⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
chekhov-dramaturgy
Writing plays and screenplays in the Chekhovian mode (契诃夫戏剧法) — distilled from the complete plays (没有父亲的人/普拉东诺夫, 伊凡诺夫, 林妖→万尼亚舅舅, 海鸥, 三姊妹, 樱桃园, nine one-acts) plus Chekhov's own letters, Stanislavsky's and Nemirovich-Danchenko's rehearsal notes and 焦菊隐/童道明 criticism. Covers the four-act mood-based structure without central climax, off-stage events, "correct answer stated in Act 1 and refused", the announced event that never happens, three-layer endings (hope monologue + nihilist line + household action), no-villain conflict with environment, every character's object and catchphrase, one-way love chains, half-step-off dialogue, philosophy cut by thirst, the shortest words for the deepest pain, stage-direction and sound discipline, and how Chekhov revised The Wood Demon into Uncle Vanya. Use when the user wants an ensemble drama, a "nothing happens" play, subtext-heavy dialogue, a family estate / provincial story, an anti-climactic structure, or asks how to "Chekhov-ize" a script.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
screenwriting-skills
26 agent skills (for Claude Code and OpenAI Codex) for screenwriting, television writing and dramaturgy, distilled from 47 craft books and 23 volumes of published scripts, scores and plays (Chinese, American, British, Japanese and Korean).
The skill files follow the open agentskills.io standard and are shared by both agents: install once and it works in both.
Ask in your own language. The skill bodies are written in Chinese, because most of the sources are Chinese originals or Chinese translations. That is only where the text lives: ask in English, Japanese, Korean or French and you get the answer in that language. See Multilingual support for why there is a single source tree.
Install
Claude Code
Plugin marketplace (recommended)
/plugin marketplace add jtydhr88/screenwriting-skills
/plugin install screenwriting@screenwriting-skills
Skills are then invoked as /screenwriting:<skill>, e.g. /screenwriting:sw-dialogue.
Personal (all projects)
git clone https://github.com/jtydhr88/screenwriting-skills.git
cp -r screenwriting-skills/plugins/screenwriting/skills/* ~/.claude/skills/
Project-specific
mkdir -p .claude/skills
cp -r screenwriting-skills/plugins/screenwriting/skills/* .claude/skills/
Verify
Skills load automatically when the agent detects relevant context. To list them: /skills.
Codex (CLI / ChatGPT desktop app / IDE extension)
Plugin marketplace (recommended)
codex plugin marketplace add jtydhr88/screenwriting-skills
# Then, in the ChatGPT desktop app or Codex CLI:
# Plugins → select "Screenwriting Skills" → Install
The same 26 skill files are shipped through the plugin, with no duplication and no rewriting.
Personal skills (all projects)
git clone https://github.com/jtydhr88/screenwriting-skills.git
cp -r screenwriting-skills/plugins/screenwriting/skills/* ~/.agents/skills/
Project-specific
mkdir -p .agents/skills
cp -r screenwriting-skills/plugins/screenwriting/skills/* .agents/skills/
Verify
Run /skills to list available skills, or invoke one explicitly with $sw-story-structure.
Usage examples
# "Break my 12-episode series into acts and place the act outs"
# → agent uses sw-series-structure
# "My dialogue is all on the nose, fix this scene"
# → agent uses sw-dialogue + sw-scene-craft
# "Turn this 400,000-word novel into a 40-episode Chinese drama outline"
# → agent uses sw-chinese-series-practice + sw-series-engine-bible
# "Set up a project and keep track of where I am"
# → agent uses sw-workflow
Multilingual support
One source tree, every language at runtime. The skills are written once, in Chinese, and the agent delivers in whatever language you asked in.
This is a deliberate decision, and it was not the first one. There was an English edition once, a parallel screenwriting-en plugin with all 20 skills translated. It was proposed in #3, built, and merged. It has since been removed. The argument that killed it is the one that applies equally to every other language: if a reader who cannot read Chinese deserves a translated tree, so does a reader who cannot read English, and the next request is Japanese, then Korean, then French, then Russian. Five languages is 230 files that drift independently, with nothing to tell you which one is stale. The translation itself is cheap. The real cost is that forking once removes any principled ground for refusing the second fork.
So the line is drawn at the source, and the runtime does the rest:
- Output language follows your question. Ask in French, get French. No flag, no separate install.
- Terminology is anchored to the original term. The craft vocabulary of this field is originally English: logline, act out, beat sheet, showrunner, staff writer. The Chinese in the source books (计程绳, 出幕, 节拍表, 剧目管理人, 试用编剧) is the translation, and different translators chose differently. The term table in
sw-workflowmaps each concept back to its original term, so the agent restores the word. The same table serves all languages at once, because a Japanese or French screenwriter also says act out and logline. - Terms with no equivalent keep their original form plus a gloss. 戏眼, 扣子, ト書き and 決定稿 come through as
戏眼 (xìyǎn — the one-line core attraction of an episode). - Your script stays in your script's language. Discussing a Chinese screenplay in English is normal; the conversation switches language, the draft does not.
What this trades away is auditability: you cannot read the instruction file itself unless you read Chinese, only the agent's account of it. That is a real cost, and it is the one thing the deleted English edition genuinely bought. It was not worth a permanent five-way maintenance burden.
READMEs are a different matter and are translated, because they are short, stable, and the thing a newcomer meets first. The Japanese, Korean and French READMEs deliberately stop at install, structure and this policy; the full skill tables and the source bibliography live here and in the Chinese README, for exactly the reason above.
How the skills are organised
Four layers. A feature project uses layers 1, 3 and 4; a series or stage project adds layer 2, because the medium layer replaces structure-for-film with the medium's own units.
1. General dramaturgy premise · structure · character · dialogue · scene · format · Truby organic anatomy · genre anatomy · project workflow
2. Medium layer series · episode & season structure · engine & bible · writers' room · half-hour comedy
stage · Chinese opera: banqiang and qupai methods, each with a full-script case library
3. Tradition & trade America · Japan · Korea & France · mainland China · the business
4. Master corpora Chekhov · Ozu · Succession · television case studies
1. General dramaturgy (medium-independent)
| Skill | What it covers | Main sources |
|---|---|---|
sw-workflow | Project orchestrator: a feature/stage stage-map (premise → structure → character → scenes → draft → revision → submission) and a separate series stage table (S0–S7: engine → character web & season arc → documents → pilot structure → break story → draft → submission), naming which skill to call at each stage, per-stage deliverables and advisory exit checks, plus a story-bible convention (with a series supplement) that keeps project state in one file across sessions | meta-skill, no new sources |
sw-story-structure | Paradigm & plot points, Save the Cat beats and board, McKee's event/scene/sequence/act, inciting incident, progressive complications, crisis-climax-resolution, subplots, Hoxter's nine beats, Hicks' attraction/anticipation/satisfaction, Lu Jun's 起承转合, eight openings, eight endings | Field, Snyder, McKee Story, Hoxter, Hicks, Lu Jun |
sw-premise-theme | Premise as tyrant, controlling idea (value + cause), the "third rail" (desire vs misbelief), five premise questions, logline tests, 选材/开掘/视角/戏核 | Egri, McKee, Cron, Hicks, Hoxter, Snyder, Lu Jun |
sw-character-conflict | Three-dimensional character, orchestration, unity of opposites, pivotal character, rising vs static vs jumping conflict; Freud/Erikson/Jung/Campbell/Murdock/Adler/May for motive; 人物要活八要, 对手要强 | Egri, Indick, McKee, Hicks, Cron, Snyder, Lu Jun |
sw-dialogue | Dialogue as action, said/unsaid/unsayable, exposition as ammunition, beats as gerunds, credibility/language/content/design flaws, character-specific vocabulary; 语言要美, 戏曲唱词三好 | McKee Dialogue, Walter, Hicks, Lu Jun, Egri, Snyder, |
// HOW IT'S BUILT
KEY FILES