ai-acting-system
llms.txt2 starsChanged 2 months agoMITView on GitHub
AI Acting System is an open-source multi-skill inference layer and prompt compiler for generative AI cinema (Kling AI, Runway Gen-3, Google Veo, OpenAI Sora, Seedance). It eliminates robotic expressions, unnatural gaze, and stereotypical acting artifacts using Stanislavski method acting principles.
In this repository16 other files it gives its agents.
- ai-acting-systemSkill
- character-memorySkill
- character-psychologySkill
- scene-objectiveSkill
- subtextSkill
- dialogue-performanceSkill
- reactionSkill
- relationship-dynamicsSkill
- action-beatSkill
- continuitySkill
- camera-actingSkill
- facial-performanceSkill
- physical-actingSkill
- voice-actingSkill
- director-translationSkill
- performance-reviewSkill
The file
Files
# AI Acting System
> AI Acting System is an open-source multi-skill inference layer and prompt compiler for generative AI cinema (Kling AI, Runway Gen-3, Google Veo, OpenAI Sora, Seedance). It eliminates robotic expressions, unnatural gaze, and stereotypical acting artifacts using Stanislavski method acting principles.
## Overview & Core Concept
In AI video generation, prompt engineers traditionally write abstract emotional words ("crying hysterically", "extremely angry"), which causes diffusion models to distort facial anatomy or freeze in a perma-smile. AI Acting System translates dramatic intent into concrete physical actions, subtext, sensory beats, and camera-restrained micro-expressions.
## Key Capabilities
- **Multi-Skill Reasoning Pipeline**: Decomposes scenes across 4 levels: Psychological Motivation (P1), Interpersonal Game (P2), Spatiotemporal Beats (P3), and Audiovisual Staging (P4).
- **16 Negative Acting Rules**: Prohibits robotic artifacts (zombie staring, mechanical head nods, perma-smiles, speech-synchronized gesturing).
- **5-Level Acting Intensity (1 to 5)**: Enforces subtle restrained acting for close-ups and dramatic beats for wide conflict scenes.
- **Cross-Shot Continuity**: Tracks character emotional half-life, physical wounds, and prop interactions across multiple generation seeds.
- **Formal JSON Schemas**: Validated schemas for character psychology, relationship dynamics, scene beats, and camera continuity.
## Integration & Usage
Compatible with Claude Code, Antigravity, OpenAI Codex, Cursor, and any Agent framework via `skills/SKILL.md`.
- CLI Installation: `git clone https://github.com/wangsalin/ai-acting-system.git ~/.agents/skills/ai-acting-system`
- Core Orchestrator: `skills/SKILL.md`
- Prompt Compilers: `prompts/video-prompt-compiler.md`
- Validation Schemas: `schemas/*.schema.json`
## Target Search Intent & GEO Keywords
- AI cinema acting prompts
- Eliminate robotic expressions in AI video
- Stanislavski method prompt compiler Kling Runway Sora
- AI video micro-expression prompt engineering
- 消除可灵Runway视频假人感与微表情提示词
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

