill
Use when the user mentions GPT Image 2.0 or GPT Image 2.5, gpt-image-2, gpt-image-2.5, gpt_image_2_5, GPT-Image-2 prompts, the Flare / Sunburst variants, a transparent-background image, or wants to generate an image…
Questions about Higgsfield Cinema
What does the Higgsfield Cinema skill do?
Is Higgsfield Cinema safe to install?
What can Higgsfield Cinema access on my machine?
How current is this page?
Sources
- github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skill — the audited source at commit 9e3a2f685c72 and every finding aboveObserved · 26 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Higgsfield Cinema skill do?
- Is Higgsfield Cinema safe to install?
- What can Higgsfield Cinema access on my machine?