higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a locked voice prompt. Use whenever a prompt needs acting, performance, or emotion direction; whenever characters read wooden, dead-eyed, or 'AI'; whenever a character must stay themselves across many shots; or when the user asks for character behavior, mannerisms, tics, a gait, or how someone reacts. Pairs with higgsfield-facs (muscle-level AU codes) and higgsfield-seedance (the prompt the paragraph goes into).
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill /tmp/higgsfield-acting && cp -r /tmp/higgsfield-acting/skills/higgsfield-acting ~/.claude/skills/higgsfield-actingSKILL.md
# Higgsfield Acting Director
`[OFFICIAL — Higgsfield "Hell Grind" open-source brief]` — the performance system behind
Higgsfield's 95-minute AI feature film, adapted to this repo's prompt surfaces.
**The core axiom of the entire system: acting is BEHAVIOR under pressure, not a display of
emotion.** A character wants something, something is in the way, and they act to get it.
Emotion is a byproduct of that struggle — never the thing you write directly.
This is a **layer on top of** `../higgsfield-seedance/SKILL.md`: the paragraph this skill
produces goes into the PERFORMANCE / CHARACTER ACTING block of an otherwise normal Seedance
prompt. It does not change camera, light, wardrobe, or grade.
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Routing aids — read the linked sections for the rules.*
- Write the **objective** (a verb aimed at a partner), never the state — "make him confess", never "be angry" [→](#the-five-pillars-of-every-scene)
- **2–4 beat changes** per scene, each one visible in behavior: a pause, a posture change, a tempo change, a shift of gaze. Unchanged behavior for the whole shot = played flat [→](#the-five-pillars-of-every-scene)
- **Listening beats speaking.** The reaction starts *before* the partner's line ends; a hard question earns a micro-pause before the answer [→](#listening-and-reaction)
- The body carries the biography: **center of gravity, tempo, openness, breath** — set all four before any psychology [→](#the-body)
- **Business** — a physical task the hands are doing — kills theatricality; the strongest accent in a scene is the moment the character **stops** it [→](#the-body)
- **Distance is drama**; a change of distance *is* a beat change. Status is what you DO, and status **breaks** are the most interesting thing in a performance [→](#the-body)
- The **master profile** is 150–220 words, one paragraph, fixed block order, written once per character and then rewritten per scene — never pasted [→](#the-acting-master-profile)
- Every tic carries a **trigger**; every mask carries a **crack** — at least one "However, when X…" clause per profile [→](#the-acting-master-profile)
- **Eye life is mandatory and never optional** — saccades, blink quality, live catchlights, eyes-lead-thought. Dead eyes are the number-one tell of AI acting [→](#eye-life)
- Scene adaptation **transforms, never deletes**: a behavior that can't physically happen is displaced into another outlet, not removed [→](#scene-adaptation)
- The **voice prompt is locked** — one per character, pasted verbatim into the audio field, never adapted per scene [→](#voice-fixed-identity-never-adapted)
- **States, not transitions.** Models fail process and nail state: "mid-throw, arm extended", not "reaches in, pulls out, winds up" [→](#states-not-transitions)
- Ensemble reactions travel in a **wave, never in sync**; the strong are still and quiet, the weak fidget and shout [→](#ensemble-and-space)
- 15 named bad-acting symptoms with prompt-level fixes, and a 0–5 self-check scale — **aim every hero shot at 4+** [→](#the-atlas-of-bad-acting)
---
## Where this sits among the repo's performance tools
| Layer | Skill | What it controls |
|---|---|---|
| **Craft** — why the character does anything | **this skill** | objective, obstacle, tactics, beats, subtext, status, business |
| Muscle | `../higgsfield-facs/SKILL.md` | facial Action Unit codes (AU12, AU6…) |
| Named expressions | `../higgsfield-soul/SKILL.md` § Micro-Expressions | expression vocabulary for identity work |
| Production form | `../higgsfield-seedance/HELL-GRIND.md` § Two extra blocks | the CHARACTER ACTING block this output fills |
| Backstory | `../higgsfield-character-design/SKILL.md` | who the character is before any scene exists |
Use this skill to decide **what the body does**; use FACS to specify **which muscles** do it
in a close-up. They compose — a FACS beat schedule inside a paragraph written by these rules
is the highest-resolution performance the platform supports.
---
# Part I — The craft
## What good acting is
Truthful behavior under imaginary circumstances. Not depicted emotions, not recited text,
not "expressive faces."
| Bad acting | Good acting |
|---|---|
| Shows the emotion ("I am angry") | Pursues the objective ("I will make you return the money") — anger arises on its own |
| Waits for their cue | Listens and reacts to the partner every second |
| Body illustrates the words (gesture = word) | Body lives its own life, sometimes contradicts the words |
| All lines in one tempo and tone | Rhythm changes with every change of tactic |
| Emotion switches on at the line and off after | State is continuous — there is a life before and a life after the line |
| The face "performs" — eyebrows, grimaces | The face thinks — the thought is readable in the eyes before the words |
## The five pillars of every scene
Every character in every scene decomposes into five elements. If one is missing, the
performance falls apart.
**1. Objective.** What the character wants IN THIS SCENE, RIGHT NOW, FROM A SPECIFIC PERSON.
Always a verb aimed at the partner: *make him confess* · *beg a week's extension* ·
*convince her I'm not afraid*. Never a state ("be angry", "feel guilty") — states cannot be
played. Behind the scene objective sits a **super-objective**: what the character wants
across the whole story, with every scene objective a step toward it.
**2. Obstacle and stakes.** What prevents them — external (another character wants the
opposite; witnesses in the room; two hours to deadline) or internal (pride won't let them
beg; they don't believe their own words). Always answer *what happens if I do NOT get what I
want?* — and the answer must frighten the character. The higher the cost of failure, the
more taut the scene.
**3. Tactics.** The concrete method of pursuing the objective right now, as an action verb:
*press · charm · shame · plead · provoke · bargain · threaten · stall*. When a tacticGuided version bump — validate, tag, and create GitHub release
Run pre-release validation checks on all SKILL.md files and JSON databases
>
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles action scenes (combat, pursuit, stunts), general scenes (landscapes, journeys, atmosphere), and dialogue scenes (confrontations, negotiations, interrogations). Use this skill whenever the user wants to create a Seedance video prompt, describes a scene for video generation, mentions Seedance, or asks for a cinematic scene breakdown.
>
>
>
>