higgsfield

Higgsfield AI Prompt Skill

<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->

Contents

• HARD RULES — pre-delivery checklist
• What Is Higgsfield?
• Working Folders — file handling
• Handling a Request
• Fast Path — Simple Creative Requests
• Full Path — Production Requests
• Route to the Right Skill
• Load Map — how much to read
• Check Templates for Genre Match
• Build the Prompt Using the MCSLA Formula
• Output Format
• Generation Ledger — log every result
• @ Reference Rules
• Shared Resources
• Reference files inside sub-skills
• Sub-Skills — open skills/<name>/SKILL.md yourself

<!-- /CONTENTS -->

Language rule: Reply in whatever language the user writes in.

Paths: every path in this file (skills/…, templates/…, specs/…, scripts/…,

db/…) is relative to the folder this SKILL.md lives in, not to the user's working

directory. A path inside any other file is relative to that file's own folder

(../../specs/… in a sub-skill climbs back to this one). Two exceptions:

workspace/ lives in the user's working directory, and the learning memory may live

outside this folder (both in § Working Folders). Sub-skills are plain

files, not separately registered skills: nothing loads them for you, so open

skills/<name>/SKILL.md yourself.

MCP tools: Higgsfield:<tool> (e.g. Higgsfield:models_explore) means that tool on

the Higgsfield MCP server (https://mcp.higgsfield.ai/mcp). Its name in your tool list

depends on how it was added — the claude.ai connector shows up in Claude Code as

mcp__claude_ai_Higgsfield__<tool> — so match on the Higgsfield server, never on a

same-named tool from another server. A bare tool name in a sub-skill means the same.

---

HARD RULES — pre-delivery checklist

These rules apply to every Higgsfield response. They are written as a pre-delivery checklist the agent runs *before* sending the response, not as prohibitions stated and then forgotten. The failure mode they prevent is plausibility-over-verification — producing a response that looks correct because the agent's training data knows the rough shape of Higgsfield work, rather than because the agent actually read the skill files and verified the platform's ground truth.

Before delivering any Higgsfield response, confirm in this order:

1. Routing line present. First line of response names which sub-skills you routed to (e.g. "Routing to higgsfield-prompt + higgsfield-camera for an Atmosphere push-in"). One line, then the work. Missing routing line = response is incomplete; add it.

2. Routed sub-skills opened and read in this conversation. Match the user's ask to the routing table below, open the matching sub-skill files (skills/<name>/SKILL.md) with the read tool, and READ them. Root SKILL.md and skills/higgsfield-prompt/SKILL.md are mandatory at minimum on any prompt request. Grepped snippets do not satisfy this rule. Full reads do. If your only access to root SKILL.md or skills/higgsfield-prompt/SKILL.md in this conversation came from grep results, you have not satisfied this rule — open the file. Platform vocabulary, preset names, and model parameters must come from the files because this platform's lineup changes between releases.

3. Named vocabulary verified, not invented. Camera preset names, motion preset names, model names, CLI flag forms, and MCP tool parameter names all come from the skill files or from verification. For model parameters, enums, and durations, verify against specs/model-specs.yaml first — it is generated from a dated models_explore snapshot (see snapshot_date inside the file); if the snapshot is stale (>30 days), verify live instead (higgsfield model get <model> for CLI param schemas; Higgsfield:models_explore for MCP). If you found yourself thinking "this flag probably looks like X" or "this preset is probably called Y" — stop. Read the file or run the verification command. Plausibility is not validity. Do not substitute generic video-prompt vocabulary for named Higgsfield presets; do not invent model versions, camera presets, or motion-preset names. If the user names one you don't see in the skill files, say so and ask for clarification.

4. MCSLA structure intact on video prompts. Model · Camera · Subject · Look · Action. Five layers, every video prompt, unless the user explicitly opted out.

5. Shared negative constraints appended. Pull positive-phrasing prevention phrases from skills/shared/negative-constraints.md. Do not paraphrase from training; use the exact phrasing from the file. (Kling 3.0 prefers positive phrasing over negations; using negation-form constraints when the file says positive is a fidelity miss.)

6. Preflight surfaced when applicable. If execution intent is signaled (CLI / MCP / bundled-skills mentioned) AND a video-class or high-cost model is named OR a budget concern is named, surface the two-step preflight (model get / Higgsfield:models_explore for schema, then cost estimate). See skills/higgsfield-stack/SKILL.md § Preflight discipline.

7. Aspect ratio is an enum, not a free-form value. Check the model's allowed ratios against specs/model-specs.yaml before writing them into the header; if the snapshot is stale (>30 days), verify live via schema (Higgsfield:models_explore / model get). Example of why this matters: Seedance 2.0 supports native 21:9, Kling 3.0 does not. Anamorphic / 2.35:1 / 2.39:1 are *style register* vocabulary for the Look line, not output ratios. See vocab.md § Aspect Ratio: output spec vs. style register. In a multi-shot Seedance sequence whose location plates carry a baked lens, whether the optics words still belong in the video prompt (Style Prefix included) is OPEN — one studio drops them, Hell Grind keeps the look in both (skills/higgsfield-seedance/SKILL.md § Bake it into the asset; skills/shared/house-rulings.md P2-6).

8. Prompt under 200 words — short-form regime only. Soft cap from MCSLA section. Going over is a signal you're padding rather than locking — tighten. Regime exception: block-scaffold production prompts (skills/higgsfield-seedance/SKILL.md § Official Prompt Architecture) replace the word cap with structural lint — harvested production Seedance briefs run 218–2,059-word medians depending on register [FIELD — 13-project community harvest, 2026-07-18]. The cap governs single-shot MCSLA prompts; a block-scaffold prompt over 200 words is not a rule-8 violation.

If any of items 1–8 are missing or unverified, the response is incomplete. Complete them before sending, not after.

---

What Is Higgsfield?

Higgsfield is a cinematic AI video and image generation platform built for filmmakers and

creators. Unlike single-model tools, Higgsfield hosts multiple generation engines on one

platform — Kling 3.0/3.0 Omni/3.0 Motion Control, Google Veo 3.1/3.1 Lite, Wan 2.7/2.6/2.5,

Seedance 2.5/2.0/Pro, FLUX 3 Video, Minimax Hailuo 2.3/02, Higgsfield DoP (Lite/Standard/Turbo) for video; Soul 2.0, Soul Cinema Preview,

Soul Cast, Nano Banana Pro/2, Kling Image 3.0/Omni, Seedream 5.0 Pro/Lite/Flash + 4.5, GPT Image 2.0 / 2.5,

Flux 2/Kontext for images — plus a library of 100+ named Motion Presets, a Soul ID

character consistency system, Cinema Studio 2.5, Cinema Studio 3.0 (Business/Team plan), and Cinema Studio 3.5 with Soul Cast AI actors, native dual-channel stereo audio, and 80+

one-click Apps. Sora 2 is retired from this skill's recommendations: OpenAI shut the Sora 2 API down on 2026-09-24; Higgsfield only ever offered it in its web UI, and whether the UI still does is unconfirmed. For scale / physics shots use Seedance 2.0 or Minimax Hailuo 2.3 (model-guide.md). Catalog check (2026-09-26): Kling 3.0 Omni, Wan 2.5, Seedance Pro, Higgsfield DoP, Soul Cinema Preview and Kling Image 3.0 / Omni are not in the API catalog (higgsfield model list / workflow list). They may be UI-only — verify in the live UI before recommending them, and prefer a catalog pick where model-guide.md names one. No catalog variant of Minimax Hailuo is named 02.

---

Working Folders — file handling

workspace/ lives in the user's current working directory (the folder the

session was started in), not in this skill's folder. Use its three subfolders for

every task that involves a user-provided document or a file you produce. This keeps

uploads and deliverables out of the project root.

• Session started inside this repo (Cowork with the repo folder as the workspace,

or Claude Code opened here): it is this repo's own workspace/.

• Skill installed elsewhere (e.g. ~/.claude/skills/higgsfield/) **while working in

another project:** use <that project>/workspace/, creating input/, output/ and

processed/ there on first use. Never put the user's files in the skill's install

folder — a reinstall replaces that folder and everything in it.

| Folder | Role | Your behavior |

|--------|------|---------------|

| workspace/input/ | Documents the user wants you to read (scripts, story bibles, briefs, character sheets, references). | Read from here first. If the user's file is somewhere else, copy it into workspace/input/ and leave the original where it is — never move or delete it. When you need a document from the user, ask them to drop it in workspace/input/. |

| workspace/output/ | Files you generate for the user (prompt packs, shot breakdowns, batch CSVs, reports, exported docs). | Write every file deliverable here, not to the project root. Tell the user the path when you finish. |

| workspace/processed/ | Inputs you have finished consuming. | When a task is complete, move the file from input/ to processed/ so input/ stays clean. Never delete the user's files — relocate them. |

Rules:

• Never scatter user uploads or generated files across the project root or skill folders — route them through workspace/.
• Treat workspace/input/ as the canonical place to look when the user says "the script / bible / reference I gave you."
• In this repo the three folders' contents are git-ignored. In another project they are not unless the user ignores them: never assume anything in them is committed or private, and ask before editing the user's .gitignore.

The memory folder. The filter memory, quality memory and generation ledger live in

one folder, and only scripts/higgsfield_memory.py reads or writes it. When this skill

runs from a Claude Code skill install (a .claude/skills/<name>/ folder), the memory

folder is ~/.higgsfield-skill/db/, copied from this skill's db/ on first use, so a

reinstall or update cannot erase it. Anywhere else (a Cowork workspace, a clone of the

repo) it is this skill's own db/. The HF_DB_DIR environment variable overrides both.

python3 <this skill's folder>/scripts/higgsfield_memory.py where prints the folder in

use; give the user that path when they ask where their memory is or before a reinstall.

If its unmerged list is not empty, another install held entries the memory folder

lacks (its own memory from before v3.42.0, or starter entries from a newer release): they

were kept there, not merged. Tell the user once.

Handling a Request

Fast Path — Simple Creative Requests

If the user provides a clear creative intent ("write me a prompt for a car chase at night")

with no specific constraints, generate immediately using these sensible defaults:

> Fast Path still requires reading skills/higgsfield-prompt/SKILL.md first — Fast Path means skip clarifying questions, NOT skip the file read.

| Parameter | Default |

|-----------|---------|

| Aspect ratio | 16:9 |

| Duration | 8s (Kling lanes — see Seedance exception below) |

| Style | Cinematic |

| Video model | Kling 3.0 (character-focused) or Seedance 2.0 (action/scale/references) |

| Image model | Soul 2.0 (portrait) or Nano Banana 2 (everything else) |

Do not ask clarifying questions. Deliver a ready-to-paste prompt. Mention the defaults

used so the user can adjust if they want something different.

> Seedance exception: Seedance 2.0 never gets a silently defaulted runtime

> (skills/higgsfield-seedance/SKILL.md — always ask, never default). On Fast

> Path that means: if the user named no duration, route video to Kling 3.0;

> pick Seedance 2.0 only when the request names a duration — or when the user

> asked for Seedance by name, in which case state the assumed runtime as the

> first adjustable default in the delivery.

> If you did not read skills/higgsfield-prompt/SKILL.md earlier in this conversation, read it now before writing the prompt.

Full Path — Production Requests

When the user signals production-grade intent (Cinema Studio, multi-shot, specific model,

budget constraints, client work), confirm before generating:

Required:

• Generation type: Image / Video / App (one-click)
• Video duration: model-dependent enum — check the model's duration values in specs/model-specs.yaml before offering choices (e.g. Seedance 2.0 4–15s, Veo 3.1 4/6/8s; image-to-video clips trend short)
• Aspect ratio: 16:9 / 9:16 / 1:1 / 4:5 / 4:3 / 21:9-where-supported (default: 16:9) — enums per model in specs/model-specs.yaml (HARD RULE 7); anamorphic / 2.35:1 / 2.39:1 are Look-line style register, never output ratios
• Model preference (or ask Claude to recommend — see skills/higgsfield-models/SKILL.md)

Optional (skip if user already provided):

• Visual style: Cinematic / VHS / Super 8MM / Anamorphic / Abstract
• Soul ID character reference (if character consistency needed)
• Reference image for image-to-video
• Motion preset preference

> Ask everything in one message — do not split across multiple rounds.

---

Route to the Right Skill

| User wants | Route to |

|------------|----------|

| User unsure which workspace/tool fits, or asks "what should I use for X" | skills/higgsfield-workspaces/SKILL.md |

| Write or improve a prompt | skills/higgsfield-prompt/SKILL.md + relevant sub-skills |

| Develop a character / world / story / premise before prompting, build a character sheet / story bible, lock a visual style ("visual DNA"), keep a character consistent across many shots, or "I keep getting generic AI characters" | skills/higgsfield-character-design/SKILL.md |

| Audit or strengthen a scene / sequence / beat outline before generating it, or "is this scene working", "what's weak here", "why doesn't this land" | skills/higgsfield-scene-engine/SKILL.md |

| Cinematic still image prompt (shot framing, angles) | skills/higgsfield-image-shots/SKILL.md |

| GPT Image 2.0 / 2.5 / gpt-image-2 / gpt_image_2_5 prompt, Flare / Sunburst, transparent-background image, UI mockup, infographic, character/reference sheet, layout-dense image, or static-ad recreation | skills/higgsfield-gpt-image-2/SKILL.md |

| Choose the right model — incl. which lane edits existing footage, which model makes one clip longer than 15s, or motion transfer (Genjutsu vs Kling Motion Control) | skills/higgsfield-models/SKILL.md + model-guide.md (§ Edit-Lane Chooser, § Long-Take Chooser) |

| Camera movement guidance (video) | skills/higgsfield-camera/SKILL.md |

| Named motion preset (Explosion, Werewolf, etc.) | skills/higgsfield-motion/SKILL.md |

| Visual style selection | skills/higgsfield-style/SKILL.md |

| Character consistency across shots | skills/higgsfield-soul/SKILL.md |

| Consistency tie-break: character consistency via a live Soul ID / reference images inside Higgsfield → skills/higgsfield-soul/SKILL.md; developing WHO the character is first (sheet, story bible, visual DNA) → skills/higgsfield-character-design/SKILL.md. Both may apply in sequence: design first, then lock with Soul. | — |

| VFX presets (Air Bending, Plasma, etc.) | skills/higgsfield-motion/SKILL.md |

| One-click App workflow | skills/higgsfield-apps/SKILL.md |

| Genre recipe (action, horror, ad, etc.) | skills/higgsfield-recipes/SKILL.md |

| Fix a failing generation | skills/higgsfield-troubleshoot/SKILL.md |

| A Seedance take came back wrong (not flagged) — reversal, babble, a third hand, gliding walk, choppy fight | skills/higgsfield-seedance/SKILL.md (skills/higgsfield-seedance/FAILURE-MODES.md) + skills/higgsfield-troubleshoot/SKILL.md (§ Stop-Rule Ladder) |

| Moodboard, style direction, Soul Hex color | skills/higgsfield-moodboard/SKILL.md |

| Visual consistency across a project | skills/higgsfield-moodboard/SKILL.md |

| Mixed Media presets (Noir, Sketch, Particles, etc.) | skills/higgsfield-mixed-media/SKILL.md |

| Photodump style preset / social-feed photo-dump aesthetic | photodump-presets.md (root reference) |

| Artistic style transformation, preset stacking | skills/higgsfield-mixed-media/SKILL.md |

| Higgsfield Assist (GPT-5 copilot) | skills/higgsfield-assist/SKILL.md |

| Credit optimization, plan selection, budget strategy | skills/higgsfield-assist/SKILL.md |

| Cinema Studio 2.5 / Cinema Studio 3.0 / Cinema Studio 3.5 / Cinema Studio 4.0 / multi-shot sequence workflow / Soul Cast | skills/higgsfield-cinema/SKILL.md |

| Cinema Studio 4.0 — cinematic_studio_video_4_0, its four modes (t2v / omni_reference / video_edit / video_extension), camera / lens / aperture / era / genre / pacing ids, light and palette controls | skills/higgsfield-cinema/SKILL.md |

| Optical physics, camera bodies, lenses, Hero Frame | skills/higgsfield-cinema/SKILL.md |

| Elements system (@Characters/@Locations/@Props) | skills/higgsfield-cinema/SKILL.md |

| Director Panel, Speed Ramp, shot modes, Popcorn | skills/higgsfield-cinema/SKILL.md |

| Cinema Studio 3.0 Smart mode, @ references, native audio | skills/higgsfield-cinema/SKILL.md |

| Cinema Studio 3.5 — three-pill UI, Style Settings, Camera Settings, Manual Style, AI director toggle | skills/higgsfield-cinema/SKILL.md |

| User mentions Marketing Studio, DTC Ads, ms_image, or marketing_studio_video model | skills/higgsfield-marketing-studio/SKILL.md |

| User wants UGC / Tutorial / Unboxing / Hyper Motion / Product Review / TV Spot / Wild Card / UGC Virtual Try On / Pro Virtual Try On ad video | skills/higgsfield-marketing-studio/SKILL.md |

| User mentions hook+setting picklists, preset / custom / text-generated avatars in MS context, or 4–15s ad video constraints | skills/higgsfield-marketing-studio/SKILL.md |

| Ad Multiplier ("multiply my ad", many independently edited versions of one 4–30s ad) or a one-off Genjutsu edit of a finished ad (swap one object / product / garment using a reference image of the new one, transfer motion) | skills/higgsfield-marketing-studio/SKILL.md (§ 14) — a swap described in words only, with no reference image of the replacement, is Seedance 2.5 video_edit (model-guide.md § Edit-Lane Chooser) |

| User wants to run a full campaign pipeline — research → plan → generate → publish → report, "create a campaign", "100 UGC videos", content plan, batch ads, cost-savings report | skills/higgsfield-content-factory/SKILL.md |

| User mentions Higgsfield Canvas, a node-based / node-graph workspace, an infinite board, chaining prompts→images→videos into a pipeline, Shared Canvas, or a ComfyUI-style node workflow | skills/higgsfield-canvas/SKILL.md |

| Multi-shot workflow, chaining tools, full production pipeline | skills/higgsfield-pipeline/SKILL.md |

| Short film, branded content, Popcorn → video → assembly | skills/higgsfield-pipeline/SKILL.md |

| Vibe Motion, kinetic typography, animated text, infographic/data/presentation animation, logo/brand animation as code (Remotion — crisp text, exact brand colors, deployable, real-time edits) | skills/higgsfield-vibe-motion/SKILL.md |

| Animated AD / brand promo as an AI-generated video built brief → storyboard sheet → Seedance ("make a motion", "motion design ad", "animate my logo into a video", "promo/ad video", classicMD/highMD) | skills/higgsfield-motion-design/SKILL.md |

| Vibe Motion vs Motion Design (both say "motion graphics / brand / logo animation"): want crisp text, exact colors, deployable code, editable canvas → skills/higgsfield-vibe-motion/SKILL.md (Remotion code); want a cinematic/kinetic AI video clip (pixel render, native audio, no guaranteed-crisp text) → skills/higgsfield-motion-design/SKILL.md (Seedance). When unsure, ask "should the text/logo stay perfectly crisp and editable (code), or is this a rendered video clip?" | — |

| Pre-generation memory check, apply past failure fixes | skills/higgsfield-recall/SKILL.md |

| User reports a generation result (kept/rejected/flagged) — log it to the ledger | skills/higgsfield-recall/SKILL.md |

| Takes-per-kept ratios, credit budgeting from logged data | skills/higgsfield-assist/SKILL.md |

| Audio design, dialogue cues, SFX, ambient sound | skills/higgsfield-audio/SKILL.md |

| Standalone audio generation — soundtrack, ambience bed, multi-speaker scene audio, Seed Audio 1.0 (seed_audio), TTS voiceover / narration as its own deliverable | skills/higgsfield-audio/SKILL.md |

| Swap or revoice the speaker in a finished video (Higgsfield:voice_change), or clone / create a reusable voice (Higgsfield:create_voice → voice_type: element) | skills/higgsfield-audio/SKILL.md |

| A finished video in, something derived out — Shorts Studio (restyle one video into shorts), Clipify (YouTube → subtitled clips), Virality Predictor ("will this go viral", score my ad), Video Analysis (scene-by-scene breakdown), and which of these cost credits | skills/higgsfield-repurpose/SKILL.md |

| 3D — image→3D / multi-view→3D / text→3D mesh (GLB), rigging or animating a mesh, remesh / retexture, 3D Body, 3D Jutsu / Scene Builder 3D projects, a 3D turnaround as a multi-angle reference, a 3D blockout as a staging reference (Higgsfield:generate_3d, Higgsfield:scene_builder_3d_*) | skills/higgsfield-3d/SKILL.md |

| Extend / continue an existing clip — "make it longer", "what happens next / before", prequel, last-frame handoff, extension chains | a native forward/backward extension on 2.5 → skills/higgsfield-seedance-2-5/SKILL.md (video_extension); a 2.0 clip continued as a video reference → skills/higgsfield-seedance/SKILL.md (§ Extension Prompting); chaining across generations → skills/higgsfield-pipeline/SKILL.md (§ Continuation & Extension Handoff) |

| Prep assets / reference sheets before video — character sheet, prop three-view, location plate, "build my elements", variety sheet for crowds | templates/ad-asset-prep.md + skills/higgsfield-gpt-image-2/SKILL.md (props) + skills/higgsfield-soul/SKILL.md (people & crowds) |

| Audition / screen-test a designed character (how they move, speak, react) before scene generation | skills/higgsfield-character-design/SKILL.md (§ Screen Test / Audition) |

| Seedance 2.0 / Pro prompt, flagged prompt, credit waste on Seedance | skills/higgsfield-seedance/SKILL.md |

| Seedance 2.5 — user names 2.5 / Dreamina / Jimeng, wants a single clip longer than 15s, wants to edit or extend a video that already exists, or supplies many image/video/audio references (up to 30/10/10) | skills/higgsfield-seedance-2-5/SKILL.md |

| 2.0 vs 2.5 (both say "Seedance"): needs 4K, mode=fast, or a genre hint → skills/higgsfield-seedance/SKILL.md; needs >15s in one generation, video editing, forward/backward extension, or heavy multi-reference → skills/higgsfield-seedance-2-5/SKILL.md. Both do 1080p and platform start/end frames (2.5 only in omni_reference); 2.5 caps at 1080p | — |

| Character performance — acting, behavior, mannerisms, tics, a gait, subtext, "my characters look wooden / dead-eyed / AI", keeping a character themselves across many shots, an acting master profile | skills/higgsfield-acting/SKILL.md |

| Feature-film production pipeline on Seedance — headless character sheets, location sheets, a scene geography block reused across shots, dialogue construction, iteration discipline, giants / crowds / threshold transitions | skills/higgsfield-seedance/SKILL.md (skills/higgsfield-seedance/HELL-GRIND.md) |

| Transform footage the user already has (video-to-video): "make a Seedance prompt for this video/clip", add a VFX element (set my head/hair on fire, transform my hand, make a limb invisible), swap the world/background around a preserved subject (desert, clouds, lava, neon city), put a giant creature behind me or on a landmark, relight/regrade to match, sync a crash-zoom/push-in to a line — a real source clip is the starting point | skills/higgsfield-seedance-vfx/SKILL.md |

| Replace a VFX/3D pipeline with generation — "can AI do this instead of VFX", put myself in this plate, put a creature in my footage, a dragon/monster shot without buying or rigging a 3D model, "how do I build a whole VFX shot", asset sheets → size-ref → locations → shots as one pipeline; also "my v2v keeps failing / turns to slop", scale drift between two subjects, which image model for faces vs creatures vs clothing vs locations | skills/higgsfield-seedance-2-5/SKILL.md (skills/higgsfield-seedance-2-5/VFX-PIPELINE.md) |

| Precise facial expression / FACS / Action Unit codes (AU12, AU6…), forced or uncanny or mixed expression, close-up micro-performance, monologue/dialogue facial acting, "which AU code for anger/fear", FACS reference sheet | skills/higgsfield-facs/SKILL.md |

| "Make a shotlist", break a script/brief/treatment into many connected Seedance prompts, director's shotlist, global style prefix + @-glossary + named per-scene prompts as one editable HTML | skills/higgsfield-shotlist-director/SKILL.md |

| User has Higgsfield CLI / MCP / bundled skills installed and asks how this skill works alongside them | skills/higgsfield-stack/SKILL.md |

| User mentions higgsfield auth login, higgsfield generate create, mcp.higgsfield.ai/mcp, /higgsfield:generate, or asks "do I need both" | skills/higgsfield-stack/SKILL.md |

| Request is squarely one of Higgsfield's own connector workflows (character-sheet, thumbnail-generation, ugc-*, faceless-video, narrator, subtitles, product-photoshoot, brand-asset-creation, ad-multiplier, video-editing / Higgsedit) — what this library adds vs hands off | skills/higgsfield-stack/SKILL.md |

| User asks where the prompt construction ends and the CLI/MCP execution begins (handoff questions) | skills/higgsfield-stack/SKILL.md |

---

Load Map — how much to read

The routing table says *where*; this says *how much*. Loads are cumulative — every path starts from HARD RULE 2's mandatory reads.

| Situation | Load |

|-----------|------|

| Simple creative prompt (Fast Path) | root SKILL.md + skills/higgsfield-prompt/SKILL.md — nothing else |

| Any Seedance prompt | + skills/higgsfield-seedance/SKILL.md (+ the matching templates/seedance/ file when the request is technique-shaped) |

| Multi-scene / sequence / script breakdown | + skills/higgsfield-shotlist-director/SKILL.md + skills/higgsfield-pipeline/SKILL.md |

| Model choice unclear or contested | + skills/higgsfield-models/SKILL.md + specs/ (the generated spec for the output type) |

| User reports a generation result | + skills/higgsfield-recall/SKILL.md (ledger write) |

| A Seedance render failed (not filtered) | + skills/higgsfield-seedance/FAILURE-MODES.md + skills/higgsfield-troubleshoot/SKILL.md |

| Budget / credits / plan question | + skills/higgsfield-assist/SKILL.md |

| Anything else | one routing-table row → that sub-skill; resist loading more than the row names |

Check Templates for Genre Match

Before writing a prompt from scratch, check if the user's request matches a common genre

pattern. The templates/ folder contains 10 annotated example templates with line-by-line

breakdowns, recommended models, negative constraints, and variations.

| User request matches | Check template |

|---------------------|----------------|

| Chase, pursuit, action, parkour | templates/01-cinematic-action-chase.md |

| Product, commercial, ad, UGC | templates/02-product-ugc-showcase.md |

| Horror, scary, creepy, dread | templates/03-horror-atmosphere.md |

| Fashion, editorial, lookbook | templates/04-fashion-editorial.md |

| Sci-fi, cyberpunk, VFX, space | templates/05-sci-fi-vfx.md |

| Portrait, character intro, close-up | templates/06-portrait-character-intro.md |

| Landscape, nature, establishing shot | templates/07-landscape-establishing-shot.md |

| Comedy, social media, TikTok, skit | templates/08-comedy-social-media.md |

| Romance, intimate, couple, wedding | templates/09-romantic-intimate.md |

| Dance, music, performance, concert | templates/10-dance-music-performance.md |

Use the template as a starting point — adapt the example prompt to the user's specific

request. The annotations explain WHY each element works, helping you make informed

substitutions.

Technique templates (templates/seedance/) — structure templates for Seedance

prompts where the user request is technique-shaped rather than genre-shaped:

| Technique need | Template |

|---|---|

| Pre-visualize multi-character spatial geometry before prompting | templates/seedance/top-down-map.md |

| Multi-character shot with cross-character relationships | templates/seedance/multi-character-anchor.md |

| Single-character shot with position + pose + contact-point locks | templates/seedance/single-character-position.md |

| Worked example: two-character anchoring end-to-end | templates/seedance/worked-example-two-character.md |

| Anime / stylized-2D animation — layered formula + style block + character turnaround | templates/seedance/anime-animation.md |

| Close-up facial acting via FACS Action Unit codes — beat-synced expression schedule | templates/seedance/facs-expression-beats.md |

| Seedance 2.5 multi-reference brief — role map + staged beats with end states | templates/seedance/omni-reference-2-5.md |

| Transform footage the user already has — preserve the subject + camera move, add the VFX element | templates/seedance/footage-vfx-transform.md |

| One style prefix shared by every shot in a sequence | templates/seedance/global-style-prefix.md |

| Show the model WHERE figures stand — a front-on outline position reference attached LAST (one incomplete-record run: no bleed, NOT reliable at moving blocking) | templates/seedance/staging-reference.md |

Text-overlay templates (templates/text-overlays/) — paste-ready text-rendering

prompts for slogan / subtitle / speech-bubble overlays:

| Text overlay type | Template |

|---|---|

| Slogan / brand callout / opening title | templates/text-overlays/slogan.md |

| Subtitle (dialogue-synchronized) | templates/text-overlays/subtitle.md |

| Speech bubble (character-attributed) | templates/text-overlays/speech-bubble.md |

---

Build the Prompt Using the MCSLA Formula

Full MCSLA definition and prompt structure → skills/higgsfield-prompt/SKILL.md

Quick summary — five layers, every prompt:

| M | C | S | L | A |

|---|---|---|---|---|

| Model | Camera | Subject | Look | Action |

Core rules:

• Be specific — name camera presets, describe VFX concretely
• Keep prompts under 200 words (short-form regime — block-scaffold production prompts follow their own structural rules, HARD RULE 8)
• Subject → Action → Camera → Style is the most reliable order

---

Output Format

Single prompt:

**Model**: [model name]
**Aspect ratio**: [ratio]  **Duration**: [Xs]  **Style**: [style]

[Prompt]

**Camera**: [camera control name]
**Motion preset** (if used): [preset name]

Two versions (when style varies):

### Version 1 — [Style Name]
[Prompt]

---
### Version 2 — [Style Name]
[Prompt]

Output rules:

• Output a clean, ready-to-paste prompt — no meta-commentary after
• Do not explain what every line does unless the user asks
• Always name the camera control and motion preset explicitly

---

Generation Ledger — log every result

Every generation attempt the user reports — kept, rejected, or filter-flagged —

gets one row in the ledger (ledger/<project>.json in the memory folder, § Working

Folders). The denominator (successes too,

not just failures) is what turns the memory system into takes-per-kept ratios

and credit budgets.

The 5-second rule: when the user reports a result, ask at most ONE

question ("keep or reject — what failed?") and write the row yourself with

one scripts/higgsfield_memory.py log-gen command (run it as `python3

<this skill's folder>/scripts/higgsfield_memory.py`; it finds the memory folder itself). Never ask

twice; never present a form. Every script this skill runs needs only python3 and its

standard library — no pip install. Full workflow: skills/higgsfield-recall/SKILL.md § Log the Generation

Result. Ratios and budgeting: skills/higgsfield-assist/SKILL.md.

---

@ Reference Rules

• User uploads a document (script, bible, brief, reference notes): read it from workspace/input/; if it landed elsewhere, copy it there first and leave the original in place (see Working Folders above)
• User uploads image: use [reference image] or describe it as "the provided reference"
• For Soul ID character: note "using Soul ID character reference" in the prompt
• For video extension: note "extend from [reference video], continue with..."
• For style transfer: note "match the visual style of [reference image]"

---

Shared Resources

| Resource | What it contains | When to use |

|----------|-----------------|-------------|

| INDEX.md | Generated heading index of every SKILL.md, each heading anchor-linked | To land on one section of a sub-skill instead of hunting for it |

| DISCIPLINE.md | Operating discipline patterns behind the HARD RULES (cites them by number, never restates them) | When unsure how a HARD RULE applies in practice |

| model-guide.md | Video + image model comparison tables, § Edit-Lane Chooser, § Long-Take Chooser | Any model choice |

| image-models.md | Image model specs, UI controls and pricing | Image model questions, specs or pricing |

| vocab.md | Camera movement + cinematic vocabulary, aspect ratio vs style register | Camera, lens and look wording |

| prompt-examples.md | Production prompt examples by genre | Before writing a prompt from scratch |

| photodump-presets.md | 29 Photodump style presets | Photodump / social-feed photo-dump requests |

| production-benchmarks.md | Production-cost and iteration anchors from a Higgsfield-made 90-minute AI feature | Credit budgets, realistic iteration counts, cost framing |

| docs/Seedance 2 Skill.md | The bilingual EN+ZH JSON Seedance output profile — not the canonical Seedance skill | Only when the user wants bilingual-JSON Seedance output |

| docs/field-test-queue.md | Models and doctrine claims this library states with no O-Side generation behind them yet | Before presenting one of them as tested |

| skills/shared/negative-constraints.md | All generation artifacts + prevention phrases, by category | Check before every prompt — append relevant constraints |

| skills/shared/provenance.md | Repo-wide provenance legend — what [OFFICIAL]/[DEMO]/[FIELD]/[EMPIRICAL]/[HOUSE]/[MEASURED] mean and the evidence each requires | Before leaning on a tagged claim |

| skills/shared/house-rulings.md | Every contested doctrine question — ruling or OPEN, scope, both sides | When two skill files seem to disagree |

| templates/ | 10 annotated genre templates with examples, models, annotations, variations | When user request matches a common genre — use as starting point |

| templates/ad-asset-prep.md | Ad asset preparation: product sheets, hero-character sheets, location plates — generate-many → test-in-motion → lock-the-winner | When an ad/product request needs reference assets built before video |

| templates/character-design/ | 6 character-design worksheets: templates/character-design/premise.md, templates/character-design/world-sheet.md, templates/character-design/9-question-character-sheet.md, templates/character-design/character-web.md, templates/character-design/story-spine.md, templates/character-design/style-sheet.md | With skills/higgsfield-character-design/SKILL.md when developing characters before prompting |

| templates/seedance/ | 10 Seedance technique templates, each listed by path in § Check Templates for Genre Match | When Seedance request is technique-shaped (spatial blocking, position references, multi-character anchoring, anime/stylized-2D, FACS acting, footage VFX, style prefix, 2.5 multi-reference) |

| templates/text-overlays/ | 3 text-rendering templates: slogan, subtitle, speech-bubble | When user request includes on-screen text rendering |

Reference files inside sub-skills

Open these directly when the row applies — alongside their sub-skill, not instead of it.

| File | What it holds | Open when |

|------|---------------|-----------|

| skills/higgsfield-seedance/ENGINE-RULES.md | Seedance 2.0's hard rendering constraints — the shared core every Seedance dialect cites | Any Seedance 2.0 prompt |

| skills/higgsfield-seedance/FAILURE-MODES.md | Catalog of Seedance 2.0 / Pro failure modes and their fixes | A Seedance take came back wrong |

| skills/higgsfield-seedance/HELL-GRIND.md | Higgsfield's open-sourced feature-film pipeline on Seedance | Feature-length or multi-scene Seedance production |

| skills/higgsfield-seedance/PRODUCTION-PATTERNS.md | Tutorial-demonstrated and field-harvested Seedance production patterns | Seedance production work beyond a single prompt |

| skills/higgsfield-seedance-2-5/MODE-PLAYBOOKS.md | Long-form templates for each Seedance 2.5 mode and technique | Writing a 2.5 prompt in a named mode |

| skills/higgsfield-seedance-2-5/VFX-PIPELINE.md | The AI-VFX pipeline: how a whole VFX shot gets built | Replacing a VFX/3D pipeline with generation |

| skills/higgsfield-seedance-vfx/references/first-frame.md | Lock an uncertain look as a still first, then animate from it | A footage transform whose look is untested |

| skills/higgsfield-seedance-vfx/references/dialogue-timing.md | Anchoring a timed camera move to a line and to a second mark | A crash zoom, push-in or reveal that must land on a beat |

| skills/higgsfield-models/MODELS-DEEP-REFERENCE.md | Long-form per-model reference behind the model sub-skill | The sub-skill's summary is not enough for the call |

| skills/higgsfield-cinema/references/output-formats-2-5-3-0.md | Per-mode output templates for Cinema Studio 2.5 + 3.0 | Formatting a Cinema Studio 2.5 / 3.0 delivery |

| skills/higgsfield-cinema/references/reference-sheet-types.md | Motion/camera, outfit/material, palette/mood and product reference sheets | A reference sheet that is not a character or location |

| skills/higgsfield-gpt-image-2/reference-sheet-workflow.md | Automatic Product Reference Sheet: one product image → a multi-view studio sheet | Product reference sheets |

| skills/higgsfield-gpt-image-2/static-ads-workflow.md | Recreating an uploaded ad with GPT Image 2.0 | Static-ad recreation |

| skills/higgsfield-marketing-studio/cross-surface-workflow.md | Four-surface ad recipe (GPT Image 2.0 → Soul Cinema → Nano Banana Pro → Marketing Studio) and ms_image / DTC Ads | A campaign built across image and video surfaces |

| skills/higgsfield-content-factory/publish-and-report-workflow.md | Campaign Stage 4 (Meta Ads publish or content calendar) and Stage 5 (cost-comparison report) | Publishing or reporting a campaign |

---

Sub-Skills — open skills/<name>/SKILL.md yourself

These are plain files, not separately registered skills, so none of them loads on its own.

Open the file in the Skill column with the read tool (paths are relative to this folder).

| Skill | Trigger |

|-------|---------|

| skills/higgsfield-workspaces/SKILL.md | User is choosing a workspace / asking "what should I use for X" / hasn't picked a tool yet |

| skills/higgsfield-prompt/SKILL.md | Any prompt writing or refinement request |

| skills/higgsfield-image-shots/SKILL.md | Cinematic image prompts — shot framing, angles, composition |

| skills/higgsfield-gpt-image-2/SKILL.md | GPT Image 2.0 / 2.5 prompts — when to prefer 2.5 (transparent background, xhigh/max), three-format taxonomy (JSON / prose / meta-prompt), UI mockups, infographics, reference sheets, static-ad recreation |

| skills/higgsfield-models/SKILL.md | "Which model should I use?" / model comparison / edit-lane, long-take (>15s) and motion-transfer choosers |

| skills/higgsfield-camera/SKILL.md | Camera movement questions (video) |

| skills/higgsfield-motion/SKILL.md | Named preset requests (Explosion, Werewolf, VFX, etc.) |

| skills/higgsfield-style/SKILL.md | Visual style / aesthetic questions |

| skills/higgsfield-soul/SKILL.md | Character consistency / Soul ID |

| skills/higgsfield-character-design/SKILL.md | Pre-production story bible — premise / world / 9-question character / story spine / visual DNA (before prompting) |

| skills/higgsfield-scene-engine/SKILL.md | Scene/sequence structural audit — Goal / Obstacle / Tactic / Reversal / Value Shift (before spending credits) |

| skills/higgsfield-apps/SKILL.md | One-click app recommendations |

| skills/higgsfield-recipes/SKILL.md | Genre scene templates |

| skills/higgsfield-troubleshoot/SKILL.md | Failed generations / quality issues |

| skills/higgsfield-moodboard/SKILL.md | Moodboard / Soul Hex / project-level style consistency |

| skills/higgsfield-mixed-media/SKILL.md | Artistic preset overlays (Noir, Sketch, Particles, etc.) |

| skills/higgsfield-assist/SKILL.md | Higgsfield Assist copilot / credit optimization / plan selection |

| skills/higgsfield-cinema/SKILL.md | Cinema Studio 2.5 + 3.0 + 3.5 / Soul Cast / color grading / optical physics / multi-shot / Elements / Smart mode / @ references / Style Settings / Camera Settings / Manual Style |

| skills/higgsfield-marketing-studio/SKILL.md | Marketing Studio / DTC Ads / ad video / UGC video / Hyper Motion / TV Spot / Wild Card / Pro Virtual Try On / hook + setting picklists / 4–15s ad video / marketing_studio_video MCP / cross-surface workflow |

| skills/higgsfield-content-factory/SKILL.md | Campaign pipeline (research → plan → generate → publish → report) / UGC-first 5-format mix / batch generation gate / Meta Ads scheduling / cost-savings report |

| skills/higgsfield-canvas/SKILL.md | Node-based Canvas workspace / infinite board / chain prompts→images→videos / named canvas patterns / build-free generate-paid cost model / Shared Canvas live collaboration |

| skills/higgsfield-pipeline/SKILL.md | Multi-shot workflow / tool chaining / full production pipeline |

| skills/higgsfield-vibe-motion/SKILL.md | Vibe Motion — motion graphics / kinetic typography / brand + logo animation as Remotion code (crisp text, exact colors, deployable) |

| skills/higgsfield-motion-design/SKILL.md | Animated-ad flow brief → storyboard → Seedance video (AI pixel render, not code; classicMD/highMD) |

| skills/higgsfield-recall/SKILL.md | Pre-generation memory check / apply past failure fixes |

| skills/higgsfield-audio/SKILL.md | Audio design, dialogue, SFX, ambient sound for audio-capable models |

| skills/higgsfield-seedance/SKILL.md | Seedance 2.0 / Pro prompt director + content-filter preflight linter (+ skills/higgsfield-seedance/HELL-GRIND.md, Higgsfield's open-sourced feature-film pipeline) |

| skills/higgsfield-seedance-2-5/SKILL.md | Seedance 2.5 omni-reference dialect — the four modes (t2v / omni_reference / video_edit / video_extension), reference-role grammar, 30s staging, editing + forward/backward extension, keyframes, storyboards, blockouts, transitions (+ skills/higgsfield-seedance-2-5/VFX-PIPELINE.md, the AI-VFX production pipeline: asset-class model routing, size-ref frame, the omni_reference v2v lane, the four-batch rule, the slop catalog) |

| skills/higgsfield-seedance-vfx/SKILL.md | Video-to-video footage transformation for Seedance 2.0 — preserve a real subject + camera move, add a VFX element / swap the environment / drop a photoreal creature / relight to match / sync a timed zoom, run in std 4K |

| skills/higgsfield-acting/SKILL.md | Character performance as behavior under pressure — objective / obstacle / tactics / beats / subtext, body + status + proxemics, mandatory eye life, the 150–220-word acting master profile and its per-scene rewrite, locked voice prompt |

| skills/higgsfield-shotlist-director/SKILL.md | Brief/script → one connected Seedance shotlist (style prefix + @-glossary + named per-scene prompts) as editable HTML |

| skills/higgsfield-facs/SKILL.md | FACS Action Unit codes for precise facial expressions in Seedance 2.0 — forced/uncanny/mixed expressions, close-up dialogue facial acting, emotion→AU recipes, FACS reference sheets |

| skills/higgsfield-stack/SKILL.md | User mentions the Higgsfield CLI / MCP connector / bundled skills, or asks how this skill coexists with those execution surfaces |

| skills/higgsfield-3d/SKILL.md | 3D meshes (image / multi-view / text → GLB), rigging + animation, remesh / retexture, 3D Body, 3D Jutsu scene projects, 3D turnarounds and 3D staging blockouts |

| skills/higgsfield-repurpose/SKILL.md | Finished video in: Shorts Studio, Clipify, Virality Predictor, Video Analysis — with the paid / free split |

> Full vocabulary in vocab.md

> Full motion preset library in skills/higgsfield-motion/SKILL.md

> Model comparison in model-guide.md

> Example prompts in prompt-examples.md

> Shared negative constraints in skills/shared/negative-constraints.md

> Genre-specific annotated templates in templates/