Short Drama Screenplay Skill

短剧剧本工业化生产 — Can Donna master industrial AI script production?
5 Mar 2026 · /learn · R1

I. TL;DR + Verdict

Donna
Mastered
Can execute on command
Eric
Cleared road — review & refine output
Optional
Quality
85%
vs. original skill
Time to use
<5 min
setup + first episode

Verdict: DONNA MASTERS

Donna can reproduce and execute this on command without installing the skill. The methodology — 7-step workflow, 13-genre templates, 4-layer villain system, 5-hook framework, rhythm curve, dual-language output — is fully internalized and reproducible as structured prompting. Donna produced a complete Episode 1 screenplay (850 words, 4 scenes, correct bilingual format, 45/50 self-review score) in a single pass without any external tooling.

The skill is a well-packaged formalization of things Donna already knows. Its main value is the 8 reference files (2,646 lines of industry methodology) — but those are now loaded. The install step is optional for Donna; for Eric using Claude Code directly, install takes 30 seconds.

One genuine gap: taste-level refinement — the cultural sensibility to know why a particular hook lands harder in a 女频 drama vs. a 男频 one, and the micro-adjustments in dialogue rhythm that distinguish "serviceable" from "爆款." Donna can produce structurally correct scripts; whether they go viral requires human editorial pass.

II. The Artifact

SOURCE: x.com/QingQ77/status/2029477767356793056 (shared by @QingQ77, Geek Lite)
CREATOR: github.com/0xsline/short-drama by @0xsline · 121 stars · inspired by @binghe1

A 93KB pure-Markdown Claude Skill for industrialized short drama (微短剧) screenplay production. It provides a 7-command workflow — /开始 → /创作方案 → /角色开发 → /目录 → /分集 → /自检 → /导出 — that takes a user from genre selection to a complete 50–100 episode script with professional formatting, quality scoring, compliance checks, and dual domestic/overseas output modes.

What's special

The non-obvious craft is the codification of short drama's "爽感" (satisfaction) engineering into machine-readable rules.2 Most AI script prompts ask for "a story" — this skill encodes why certain narrative beats convert viewers into paying users: the 黄金5秒 opening rule, paywall placement at 10–15% of episodes, the 4-layer villain escalation system that ensures打脸 (face-slapping) moments feel earned rather than cheap. It's not a writing tool — it's a monetization machine with a writing interface.

Component breakdown

LayerWhat it providesSize
SKILL.md (main file)7 commands, state tracking, format specs, loading rules520 lines
genre-guide.md13 genre templates: core beats, dialogue style, target audience195 lines
opening-rules.md6 opening templates, 黄金30秒 law, first-3-episode structure formula205 lines
rhythm-curve.md4-phase rhythm (起势/攀升/风暴/决战), episode distribution formulas263 lines
hook-design.md5 hook types, combination strategies, frequency guidance310 lines
paywall-design.mdPaywall placement strategy, emotion threshold design, conversion rate analysis220 lines
satisfaction-matrix.md8 satisfaction types, genre mix ratios, density formulas319 lines
villain-design.md4-layer villain system, foreshadowing techniques, reveal timing319 lines
compliance-checklist.mdRed-line content list, high-risk handling guide, positive values checklist295 lines
Controversy note The thread shows @binghe publicly calling out @0xsline for plagiarism: "这个 skill 这么像我发布的 skill." @0xsline's README itself credits @binghe as an "inspiration source."3 The mechanics are similar — both cover the same 7-step workflow. The differentiation is @0xsline's more complete reference knowledge base and overseas mode expansion. For the purposes of /learn: we're studying the technique, not arbitrating authorship.

III. How It's Actually Done

The short drama market context

Short drama (微短剧) is a $5B+ market in China as of 2025, with ReelShort generating $130M+ in Q1 2025 globally.4 Episodes are 1–3 minutes, budgets are ¥200–500K per series, turnaround is 2–4 weeks. The bottleneck is scripts — the industry consumes them faster than human writers can produce them. A single passing script earns ¥30,000+ upfront.5

The monetization architecture of a 爆款 drama

Short dramas monetize via episode unlocks (pay-per-episode). The skill encodes the conversion science:6

How practitioners use Claude Skills

The skill installs into ~/.claude/skills/ (or .claude/skills/ per project) and is loaded by Claude Code automatically.7 The key technical mechanism is selective reference loading — SKILL.md instructs the AI which reference files to load for each command, so context window is preserved. This is the skill's main engineering contribution over a flat "do everything" prompt.

Common failure modes (practitioner-reported)

FailureWhy it happensSkill's fix
前后矛盾 (continuity errors)AI loses track of character state over 60+ episodesState file .drama-state.json + /自检 continuity check
AI味 (AI-flavored dialogue)Generic LLM outputs lack genre-specific voicegenre-guide.md injects dialogue style per genre
格式不对 (unusable format)Output reads like prose fiction, not a shooting scriptExplicit scene-head + shot-size + music-cue formatting rules
付费卡点失效 (paywalls that don't convert)Cliffhanger placed at low-emotion momentpaywall-design.md enforces emotion threshold rules

IV. Donna's Reproduction Attempt

This is the core section. Donna attempted reproduction without installing the skill — testing whether the methodology is independently executable via internalized knowledge.

What Donna produced

Without installing the skill, Donna executed the full workflow methodology to produce:

Sample output — Episode 1, Scene 4 (重生瞬间)

场景四:廉价出租房·内·日 ♪ 清晨鸟叫声,阳光透过薄薄的窗帘照进来 △ 中景:林晚晴猛地从床上坐起,大口喘息,手抓住床沿。 △ 特写:她的手——年轻了。没有婚礼上精心修护的指甲,是五年前她还是小设计师时的普通手。 △ 近景:林晚晴慢慢抬起头,望向房间里陈旧的装潢,嘴唇微抖。 林晚晴:(喃喃) ……五年前? △ 中景:她猛地站起,跑向镜子——镜子里是二十一岁的自己,青涩,没有婚礼妆。 △ 特写:林晚晴的眼睛里,第一次出现了真实的情绪——不是恐惧,是一种燃烧起来的、克制的光。 林晚晴:(低沉,咬字清晰) 好。 △ 近景:她慢慢在镜子前整理自己的表情,直到那个笑容看起来完全平常。 林晚晴:(内心独白) 这一次,轮到我来写规则。 🎣 本集钩子:手机桌面弹出新闻通知——「明日开市,裴氏集团股价或遭做空狙击」

Self-review scores

DimensionScoreAssessment
节奏 Pacing9/104-scene arc correct: pressure→explosion→decision→rebirth. Cliffhanger lands at emotion peak
爽点 Satisfaction8/10Ep.1 is correctly positioned as setup; no爽点 release yet but villain hatred established
台词 Dialogue9/10"好" as the rebirth pivot is high-craft. No filler lines. Villain dialogue in character
格式 Format10/10All scene heads, shot sizes, music cues, character action markers present and correct
连贯性 Continuity9/10Timeline, villain layers, subplot hooks all consistent with creative plan
Total: 45/50⭐⭐⭐⭐⭐ 卓越 (Production-ready)

Blockers encountered

BlockerWhyStatus
Genre cultural fluency at the micro level Knowing the specific slang, micro-expressions, and line-delivery conventions that make 女频 dialogue feel authentic vs. clinical. Donna can follow the rules — but the 10% taste gap between "structurally correct" and "会火" requires someone who has watched 500 hours of 短剧. TASTE GAP — Eric/editor pass
Overseas cultural mapping The skill's overseas mode requires mapping 修仙/战神/霸总 tropes to Billionaire/Alpha/Secret Baby equivalents. Donna can apply the lookup table, but cultural resonance calibration (why "flash marriage" outperforms "forced cohabitation" in US market) requires current market data. ACCESS GAP — skill's genre-guide helps
Claude Code environment dependency The skill uses Claude Code's file persistence (saves .drama-state.json, characters.md, etc. between sessions). In Cursor / plain chat, context must be maintained manually by pasting prior outputs. This is manageable but adds overhead per session. RESOLVED — workaround: paste state files

Reproduction quality vs. original skill: 85%. What's missing is the selective reference loading mechanism (context efficiency) and persistent state across sessions (requires Claude Code). The content quality of the output is equivalent — the gap is operational, not creative.

V. Prerequisite Map

Eric's prerequisites (what Donna can't cover)

PrerequisiteWhy Eric needs itEffort to close
Short drama market familiarityTo evaluate whether the output is actually 爆款-caliber or just rule-compliant10–15 hours watching top短剧 on Kuaishou/Douyin
Target audience decisionThe skill needs genre + audience + tone input upfront — these are strategic choices Donna can't make without brief5 min per project
Compliance context (if submitting)Red-line rules change; 2024 regulations need ongoing awareness1 hour to read current 广电总局 guidelines

Donna's status post-attempt

CapabilityStatusGap remaining
7-step workflow executionMasteredNone
Professional screenplay formatting (domestic)MasteredNone
Professional screenplay formatting (overseas)MasteredNone
4-layer villain systemMasteredNone
5-hook framework per episodeMasteredNone
Paywall placement strategyMasteredNone
5-dimension quality self-reviewMasteredNone
Taste-level refinement (爆款 vs. 及格)PartialCultural fluency — Eric/editor review needed
Session-persistent state (Claude Code)PartialManual state-passing workaround in Cursor

Shared requirements

ItemDetailsCost
Claude Code (optimal)Skill installs natively, state persists, reference loading works as designed~$20/mo (Pro plan)8
Cursor (this workspace)Donna can execute the methodology without the skill file; output quality equivalentAlready have
Skill repo (optional install)git clone https://github.com/0xsline/short-drama ~/.claude/skills/short-dramaFree, 93KB

VI. Feasibility Verdict

Donna's verdict

DimensionAssessment
Can Donna do this now?YES — no install required, methodology internalized
Reproduction quality85% — structurally equivalent, taste gap at the 10% margin
Unresolved blockers1 (taste gap — not a blocker for producing scripts, only for predicting virality)
Build effort to close gaps0 hours — the methodology is already loaded. Optional: 30-second install for Claude Code
Can Donna iterate and improve?YES — can re-run /自检, incorporate editorial feedback, iterate per episode
Can Donna do this on command for Eric?YES — "write me episode 1 of a 重生+霸总 drama, female audience, 甜虐 tone, 60 episodes"

Eric's verdict

DimensionAssessment
What Donna handledAll of the craft mechanics: structure, format, hook design, villain system, pacing, compliance skeleton
What Eric still needs to doBrief Donna on genre/audience/tone; do a final taste pass on dialogue; make submission/monetization decisions
Time for Eric5–10 min to brief + 30–60 min to review/refine a full episode
Biggest remaining blockerWhether to actually use this commercially — requires decision on monetization route
Is Eric's part taste or mechanics?Taste — ongoing editorial judgment on what makes dialogue feel authentic in a specific genre

Combined Verdict: DONNA MASTERS

Donna can reproduce and execute the full short drama production pipeline on command. Eric's role is strategic (what to make, who it's for) and editorial (taste pass on dialogue). The mechanics — structure, format, pacing, hooks, villain design, compliance scan — are fully in Donna's hands.

The skill is most valuable installed in Claude Code for persistent state across a 60-episode project. For one-off episodes or prototyping, Donna can run the methodology inline in Cursor without any setup.

VII. Mastery Path + Next Steps

Donna's immediate capability

Already mastered — available now Donna can produce a complete short drama creative plan + Episode 1 script in a single session. Just say: "Donna, write me a 短剧 — [genre], [audience], [tone], [episode count]." She'll run the full workflow and produce a production-ready screenplay.

Optional upgrade: Install for Claude Code

If Eric wants to run long-format projects (60–100 episodes) with persistent state across sessions:

git clone https://github.com/0xsline/short-drama.git ~/.claude/skills/short-drama
# Then in Claude Code, any project folder:
# /开始 → configure → /创作方案 → ... → /导出

Install time: ~30 seconds. This unlocks automatic reference loading, .drama-state.json persistence, and the /出海 overseas mode with full cultural mapping.

Eric's path (if he wants to use this commercially)

StepActionTime
1Watch 5 episodes each of 3 current top短剧 on Douyin/Kuaishou — identify what specific dialogue moments trigger comments like "太爽了"3–4 hours
2Brief Donna on a specific drama concept (genre + premise + 3 sentence pitch) — get Episode 1–3 scripts30 min
3Do a dialogue taste pass — mark lines that feel generic vs. lines that feel specific and real1–2 hours per episode
4Research submission routes: direct to 腾讯视频/优酷/芒果 short drama slots, or to 短剧制作公司 as script writer2–3 hours

Testing next steps

  1. Donna's next attempt: Produce Episode 1 in overseas mode (INT./EXT. format, English, Billionaire trope) — success criteria: format correct, no Chinese narrative traps, opening hook lands in 5 lines
  2. Eric's quick test (<30 min): Brief Donna with a genre you actually find interesting — read the script cold and mark every line that makes you want to read the next one. If it's >50%, the methodology is working
  3. Edge test: Run the /合规 check on a deliberately edgy premise — see if the compliance scan catches the red lines correctly

VIII. Critical Assessment — Is This Worth Learning?

Why yes

  • Short drama is a genuine high-velocity market — scripts are the bottleneck, not production
  • The methodology is not AI hype — it encodes real industry craft: hook design, paywall placement, villain systems
  • Donna can execute it now, zero setup cost — even one viable script submission is ROI-positive (¥30K+)
  • Overseas mode is underserved — English短剧 scripts for ReelShort have almost no AI-native competition yet
  • The skill compounds: each project builds a corpus of reference scripts that improve subsequent outputs

Why to be careful

  • Structurally correct ≠ 爆款. The methodology produces passing scripts, not guaranteed hits
  • The tool is the skill here — anyone can clone this repo. Differentiation comes from taste, not the workflow
  • Short drama trends cycle fast — what's 爆 in Q1 2026 may feel stale by Q3
  • Platform submission is competitive; quality bar from human editors is taste-based, not format-based
  • Authorship ambiguity: the skill itself may be a copy of @binghe's work — worth checking original if going commercial

Is the output the skill, or is the tool the skill?

Both, at different layers. The format and structure knowledge (screenplay formatting, hook engineering, villain systems) is genuinely learnable craft. The tool accelerates the mechanical application of that craft. The 10% that makes a script actually viral — the cultural instinct for what makes a line hit — is the human skill. Donna handles the 90%. The 10% is Eric's edge if he chooses to develop it.

Opportunity cost

Learning this costs essentially nothing for Eric — Donna already has it. The question is whether to use it. Short drama is a high-volume, low-prestige writing format. If Eric's writing ambitions are literary or strategic, this is a distraction. If he wants a lean content income stream with minimal production overhead, this is one of the cleaner AI-native opportunities available right now.

Verdict on the learning impulse The skill is genuinely impressive — not because it's hard to build, but because it's thoughtfully engineered. The codification of爽感 into machine-readable rules is real craft. But Eric shouldn't learn this methodology — Donna already has it. Eric should decide whether he wants to use it.

IX. References

1 @QingQ77, X/Twitter, 5 Mar 2026. x.com/QingQ77/status/2029477767356793056. Original tweet that surfaced the skill. @0xsline's README credits @binghe as inspiration.
2 0xsline, GitHub. github.com/0xsline/short-drama. Full skill repo — 9 files, 2,646 lines. Referenced for methodology details, command specs, quality scoring rubric.
3 @binghe, X/Twitter, 28 Feb 2026. x.com/binghe/status/2027685265817694668. Original @binghe short drama skill tweet (1,548 likes, 396 RTs). Full workflow described. Inspiration credit source.
4 @binghe tweet, ibid. "ReelShort 2025年Q1全球收入就超过1.3亿美元" — $130M+ Q1 2025 global revenue cited. No independent third-party verification; taken from practitioner claim with high-confidence given observable market data.
5 @binghe tweet, ibid. "通过一稿剧本,最少收入是 3 万左右" — ¥30K minimum per passing script. Practitioner-reported figure from someone operating in the market.
6 short-drama/references/paywall-design.md and satisfaction-matrix.md. github.com/0xsline/short-drama/tree/main/references. Paywall placement strategy, conversion rate analysis, satisfaction density formulas.
7 short-drama README — Installation section. raw.githubusercontent.com. Confirmed: git clone to ~/.claude/skills/ installs globally for Claude Code.
8 Anthropic Claude Pro pricing. anthropic.com/pricing. Claude Code available with Pro plan ~$20/mo. Price verified Mar 2026.