higgsfield
Writes and refines prompts for Higgsfield AI's video and image models, and picks the model, camera controls and motion presets for each shot. Use 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 Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema Studio 2.5/3.0, Vibe Motion, troubleshooting failed generations, credit optimization, Photodump, or any mention of higgsfield.ai. Also trigger on generic "write me a video prompt" or "make me an AI video prompt" requests when Higgsfield is the user's configured platform.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/osidemedia/higgsfield-ai-prompt-skill with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/osidemedia/higgsfield-ai-prompt-skill'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/osidemedia--higgsfield-ai-prompt-skill)HTML
<a href="/listings/osidemedia--higgsfield-ai-prompt-skill"><img src="/api/listings/osidemedia--higgsfield-ai-prompt-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Claude Code
git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield
Claude Code registers the root `SKILL.md` as one skill, `higgsfield`. The 35 sub-skills under `skills/` are not registered separately; the root routes to each by its full path and Claude opens it from there. The skill's scripts need only `python3` (standard library).
Your documents and the skill's deliverables go in a `workspace/` folder (`input/`, `output/`, `processed/`) inside the project you are working in, created on first use. Your documents and deliverables are never written into `~/.claude/skills/higgsfield/`, so updating or reinstalling the skill never touches them. The learning memory and generation ledger live in `~/.higgsfield-skill/db/`, outside the skill folder, so an update or reinstall keeps them too. The skill creates that folder on first use from its own `db/`, which also carries over the memory from an install older than v3.42.0. If you had two older installs (say a personal one and one inside a project), the second one's own entries are kept in `~/.higgsfield-skill/unmerged/`, not merged into the first; `where` lists them. In Cowork, or when you run the skill from a clone of this repo, the memory stays in the skill's own `db/`. To see which folder is in use, run `python3 scripts/higgsfield_memory.py where` from the skill's folder.
Claude Cowork
Drop the repo folder into your Cowork workspace. The skill dispatcher is at `SKILL.md` in the repo root.
Claude.ai Projects
Upload `SKILL.md` (root) as your project instruction base. Upload files from `skills/` as project documents.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 500 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- ---
- name: higgsfield
- description: >
- Writes and refines prompts for Higgsfield AI's video and image models, and picks the
- model, camera controls and motion presets for each shot. Use 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 Banana, Seedream, Flux, GPT Image, etc.), camera
- controls, named motion presets, Soul ID character consistency, Cinema Studio 2.5/3.0,
- Vibe Motion, troubleshooting failed generations, credit optimization, Photodump,
- or any mention of higgsfield.ai. Also trigger on generic "write me a video prompt"
- or "make me an AI video prompt" requests when Higgsfield is the user's configured
- platform.
- user-invocable: true
- metadata:
- tags: [higgsfield, video, image, prompt, cinematic, AI, filmmaking, motion, camera]
- version: 3.42.0
- updated: 2026-10-23
- author: O-Side Media
- license: MIT
- ---
- # Higgsfield AI Prompt Skill
- <!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
- **Contents**
- - [HARD RULES — pre-delivery checklist](#hard-rules--pre-delivery-checklist)
- - [What Is Higgsfield?](#what-is-higgsfield)
- - [Working Folders — file handling](#working-folders--file-handling)
- - [Handling a Request](#handling-a-request)
- - [Fast Path — Simple Creative Requests](#fast-path--simple-creative-requests)
- - [Full Path — Production Requests](#full-path--production-requests)
- - [Route to the Right Skill](#route-to-the-right-skill)
- - [Load Map — how much to read](#load-map--how-much-to-read)
- - [Check Templates for Genre Match](#check-templates-for-genre-match)
- - [Build the Prompt Using the MCSLA Formula](#build-the-prompt-using-the-mcsla-formula)
- - [Output Format](#output-format)
- - [Generation Ledger — log every result](#generation-ledger--log-every-result)
- - [@ Reference Rules](#-reference-rules)
- - [Shared Resources](#shared-resources)
- - [Reference files inside sub-skills](#reference-files-inside-sub-skills)
- - [Sub-Skills — open `skills/<name>/SKILL.md` yourself](#sub-skills--open-skillsnameskillmd-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/`
README.md · README · 378 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- [](https://github.com/OSideMedia/higgsfield-ai-prompt-skill)
- [](specs/MODEL-SPECS.md)
- [](LICENSE)
- [](https://github.com/OSideMedia/higgsfield-ai-prompt-skill)
- # Higgsfield AI Prompt Skill
- > **⚠️ No longer maintained (archived November 2026).** Our work has moved to a different AI
- > filmmaking tool, so this skill gets no further updates, fixes or model refreshes. v3.42.0 is
- > the final release. Its model specs are a snapshot from 2026-09-26 and will fall behind the
- > Higgsfield platform as models change. The repo is archived and kept for reference: issues and
- > pull requests are closed. It is MIT-licensed, so you are welcome to fork it and carry it on.
- A comprehensive Claude skill library for generating high-quality prompts on
- [Higgsfield AI](https://higgsfield.ai) — the cinematic video and image generation platform.
- ## What This Skill Does
- Transforms natural language requests into production-ready Higgsfield prompts using:
- - The **MCSLA formula** (Model · Camera · Subject · Look · Action)
- - Named camera controls and motion presets the platform recognizes
- - Model selection guidance across Kling 3.0 / 3.0 Omni / 3.0 Motion Control, Veo 3.1, Wan, Seedance 2.5 / 2.0, FLUX 3 Video, Minimax Hailuo, Higgsfield DoP, and more
- - Genre recipe templates for action, horror, romance, sci-fi, product ads, and more
- - Soul ID character consistency guidance + Character Sheet creation
- - Troubleshooting for failed or poor generations
- - **Cinema Studio 2.5** advanced features: Soul Cast AI actors, built-in color grading, 3D Mode (Gaussian Splatting), Grid Generation, Resolution Settings, Frame Extraction Loop, Object & Person Insertion, Per-Character Emotions, Clustering, Five-View Location Reference Sheet, Reference Sheet Types (Motion / Outfit / Palette), Elements System with library surface (5 source tabs × 6 element categories)
- - **Cinema Studio 3.0** (Business/Team plan): native dual-channel stereo audio, Smart shot control, 15s max duration, 7 genres, @ reference patterns, Soul Cast 3.0
- - **Cinema Studio 4.0** (`cinematic_studio_video_4_0`, CLI workflow): the Seedance 2.5 four-mode surface (t2v / omni_reference / video_edit / video_extension) plus camera body / lens / aperture / era / genre / pacing and light / palette controls — schema-documented, not yet field-rated
- - **3D** (`higgsfield-3d`): image / multi-view / text → GLB meshes, rigging + a 678-clip animation library, remesh / retexture, 3D Jutsu scene projects, 3D turnarounds and staging blockouts
- - **Repurposing** (`higgsfield-repurpose`): Shorts Studio, Clipify, Virality Predictor, Video Analysis — with the paid / free split
- - **Cinema Studio 3.5**: three-pill main UI (Genre / Style / Camera), Style Settings panel (8 Color Palette / 6 Lighting / 9 Camera Moveset Style + Manual Style mode), Camera Settings four-axis panel (3 Camera Body / 5 Lens / 5 Focal Length including new 75mm / 3 Aperture), Image Mode with four Cinematic models picker (Soul Cinema default, Cinematic Characters, Cinematic Locations, Cinematic Cameras with 2.5 vocabulary)
- - **Seedance 2.0 prompting best practices** — Intent over Precision, Genre Router, I2V Gate, Anti-Slop, Physics Language, SCELA audio, Reference-Based / Continuation / Expand Shot / Edit Shot / Transformation prompt modes, Continuation Prompt Formula, the Iteration Rule
- - **Seedance 2.5 omni-reference director** — the four generation modes (`t2v` / `omni_reference` / `video_edit` / `video_extension`), explicit `@Image` / `@Video` / `@Audio` reference roles with exclusions, the five-step multi-reference workflow, 30-second staging with end states, timestamp pacing, bracket syntax for music / SFX / dialogue / subtitles, first-last-frame control (platform `start_image`/`end_image` in `omni_reference`, or declared in-prompt) and multi-keyframe control, storyboard grids, coarse-vs-fine blockout rendering, one-click video, seamless transitions, and a 2.0-vs-2.5 routing table
- - **Hell Grind feature-film pipeline** — Higgsfield's open-sourced 95-minute-feature system: headless character sheets, mask-composited point edits, location sheets with anchors and one light logic, the per-scene GEO SPATIAL LAYOUT block, the position-fixing first second, dialogue construction, the ban dictionary, the 10–15 iteration rule, and the crowd / giant / threshold solutions
- - **AI-VFX pipeline** — the production layer under Seedance 2.5, from Higgsfield's AI-vs-VFX challenge build: model routing per asset class (faces / creatures / clothing / locations), the plain-grey sheet law, two-close-up creature sheets, the face-lock crop, the size-ref frame for scale between two subjects, location batching selected on light, the `omni_reference` video-to-video lane (source ≥4s, duration = source) with its performance-inheritance clause, the four-batch stop rule and the i2v fallback with a deliberate empty-frame stitch point, and a slop catalog of the tells that give a shot away
- - **Acting director** — performance as behavior under pressure: objective / obstacle / tactics / beats / subtext, listening markers, body + status + proxemics, mandatory eye life, the 150–220-word acting master profile and its per-scene rewrite, the locked voice prompt, a 15-symptom atlas of bad acting, and a 0–5 performance scale
- - **GPT Image 2.0 prompt director** — three-format taxonomy (structured JSON for UI mockups / infographics / reference sheets, dense cinematic prose for single-subject scenes, auto-derive meta-prompt for theme-only concepts) plus reference-sheet and static-ad-recreation workflow satellites
- - **Higgsfield Canvas** — node-based / infinite-board workspace guidance: chaining prompts → images → videos, named canvas patterns, Shared Canvas live collaboration, build-free / generate-paid cost model
- - **Marketing Studio + Content Factory** — 9 DTC ad presets (UGC / Tutorial / Unboxing / Hyper Motion / TV Spot / Wild Card / Virtual Try-On) with 4–15s ad video, plus an end-to-end campaign pipeline (research → plan → generate → publish → report) with a cost-savings report
- - **Shared negative constraints reference** — categorized artifacts + prevention phrases (positive alternatives for 3.0); Kling 3.0 Motion Control failure diagnostic; Physics Rendering — Resolution Decision Matrix (cross-model 480p / 720p / 1080p routing rule for Seedance 2.0 + Cinema Studio 3.x)
- - **Identity vs. Motion separation** — hard rule for character consistency across shots
- - **Annotated templates library** — 10 genre templates with Cinema Studio 3.0 genre mappings, plus Seedance technique + character-design + text-overlay sub-libraries (19 files across 3 categories)
- - **DISCIPLINE.md cross-cutting framework** — 9 named discipline patterns in 3-3-3 tier symmetry (prompt-construction, model-selection, iteration-discipline) governing decisions across all sub-skills
- - **production-benchmarks.md** — Hell Grind 90-min Cannes feature reference, per-character iteration anchors, acceptance-rate calibration; what "production quality" means in practice
- - **FAILURE-MODES.md (Seedance)** — 15 named render failures documented with symptom + mechanism + counter for diagnosis-first iteration
- - **C-arc Building Complete AI Projects — 10-Step Methodology** — end-to-end pipeline from idea to delivered project; complements the genre/scene templates
- - **Expanded Seedance methodology + Soul refinement** — Iteration Rule + 6-Pass Diagnostic Sequence + Four Questions + Next-Shot Decision Tree + Bridging / Continuation / Repair working modes; Character Anchor Block + Two-Tool Refinement Pipeline for character consistency at production scale
- ## Install
- ### Claude Code
- ```bash
- git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield
- ```
- Claude Code registers the root `SKILL.md` as one skill, `higgsfield`. The 35 sub-skills under `skills/` are not registered separately; the root routes to each by its full path and Claude opens it from there. The skill's scripts need only `python3` (standard library).
- Your documents and the skill's deliverables go in a `workspace/` folder (`input/`, `output/`, `processed/`) inside the project you are working in, created on first use. Your documents and deliverables are never written into `~/.claude/skills/higgsfield/`, so updating or reinstalling the skill never touches them. The learning memory and generation ledger live in `~/.higgsfield-skill/db/`, outside the skill folder, so an update or reinstall keeps them too. The skill creates that folder on first use from its own `db/`, which also carries over the memory from an install older than v3.42.0. If you had two older installs (say a personal one and one inside a project), the second one's own entries are kept in `~/.higgsfield-skill/unmerged/`, not merged into the first; `where` lists them. In Cowork, or when you run the skill from a clone of this repo, the memory stays in the skill's own `db/`. To see which folder is in use, run `python3 scripts/higgsfield_memory.py where` from the skill's folder.
- ### Claude Cowork
- Drop the repo folder into your Cowork workspace. The skill dispatcher is at `SKILL.md` in the repo root.
- ### Claude.ai Projects
- Upload `SKILL.md` (root) as your project instruction base. Upload files from `skills/` as project documents.
- ## Higgsfield Stack Integration
- This skill is the prompt-construction layer. Higgsfield ships official execution tooling — a CLI, an MCP custom connector, and a bundled skills package. They complement each other: this skill produces the prompt, their tooling executes it. None of their tooling is required for this skill to work — you can always paste prompts directly into higgsfield.ai. But if you want an end-to-end loop, you'll want one of the three.
- **A Higgsfield account is required** for any of the tooling below. Sign up at [higgsfield.ai](https://higgsfield.ai).
- ### Higgsfield CLI
- Command-line tool for terminal-native agents (Claude Code, Codex, Cursor). Per Higgsfield's own guidance, prefer the CLI over the MCP if you're working in a terminal.
- - Repo: [github.com/higgsfield-ai/cli](https://github.com/higgsfield-ai/cli)
- - Install: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh` or `brew install higgsfield-ai/tap/higgsfield`
- - Auth: `higgsfield auth login`
- ### Higgsfield MCP
- Custom connector for claude.ai web and the Claude desktop app. Separate product from the CLI.
- - Connector URL: `https://mcp.higgsfield.ai/mcp`
- - Install: claude.ai → Settings → Connectors → Add custom connector → paste the URL above → sign in
- ### Higgsfield Bundled Skills
- Markdown skill bundle for agents that consume Cowork-style skills. All three skills drive the CLI under the hood.
- - Repo: [github.com/higgsfield-ai/skills](https://github.com/higgsfield-ai/skills)
- - Install: `npx skills add higgsfield-ai/skills`
- - Skills included: `higgsfield-generate`, `higgsfield-soul`, `higgsfield-product-photoshoot`
- - Invoke: `/higgsfield:generate`, `/higgsfield:soul`, `/higgsfield:product-photoshoot`
- ### End-to-end example
- How the layers fit together for a real request:
- ```
- USER: "Make me a cinematic chase scene through a night market.
- Use my trained Soul character — reference_id abc123."
- ↓
- THIS SKILL — higgsfield-ai-prompt-skill
- • routes to higgsfield-prompt + higgsfield-camera + higgsfield-soul
- • picks Kling 3.0 (character-focused, supports --soul-id)
- • applies MCSLA: model, camera preset, subject, look, action
- • appends shared negative constraints
- • outputs a production-grade Higgsfield prompt
- ↓
- PRE-FLIGHT (optional, recommended for Veo / Kling / Seedance video):
- SCHEMA VERIFY (recommended for any model you haven't called recently):
- CLI path: higgsfield model get kling3_0
- → returns schema: aspect_ratio enum, duration range,
- mode/sound options, media roles
- MCP path: models_explore(action="get", model_id="kling3_0")
- → returns same schema as CLI
- COST ESTIMATE (no job submitted):
- MCP path: generate_video(..., get_cost: true)
- → returns credit cost + adjustments block
- CLI path: higgsfield generate cost kling3_0 \
- --prompt "<prompt from this skill>" \
- --aspect_ratio 16:9 \
- --duration 8
- # (add reference flags as needed: --soul-id, --start-image,
- # --end-image — consult `higgsfield model get kling3_0`
- # for supported media roles)
- Bundled skills: drop to CLI for the cost check (same auth, same workspace),
- then invoke /higgsfield:generate
- Optional account checks (same data across surfaces):
- MCP path: balance / transactions tools
- CLI path: higgsfield account status
- higgsfield account transactions --size 50
- Note: 2.35:1 is anamorphic STYLE vocabulary, not a valid Kling 3.0 output
- ratio. Output ratios are platform-bounded: 16:9 / 9:16 / 1:1 only.
- ↓
- HIGGSFIELD STACK — one of three execution surfaces:
- CLI path:
- higgsfield generate create kling3_0 \
- --prompt "<prompt from this skill>" \
- --aspect_ratio 16:9 \
- --duration 8 \
- --wait
- # (add reference flags as needed: --soul-id, --start-image, --end-image —
- # consult `higgsfield model get kling3_0` for supported media roles)
- Bundled skills path:
- /higgsfield:generate — takes the prompt as its --prompt argument,
- formats the CLI call above under the hood
- MCP path (claude.ai web/desktop):
- Claude invokes the Higgsfield connector with the prompt as input
- ↓
- USER: Result URL returned. Iterate if needed (this skill's
- iteration discipline applies regardless of execution surface).
- ```
- The layer split holds in every case: this skill always produces the prompt, the Higgsfield stack always handles the generation call. None of the three execution paths reach back into prompt construction; this skill never shells out to their CLI or API.
- > Full preflight discipline — when to surface it, marketing-studio caveat, CLI naming gotchas (`account status`, not `balance`), and the plan-tier-vs-surface framing — lives in [`skills/higgsfield-stack/SKILL.md`](skills/higgsfield-stack/SKILL.md) § Preflight discipline.
- ### Coexistence rules
- For the full coexistence rules, detection signals, naming-collision callouts, and handoff templates, see [`skills/higgsfield-stack/SKILL.md`](skills/higgsfield-stack/SKILL.md).
- ## Structure
- ```
- .
- ├── SKILL.md ← Main dispatcher (routes to sub-skills — start here)
- ├── README.md ← This file
- ├── CHANGELOG.md ← Version history
- ├── CONTRIBUTING.md ← Contribution guidelines
- ├── LICENSE ← MIT license
- ├── CLAUDE.md ← Project instructions for Claude Code
- ├── .markdownlint.json ← Linter config (CHANGELOG convention silencing — v3.6.1)
- ├── model-guide.md ← Model comparison tables + decision flowchart
- ├── image-models.md ← Image model reference + pricing tiers
- ├── vocab.md ← Full platform vocabulary reference
- ├── prompt-examples.md ← High-quality example prompts + Before/After pairs
- ├── photodump-presets.md ← Photodump mode presets
- ├── DISCIPLINE.md ← Cross-cutting discipline framework (9 patterns, 3-3-3 tier symmetry)
- ├── production-benchmarks.md ← Production-quality anchors + acceptance-rate calibration
- ├── scripts/ ← Python tooling (run from the repo root)
- │ ├── higgsfield_memory.py ← Memory system script
- │ ├── seedance_lint.py ← Seedance preflight linter
- │ ├── validate.py ← Pre-release validation script
- │ ├── build_index.py ← Regenerates INDEX.md + checks QUICK FACTS anchors
- │ ├── sync_specs.py ← Regenerates specs/ from a models_explore snapshot
- │ ├── refresh_specs.py ← Spec-drift tripwire (live CLI vs baseline; params, ranges, media roles)
- │ ├── snapshot_crosscheck.py ← Two-way structural check: models_explore snapshot vs live CLI
- │ ├── preflight.py ← Free any-model platform-constraint preflight (enums + CEL rules, fails closed)
- │ ├── claims_lint.py ← Doctrine claims vs today's specs (registry: evals/spec-claims.json)
- │ ├── repo_walk.py ← Repo file walks that skip agent worktrees
- │ ├── user_guide_content.py ← USER-GUIDE content derived from disk (dependency-free)
- │ ├── generate_user_guide.py ← USER-GUIDE.pdf generator (Path B refactor — v3.7.0)
- │ ├── validate_user_guide.py ← USER-GUIDE.pdf drift validator (text-extract + binary diff)
- │ └── sub_skill_descriptions.py ← Canonical sub-skill roster (shared data module)
- ├── db/
- │ ├── filter-memory.json ← Content filter memory (seeded)
- │ └── quality-memory.json ← Quality failure memory (seeded)
- ├── docs/ ← Extended reference documents
- │ ├── Seedance 2 Skill.md ← Bilingual EN+ZH Seedance director reference
- │ ├── archive/ ← Historical records
- │ │ ├── HISTORY.md ← Consolidated v3.0.0–v3.6.0 audit + inventory snapshots
- │ │ └── AUDIT-2026-06-03.md ← Full repo audit (security, bugs, docs hygiene)
- │ └── user-guide/ ← Exported USER-GUIDE.pdf + current-version baseline (rotate, not accumulate)
- ├── templates/ ← Genre templates + Seedance coordination + text-overlays
- │ ├── 01-cinematic-action-chase.md
- │ ├── 02-product-ugc-showcase.md
- │ ├── 03-horror-atmosphere.md
- │ ├── 04-fashion-editorial.md
- │ ├── 05-sci-fi-vfx.md
- │ ├── 06-portrait-character-intro.md
- │ ├── 07-landscape-establishing-shot.md
- │ ├── 08-comedy-social-media.md
- │ ├── 09-romantic-intimate.md
- │ ├── 10-dance-music-performance.md
- │ ├── seedance/ ← Seedance technique templates (10)
- │ │ ├── multi-character-anchor.md
- │ │ ├── single-character-position.md
- │ │ ├── top-down-map.md
- │ │ ├── omni-reference-2-5.md ← Seedance 2.5 multi-reference brief
- │ │ └── worked-example-two-character.md
- │ └── text-overlays/ ← Text overlay templates
- │ ├── slogan.md
- │ ├── speech-bubble.md
- │ └── subtitle.md
- └── skills/
- ├── shared/
- │ └── negative-constraints.md ← Shared artifact prevention reference
- ├── higgsfield-prompt/SKILL.md ← Core MCSLA formula + prompt structure + Identity/Motion separation
- ├── higgsfield-image-shots/SKILL.md ← Cinematic image prompting (shots, angles, composition)
- ├── higgsfield-gpt-image-2/
- │ ├── SKILL.md ← GPT Image 2.0 director (JSON / prose / meta-prompt taxonomy)
- │ ├── reference-sheet-workflow.md ← Automatic product reference-sheet workflow
- │ └── static-ads-workflow.md ← Static-ad recreation workflow
- ├── higgsfield-models/
- │ ├── SKILL.md ← Compact model selection guide
- │ └── MODELS-DEEP-REFERENCE.md ← Full per-model documentation (on-demand)
- ├── higgsfield-camera/SKILL.md ← All camera controls + usage
- ├── higgsfield-motion/SKILL.md ← Named motion presets library
- ├── higgsfield-style/SKILL.md ← Visual styles + color grades + lighting
- ├── higgsfield-soul/SKILL.md ← Soul ID character consistency
- ├── higgsfield-audio/SKILL.md ← Audio prompting + Cinema Studio 3.0 native audio
- ├── higgsfield-apps/SKILL.md ← One-click Apps guide
- ├── higgsfield-recipes/SKILL.md ← Genre scene templates
- ├── higgsfield-troubleshoot/SKILL.md ← Fix failing generations
- ├── higgsfield-assist/SKILL.md ← General assistant + platform guidance
- ├── higgsfield-mixed-media/SKILL.md ← Mixed media + hybrid generation
- ├── higgsfield-moodboard/SKILL.md ← Moodboard creation workflows
- ├── higgsfield-pipeline/SKILL.md ← Multi-step generation pipelines
- ├── higgsfield-canvas/SKILL.md ← Node-based Canvas workspace + named patterns + Shared Canvas
- ├── higgsfield-content-factory/
- │ ├── SKILL.md ← Campaign pipeline (research → plan → generate → publish → report)
- │ └── publish-and-report-workflow.md ← Publish + cost-savings report satellite
- ├── higgsfield-marketing-studio/
- │ ├── SKILL.md ← Marketing Studio: 9 ad presets + 4–15s ad video
- │ └── cross-surface-workflow.md ← ms_image / DTC Ads cross-surface workflow
- ├── higgsfield-recall/SKILL.md ← Recall + regeneration patterns
- ├── higgsfield-3d/SKILL.md ← 3D meshes (image / multi-view / text → GLB), rigging, 3D Jutsu scenes
- ├── higgsfield-repurpose/SKILL.md ← Finished video in: Shorts Studio, Clipify, Virality Predictor, Video Analysis
- ├── higgsfield-cinema/SKILL.md ← Cinema Studio 2.5 + 3.0 + 3.5 + 4.0 (Soul Cast, Color Grading, 3D Mode, Smart Mode, @ References, Native Audio, three-pill UI, Image Mode, Cinematic models picker)
- ├── higgsfield-seedance/
- │ ├── SKILL.md ← Seedance 2.0 prompt director + content-filter preflight
- │ ├── ENGINE-RULES.md ← Hard rendering constraints shared across the Seedance family
- │ ├── PRODUCTION-PATTERNS.md ← Tutorial-demonstrated production patterns
- │ ├── HELL-GRIND.md ← Higgsfield's open-sourced 95-min feature pipeline
- │ └── FAILURE-MODES.md ← 15 named Seedance render failures (symptom · mechanism · counter)
- ├── higgsfield-seedance-2-5/
- │ ├── SKILL.md ← Seedance 2.5 omni-reference dialect + 4-mode router
- │ ├── MODE-PLAYBOOKS.md ← Edit / extend / storyboard / blockout / one-click / transitions
- │ └── VFX-PIPELINE.md ← AI-VFX pipeline: asset routing, size-ref frame, omni_reference v2v, slop catalog
- ├── higgsfield-acting/SKILL.md ← Performance craft: objective, beats, eye life, master profile
- ├── higgsfield-scene-engine/SKILL.md ← Structural scene audit: goal · obstacle · tactic · reversal · value shift
- ├── higgsfield-vibe-motion/SKILL.md ← Vibe-based motion direction
- └── higgsfield-workspaces/SKILL.md ← Workspace-first decision layer (Cinema Studio / Lipsync / Draw-to-Video / Viral Hub presets / Click to Ad / Higgsfield Audio)
- ```
- ## Generation Ledger
- Every generation attempt — kept, rejected, or filter-flagged — gets one row in
- `ledger/<project>.json` in the memory folder, logged by the agent in ≤5 seconds (one question,
- one command — never a form). After ~30–40 rows a production has empirical
- takes-per-kept ratios per shot type instead of vibes:
- ```bash
- python3 scripts/higgsfield_memory.py log-gen adze --model seedance_2_0 \
- --tags dialogue-cu,two-char --outcome rejected --reason extra-cuts
- python3 scripts/higgsfield_memory.py ratio adze --credits # hit rates + money view
- python3 scripts/higgsfield_memory.py budget adze --shots plan.json # price before burning
- ```
- Tags and reject reasons come from controlled vocabularies (`db/ledger/README.md`);
- rows are append-only with superseding corrections; `ratio` splits structural vs
- stochastic rejections and flags `low-n` rows instead of faking precision.
- ## Maintenance — two activation steps
- Two capabilities ship **inactive on purpose** and need a one-time setup.
- ### 1. Activate the scheduled spec-drift check
- `.github/workflows/spec-drift.yml` runs `scripts/refresh_specs.py` weekly to catch when
- Higgsfield changes a model's lineup or capabilities before the 30-day staleness
- warning would. It ships **dormant** until you give it the Higgsfield CLI
- credentials as a repo secret:
- ```bash
- higgsfield auth login # if not already authenticated locally
- gh secret set HIGGSFIELD_CREDENTIALS < ~/.config/higgsfield/credentials.json
- ```
- Then run it once manually (Actions tab → **spec-drift** → *Run workflow*) to
- confirm the CLI-install step resolves on the runner. After that it's automatic:
- **fresh** → nothing; **drift** → it opens/updates a GitHub issue with next steps;
- **auth expired** → the job fails so GitHub notifies you to re-run
- `higgsfield auth login` and refresh the secret. The credentials live only in the
- GitHub secret — they are never committed.
- ### 2. Let routing telemetry accumulate before pruning
- `log-route` / `routing` (in `scripts/higgsfield_memory.py`) record which sub-skills each
- request opens, so "which skills are load-bearing, which to retire" becomes a
- data question:
- ```bash
- python3 scripts/higgsfield_memory.py log-route --skills higgsfield-prompt,higgsfield-camera
- python3 scripts/higgsfield_memory.py routing # ranks opens, lists the never-opened tail
- ```
- This is **instrumentation, not a verdict** — let real requests accumulate before
- acting on the tail. A small sample is not evidence a skill is dead.
- ## Example Prompts
- **Basic:**
- > "Write me a Higgsfield prompt for a cinematic action chase through a night market"
- **Specific:**
- > "I need a horror prompt using VHS style, Dutch angle camera, and the Horror Face preset"
- **With reference:**
- > "I have a Soul ID character. Write 3 different scene prompts with her — office, party, rooftop"
- **Model question:**
- > "Should I use Kling 3.0 or Seedance 2.0 for a large-scale battle scene?"
- **Troubleshoot:**
- > "My image-to-video isn't animating, it's just static. What am I doing wrong?"
- ## The MCSLA Formula
- | Letter | Layer | Example |
- |--------|-------|---------|
- | M | Model | Kling 3.0 |
- | C | Camera | FPV Drone weaving through the alley |
- | S | Subject | A woman in a tactical jacket |
- | L | Look | Cinematic, cold blue shadows, 16:9 |
- | A | Action | She sprints, slides under a gate |
- ## Acknowledgements
- - [@vitaesomniastore-commits](https://github.com/vitaesomniastore-commits) — skill-authoring
- review of v3.40.0 against Anthropic's skill best practices
- ([#110](https://github.com/OSideMedia/higgsfield-ai-prompt-skill/issues/110)), which shaped
- v3.41.0.
- ---
- Built February 2026 · v3.42.0 (updated 2026-10-23) · Platform: [higgsfield.ai](https://higgsfield.ai)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.