jtydhr88/screenwriting-skills

Professional agent skills for screenwriting, television writing and dramaturgy

What it solves

This project provides a comprehensive set of 24 specialized agent skills designed to help AI assistants (specifically Claude Code and OpenAI Codex) perform professional-grade screenwriting, television writing, and dramaturgy. It bridges the gap between general LLM text generation and the rigorous technical requirements of professional scriptwriting across different mediums and cultural traditions.

How it works

The project consists of SKILL.md files that follow the agentskills.io standard. These files contain principles, checklists, and workflows distilled from 45 craft books and 23 volumes of published scripts.

Key technical features include:

  • Multilingual Runtime: The source instructions are written in Chinese, but the agents are instructed to deliver output in the user's requested language (English, Japanese, Korean, French, etc.) while maintaining industry-standard terminology (e.g., "logline", "act out").
  • Layered Organization: Skills are categorized into four layers: General Dramaturgy (medium-independent), Medium Layer (TV/Stage specific), Tradition & Trade (regional industry practices), and Master Corpora (analyses of specific masters like Chekhov or Ozu).
  • Cross-Agent Compatibility: The skills are designed to be installed once and work across both Claude Code and OpenAI Codex.

Who it’s for

  • Screenwriters and television writers looking for AI-assisted structural analysis, dialogue polishing, or series planning.
  • Dramaturgs and playwrights working with various theatrical traditions, including specialized Chinese opera systems (banqiang and qupai).
  • Writers adapting novels or IP into long-form series (particularly for the Chinese market).

Highlights

  • Deep Domain Expertise: Distilled from dozens of professional craft books and primary script corpora.
  • Comprehensive Coverage: Includes everything from basic plot points (Save the Cat) to complex series engines and "writers' room" workflows.
  • Specialized Stage Support: Detailed skills for Chinese opera, covering both the banqiang and qupai vocal systems.
  • Case-Study Driven: Includes tabulated analyses of works like Succession, The West Wing, and the plays of Chekhov.

Related

  • Project
    mozilla-ai/cq

    An open standard for shared agent learning that allows AI agents to store and retrieve structured knowledge to avoid repeating mistakes.

  • Project
    strands-agents/tools

    A comprehensive library of ready-to-use tools for AI agents, enabling them to perform file operations, web automation, memory management, and multi-agent coordination.

  • Project
    s2b-dev/smart-second-brain

    An open-source Obsidian plugin that adds semantic search, an interactive knowledge graph, and an AI agent to help users discover and connect their notes.

  • Project
    voidful/hung-yi-lee-skill

    A structured knowledge system that distills Professor Hung-yi Lee's teaching style and AI expertise into a knowledge graph and linguistic framework for AI assistants.