Skip to content
SkillScript-led3,065 tokens in use

short-drama-write

Writes or revises a single short-drama episode as one Markdown script with scene headings, dialogue and production tags, and can estimate its running time.

4,570 stars on the repository MIT Licensezenstory-ai/drama-skills · skills/short-drama-write
npx skills add zenstory-ai/drama-skills -y -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing short-drama-write costs

168tokens idle
3,065tokens in use
24,159tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/duration_estimate.py, scripts/screenplay_index.py, scripts/selftest.py.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter11/15
  • Structure16/25
  • Examples6/15
  • Output5/15
  • Size13/15
  • Resources8/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/screenplay_index.py, line 1253

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance100
  • Community52
  • Maturity20
  • Momentum40

short-drama-write turns an episode outline, a rough idea or an existing draft into a script that can be performed and filmed. The script lives in one file, 剧集/<EP>/剧本.md, with scene headings, action, dialogue, voice-over, sound effects, on-screen text and continuity notes.

The skill keeps an author’s own wording when polishing, reformats scripts that arrive in other layouts, and includes a Python estimator that counts spoken characters and action paragraphs to report running time. The skill is written in Chinese and is aimed at Chinese-language short drama and animated drama.

What You Get

  • A script file at 剧集/<EP>/剧本.md with an episode title, numbered scene headings, action, dialogue and production tags
  • Standard markers for voice-over, off-screen voice, sound effects, on-screen text, continuity notes and transitions
  • A rewritten or reformatted version of an existing script that keeps the original lines
  • An optional running-time report from the bundled estimator, with spoken characters, action paragraphs and voice-over share

Common Use Cases

  • Turning an episode outline into a full script ready for storyboarding
  • Continuing a series with the next episode that picks up the previous cliffhanger
  • Polishing a draft to remove machine-sounding lines while keeping the author’s tone
  • Converting a crew’s differently formatted script into the standard layout before production
  • Checking whether an episode fits its target running time

What Makes It Unique

It is one stage of a twelve-skill short-drama pipeline and stays inside that stage: only the script file is maintained, with no beat sheets, approval forms or status files beside it. A numbered rule set covers hooks, confrontations, dilemmas, countdowns and voice-over use, and the rules are marked as defaults, taste options or checked invariants. Time estimates are reported only from rates the project declares, and the estimator never invents seconds.

Under The Hood

The skill loads its SKILL.md and, when a situation calls for it, one of five reference documents on format, craft, dialogue and stage rules. The agent writes the script file in the project folder using its own model. The only code is a Python 3.9 estimator and indexer that read the script locally to count characters and paragraphs, plus a self-test run only at install time. The agent can run these Python scripts from the shell, and they read and write local files. The skill does not fetch web pages or call outside services.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers